Forthcoming articles

 


International Journal of Biomedical Engineering and Technology

 

These articles have been peer-reviewed and accepted for publication in IJBET, but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

 

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

 

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

 

Articles marked with this Open Access icon are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

 

Register for our alerting service, which notifies you by email when new issues of IJBET are published online.

 

We also offer RSS feeds which provide timely updates of tables of contents, newly published articles and calls for papers.

 

International Journal of Biomedical Engineering and Technology (192 papers in press)

 

Regular Issues

 

  • Statistical method for ECG analysis and diagnostic   Order a copy of this article
    by Hanen Chaouch Jebril, Khaled Ouni, Lotfi Nabli 
    Abstract: In this paper, a statistical method of ECG analysis and diagnostic is proposed. This method is based on three parts: data simplification using multiscaled PCA, faults detection and localization by introducing classic linear PCA. The studied data is presented as a multivariate matrix. The variables of this matrix are extracted from the ECG waves characteristics: waves amplitudes and segments measurements. The developed approach allows detecting arrhythmias and heart beat troubles. Comparing the results obtained by this approach and the data of the expert, we approve the performance of our study.
    Keywords: ECG diagnostic;mutiscaled PCA; fault detection;fault isolation;arrhythmia.

  • Gray scale and color Medical Image Compressed using hybrid Contourlet Biorthogonal CDF lifting scheme, bandelet and Quincunx wavelet Transforms : A comparative study   Order a copy of this article
    by Ismail Boukli Hacene, Abdelhafid Bessaid 
    Abstract: The Quincunx wavelet , the lifting Scheme wavelet and the Second generation bandelet transform are a new method to offer an optimal representation for image geometric. In the field of medical diagnostics, interested parties have resorted increasingly to medical imaging. It is well established that the accuracy and completeness of diagnosis are initially connected with the image quality, but the quality of the image is itself dependent on a number of factors including primarily the processing that an image must undergo to enhance its quality. The quality evaluation of compressed image is necessary to judge the performance of a compression method. This paper introduces an algorithm for medical image compression based on hybrid Nonsubsampled contourlet (NSCT) and quincunx wavelet transforms (QWT) coupled with SPIHT coding algorithm, of which we present the objective measurements (PSNR, EDGE, WPSNR, MSSIM, VIF, and WSNR) in order to evaluate the quality of the image.
    Keywords: Medical image; NSCT;QWT; Biorthogonal wavelet 9/7; lifting scheme ; Bandelet transform;Compression;SPIHT coder;Objective measurements.

  • ECG Beat Classification using Machine Learning Techniques   Order a copy of this article
    by Shweta Jambukia, Vipul Dabhi, Harshadkumar Prajapati 
    Abstract: An arrhythmia is an abnormality in the heart rhythm, or heartbeat pattern. ECG beats can be classified into six different arrhythmia beat types (left bundle branch block, right bundle branch block, paced beats, premature ventricular contradiction, atrial premature beats, and normal rhythm). Early and accurate detection of arrhythmia types is important in detecting heart diseases and choosing appropriate treatment for a patient. This paper proposes a combination of Particle Swarm Optimization (PSO) and Feed Forward Neural Network (FFNN) for ECG beat classification. We have used MIT-BIH arrhythmia database for data collection and prepared three different datasets. Features, such as R peak sample number and QRS complex, are extracted using Pan-Tompkins algorithm. The extracted features are used as inputs to three different classifiers: MultiLayer Perceptron Neural Network (MLPNN), Support Vector Machine (SVM), and PSO-FFNN. Results show high classification accuracy of over 97 % with either of these three classifiers. The performance comparison of these classifiers is carried out using three measures: sensitivity, specificity, and accuracy. The results suggest that PSO-FFNN shows slightly better performance than MLPNN and SVM in terms of accuracy on all datasets.
    Keywords: ECG beat classification; Particle Swarm Optimization; Neural Network; Support Vector Machine; RR Interval; QRS Complex.

  • FEATURE LEVEL FUSION USING PHYSICAL BIOMETRIC TRAITS   Order a copy of this article
    by Jerusalin Carol J, Lenin Fred A 
    Abstract: Biometric is a measuring technique that is utilized to discern a persons identity through a physiological or behavioral feature. Each modality on its own cannot always be reliable for recognition. The multimodal biometric system offers several advantages over the traditional biometric system. In order to overcome the limitations of the unimodal biometrics, the fusion of multimodal biometric traits have been used. In this paper, a multi-modal biometric based on fingerprint, palm print and knuckle print is presented. Gabor filter is employed to extract features from these biometric traits. The features extracted from these biometric traits are normalized and fused together. The features are fused by feature level fusion and the result of the proposed method provides efficient authentication, by minimizing the FAR by 1.43% and the framework achieves satisfactory performance.
    Keywords: Biometric; fingerprint; palm print; knuckle print; Minutiae-based matching; Gabor filter.

  • A Non-invasive Approach for the Diagnosis of Type-II Diabetes Using HRV Parameters   Order a copy of this article
    by Marykutty Cyriac, Sankar P 
    Abstract: As per the records of World Health Organisation, diabetes is currently one of the major diseases faced by the world community. This necessitates the introduction of screening tools for diabetes. In this paper, a non-invasive approach is proposed to diagnose the presence of Type-II diabetes by analysing the relationship between the Heart Rate Variability (HRV) parameters and the arterial blood glucose changes. The HRV analysis is performed using nonlinear methods such as Detrended Fluctuation Analysis (DFA) and Poincare plot. A few parameters derived from these nonlinear methods are used to introduce two metrics named as Standard Deviation Ratio (SDR) and Alpha-ratio. These two metrics are given as input to a machine learning classifier to categorize the subjects as diabetic or non-diabetic. The accuracy analysis of the classification results shows that 94.7% of the subjects are categorized correctly. Therefore, the proposed metrics can be considered as non-invasive screening tools in predicting the presence of Type-II diabetes.
    Keywords: Alpha-ratio ; Detrended Fluctuation Analysis; Heart Rate Variability; Poincare Plot ; Standard Deviation Ratio.

  • Efficient Speech Recognition System for Hearing Impaired Children in Classical Tamil Language.   Order a copy of this article
    by Lakshmi Chelliah, Revathi Dhanabal 
    Abstract: This paper presents the development of the robust speech recognition system for the children with hearing impairment. It is a challenging task to recognize the distorted speeches of the hearing impaired since the characteristics of the speeches uttered by these people normally have variations in terms of accent, pronunciation and speed. Because of their inability to hear, they are not able to speak even though their nasal and oral cavities aiding for the speech production are perfect like normal persons. This work mainly emphasizes the use of MFCC & MF-PLP features at the front end and HMM & K means clustering at the back end. Performance of the system is evaluated and compared for the two modelling techniques and recognition accuracy is 94%, 97% and 84% for MFCC with HMM and accuracy is 98.3%, 93.5% and 93.6% for MF-PLP with K means clustering for recognition system developed for recognizing isolated digits, connected words and continuous speeches of Hearing impaired. Noteworthy point to be mentioned is that though the clustering technique is an old technique, it is proved that it gives better results as compared to HMM.
    Keywords: HTK (Hidden Markov Model tool kit); Mel frequency Perceptual linear predictive cepstrum (MFPLPC); MFCC (Mel frequency cepstral coefficients); Hearing impaired (HI); Normal Hearing (NH); Recognition accuracy (RA).

  • Hybridization of Feed Forward Neural Network and Self Adaptive PSO with Diverse of Features for Anomaly Detection   Order a copy of this article
    by A.R. Revathi, Dhananjay Kumar 
    Abstract: The present paper describes a hybrid SLPSO-FFNN based model for the anomaly detection in video frames. The proposed hybrid model combines the feed forward neural network, which has been successfully detecting the anomaly present in the video, with the use of SLPSO techniques. In the core technology, four critical processing phases are mainly discussed: Back ground Estimation (BE) phase, Object Segmentation (OS) phase, Feature Extraction (FE) phase, and Activity Recognition (AR) phase. At first, we generated the high quality back ground using Background Estimation (BE) phase. After a high-quality background is generated, the OS model is developed to extract the object from the videos and then object tracking process is used to track the object through the overlapping detection scheme. From the tracked objects, the FE module extracts some useful features such as Tamura features, SFTA features, Haralick features, etc., Finally, SLPSO-FFNN based approach is used to detect the anomaly present in the videos. Experiments are performed on the USCD and CDNET benchmark dataset of abnormal activities and comparisons with the state-of-the-art methods validate the advantages of our algorithm. In experimentation, we use two types of dataset UCSD pedestrian dataset (Ped_1, Ped_2) and CDNET dataset. The experimental result shows our proposed anomaly detection system obtains the minimum Equal Error Rate (EER) of 0.1% and achieves the maximum accuracy of 97.64%.
    Keywords: Anomaly detection; EER; SLPSO-FNN; Tracked object; Object segmentation; Background.

  • Classification of ECG signals using cross recurrence quantification analysis and probabilistic neural network classifier for ventricular tachycardia patients   Order a copy of this article
    by Shipra Saraswat, Geetika Srivastava, Sachidanand Shukla 
    Abstract: Ventricular Tachycardia (VT) is one of the leading causes of sudden cardiac death in the world. Prediction of VT is usually diagnosed by using Electrocardiogram (ECG) and requires expeditious treatment which reduces the mortality rate. The cross recurrence plot (CRP) toolbox is used for computing the recurrence rate values for both (healthy and unhealthy) subjects and artificial neural network (ANN) toolbox in Matlab is used for generating the accurate results. Radial basis function neural network (RBFNN) is used for designing the probabilistic neural network classifier for discriminating the normal from abnormal (VT) signals based on the recurrence rate values. This paper illustrates the cross recurrence quantification analysis (CRQA) of ECG signals followed by the decomposition method using discrete wavelet transform (DWT) for the analysis of cardiac disorders with sensitivity, specificity of 98.5% and 97.6% respectively and overall accuracy achieved is 98.7%. This paper is useful in adopting automated approach for detecting the cardiac arrhythmias efficiently.
    Keywords: Electrocardiogram; Artificial Neural network; Ventricular Tachycardia; Cross Recurrence Quantification Analysis; Ventricular Arrhythmia; Ventricular Flutter; Ventricular Fibrillation; Ventricular Tachycardia; Discrete Wavelet Transform; MIT-BIH; Daubechies; Probabilistic neural network.

  • Low Power and Adjustable Biomedical Sensor Interface System   Order a copy of this article
    by Saed Moradi, Esmaeel Maghsoudloo, Abdolrasoul Ghasemi, Mostafa Haghi 
    Abstract: Advances in CMOS technology, communications, and low power architectures have spurred considerable interest in implantable biomedical devices. The sensor interface is one of the critical building blocks in an implantable device. The main challenge in design of biomedical sensor interfaces is the nature of physiological signals. The amplitude range of physiological signals varies between 50 - 500
    Keywords: biomedical device; implantable devices; sensor interface; current mode; signal converter.

  • Effect of Magnetic field and rotation on the micropolar fluid model of blood flow through stenotic arteries.   Order a copy of this article
    by Ajaz Ahmad Dar, K. Elangovan 
    Abstract: The problem of blood flow through a horizontal nonsymmetric artery with a mild stenosis has been investigated. Blood is modelled as a homogeneous and incompressible micropolar fluid. The effect of both rotation and magnetic field are studied analytically and computed numerically. To evaluate the influence of the stenosis shape, an appropriate geometry has been considered such that the shape of the stenosis can be changed simply just by varying a parameter (referred to as the shape parameter). The expressions for the flow characteristics such as velocity, the impedance (resistance to flow), the wall shear stress distribution and its magnitude at the stenosis throat have been derived and analyzed for different values of shape parameter n, rotation parameter, the magnetic field parameter M, the coupling number N and the micropolar fluid parameter m.
    Keywords: Micropolar fluid; Magnetic field; Blood Flow; Rotation; Stenosed Artery.

  • Contour and region characterization of breast tumor masses with fractal and statistical attributes   Order a copy of this article
    by K. Khemis, S.A. Lazzouni, M. Messadi, A. Bessaid 
    Abstract: Breast cancer continues to rank at the forefront of public health problems. Characterization of breast tissue is a step in computer aided diagnosis, so we focus on it considering in particular texture and contour analysis of tumor masses with fractal and statistical approaches. Fist we extracted the mammographic mass with the mathematical morphology segmentation tool Watershed Line algorithm. Then we calculated fractal dimension of the mass contour using box counting algorithm. In addition to that we measured textural attributes from the gray level co-occurrence matrix of the segmented image (region). Finally, we used Support Vector Machine classifier evaluated in K-fold cross-validation mode with OneVsOne strategy considering multiclass classification: Benin masses/Malignant masses. As a result we obtained a classification rate of 98%.
    Keywords: Mammography; Fractal; Texture; Gray Level Co-occurrence Matrix; contour; Watershed Line; Characterization; Classification; SVM.

  • Maximization of Arrhythmia Classification Accuracy by Addressing Class Overlap and Imbalance Problem   Order a copy of this article
    by Rekha Rajagopal, Vidhyapriya Ranganathan 
    Abstract: Automation in arrhythmia classification helps medical professionals to make accurate decisions upon the patients health. Classification becomes complicated when class overlapping and class imbalance problem occurs together. The aim of this work is to improve the arrhythmia classification accuracy. Proposed methodology consists of fisher discriminant ratio based feature ranking stage and anomaly detection based training sample selection stage followed by classification using probabilistic neural network classifier. As per the recommendations of the Association for the Advancement of Medical Instrumentation, five arrhythmia classes were classified. The proposed method resulted in average sensitivity, positive predictive value and F Score of 95.37%, 98.35% and 96.72% respectively. The experimental results revealed that: (1) Selected non-overlapping features were able to better discriminate arrhythmia classes (2) Mixture of Gaussians based anomaly detection method suited well to handle the class imbalance problem (3) Minority classes with few training samples were also correctly classified using the proposed method.
    Keywords: Arrhythmia classification;Feature Selection;Class overlap;Class imbalance;Probabilistic neural network classifier;AAMI;MIT_BIH arrhythmia database.

  • New algorithm for the estimation of the Electrocardiogram derived respiration signal   Order a copy of this article
    by Bachir M’hamed Saadi, Benali Medjahed Oussama, Hadj Slimane Zine-Eddine 
    Abstract: Recently, ECG-derived respiration methods (EDR) have become a widely used tool in respiratory monitoring. In this paper, four new methods are presented for EDR signal estimation. The first two methods we have developed are based on ECG interval and QRS energy measurement. A wavelet transform method, based on the Mexican-Hat wavelet is also used in the present study. The final EDR signal method we have proposed is obtained by summing the first three estimated ECG-derived respiration signals. Correlation and magnitude squared coherence coefficients are used to evaluate the performance of the proposed EDR techniques. Compared to other recent works cited in the literature, the proposed algorithms allow to achieve high estimation performances.
    Keywords: ECG-derived respiration; Electrocardiogram signal; Respiratory signal; QRS energy; Mexican-Hat wavelet

  • Heart Disease Classification System using Optimized Fuzzy Rule Based Algorithm   Order a copy of this article
    by G. Thippa Reddy, Neelu Khare 
    Abstract: Heart disease prediction and identification is a difficult task which needs much experience and knowledge. In order to predict the heart disease, we introduce a technique named as RBFL prediction algorithm. The overall process of the RBFL prediction algorithm is divided into two main steps, such as 1) feature reduction using LPP algorithm 2) Heart disease classification by means of rule based fuzzy classifier. Initially, LPP algorithm is employed to recognize the related attributes and then fuzzy rules are produced from the FFBAT algorithm. Next, the fuzzy system is designed with the help of designed fuzzy rules and membership functions so that classification can be carried out within the fuzzy system designed. At last, the experimentation is performed by means of publicly available UCI datasets, i.e., Cleveland, Hungarian, Switzerland datasets. The experimentation result proves that the RBFL prediction algorithm outperformed the existing approach by attaining the accuracy of 76.51%.
    Keywords: heart disease prediction; FFBAT; RBFL; fuzzy logic classifier; feature reduction; LPP; membership function.

  • Hermite transform and support vector machine based analysis of schizophrenia disorder in magnetic resonance brain images   Order a copy of this article
    by Latha M, Kavitha G 
    Abstract: Schizophrenia is a brain disorder characterized by disturbances in cognition and emotional responsiveness resulting in disorganized speech, thinking and behavior. Magnetic resonance imaging (MRI) is used to capture structural abnormalities in brain regions. In this work, an attempt has been made to analyze Schizophrenia (SZ) disorder using Steered Hermite transform with support vector machine. First, the normal and abnormal images are subjected to skull stripping process to remove the non-brain tissue using non-parametric region based active contour method. The skull stripping results obtained from non-parametric region based active contour is compared with BET and BSE methods. The skull stripped images are subjected to Steered Hermite transform and are analyzed. Statistical features such as mean, energy (E0, E1, E2 and E3), entropy and homogeneity are obtained from the transform coefficients. The significant features are selected based on maximum relevance ranking and subjected to classification using Support Vector Machine (SVM), Na
    Keywords: Keywords— Schizophrenia, Steered Hermite transform, non-parametric region based active contour, feature selection, classifier, SVM, Magnetic Resonance images

  • Motor Imagery Classification from human EEG Signatures   Order a copy of this article
    by Rohtash Dhiman, Priyanka ., J.S. Saini 
    Abstract: Brain Computer Interface (BCI) systems translate the imagination in the human brain to an action in real world by means of machines. These systems can prove to be a blessing for severely impaired patients in terms of BCI prosthetics. This paper proposes a motor imagery classification system based upon Wavelet Packet Decomposition (WPD) and Support Vector Machine (SVM). The wavelet packet transform is used for both selection of sensory motor frequency band and feature extraction. The publically available BCI competition-IV data set-I has been used to evaluate the performance of the proposed scheme. The classification results obtained outperform the previously reported results of the technique Noise Assisted Multivariate Empirical Mode Decomposition (NA-MEMD) for subjects a and b, where a and b refers to two subjects from BCI competition data set-IV.
    Keywords: Brain Computer Interface (BCI); Wavelet Packet Decomposition (WPD); Support Vector Machine (SVM); Approximate Entropy (ApEn).

  • Multimodal Medical Image Fusion using Multiresolution Transform   Order a copy of this article
    by Abdelfatih Bengana, Mohammed Amine Chikh, Ismail Boukli Hacene 
    Abstract: Multimodal image fusion is used to enhance the quality of fused image in medical diagnosis by combining two images same scene from different techniques, such as Computed Tomography (CT) scan or Magnetic Resonance Imaging (MRI) with Positron Emission Tomography (PET). This paper, we presents a hybrid technique using Nonsubsampled contourlet for contrast-enhancement to balances the requirement of local and global contrast enhancements of each input image appearance and biorthogonal CDF9/7 wavelet based on lifting scheme. Then the low frequency subbands are combined by a maximal selection rule and the high frequency subbands are combined by a maximal spatial frequency. In this technique, the proposed scheme is free from the common shortcomings of the state-of-the-art MIF techniques: contrast reduction, loss of image fine details and unwanted image degradations etc. Subjective and objective evaluations show better performance of this new approach compared to existing techniques. (MI), entropy (EN), spatial frequency (SF), and standard deviation (STD) for image result. This shows that the quality of fused image was better compared with existing methods in case of hybrid method.
    Keywords: Image fusion; Medical image; Multi-scale transforms; Wavelet CDF9/7; Lifting scheme; NSCT.

  • Computer Aided Diagnosis of Breast Cancer in Digital Mammograms   Order a copy of this article
    by Laxman Singh, Zainul Abdin Jaffery 
    Abstract: Breast cancer continues to be a major health problem in the world. Detection of breast cancer at an early stage can reduce the mortality rate in women. Calcifications and masses are treated as the early sign of breast cancer. However, it is difficult to distinguish mass regions from surrounding tissues due to their low contrast and ambiguous margins and their classification is even more challenging. This paper presents a computer aided diagnosis (CAD) system to classify the masses into benign and malignant using artificial neural network (ANN). The gray level and texture features are used as an input to the ANN. The proposed system achieved the sensitivity of 92.6% and specificity of 93.3% with a classification accuracy of 92.9%.
    Keywords: Breast cancer; mammograms; artificial neural network; principal component analysis.

  • Discrete wavelet transform analysis and empirical mode decomposition of physiological signals for stress recognition   Order a copy of this article
    by Khadidja Gouizi, Fethi Bereksi Reguig, Choubeila Maaoui 
    Abstract: Stress is universally known to be a contributing factor the developing of many diseases. Various modalities have been employed for the detection of stress. Most research on stress recognition has focused on the analysis of speech, facial expressions or physiological responses. This work focuses on developing a user-independent and user-dependent stress recognition system using five physiological signals that are Electromyogram, Galvanic skin response, Skin temperature, Blood volume pulse and Respiratory response. Emotional data is collected from 33subjects by using Stroop game. These are processed using Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) in order to extract some features which are used in recognizing emotions. The mean and the standard deviation of approximation and detail coefficients are calculated. Also, decomposition of physiological signals into intrinsic mode functions (IMFs) by the EMD method is done. Then, extraction of instantaneous amplitude and instantaneous frequency of each IMF is carried out. The extracted features using both methods indicate significant differences between stress and relax states. With the Support Vector Machine (SVM), the classification results show a better accuracy using the DWT method compared to those of the EMD method. For the user-independent study an overall classification accuracy of 60.9% in stress recognition is reached whereas for the user-dependent study an overall classification accuracy of 80% is achieved. Also, recognition rate for both stress and relaxation separately can achieve 100%. In addition, overall recognition rates attain 100% when using the DWT. Therefore, these results show the reliability of the proposed system in stress recognition area.
    Keywords: Physiological signals; discrete wavelet transform; empirical mode decomposition; stress recognition; Support vector machine

  • Noise Estimation and reduction in heart sounds Using Time frequency Block thresholding method   Order a copy of this article
    by Vishwanath Shervegar, Ganesh Bhat 
    Abstract: In this paper a novel method of de-noising phonocardiogram by time-frequency Overlapping Group Shrinkage method is described. In this method sigma, the standard deviation of the stationary noise present in a noisy phonocardiogram is found using activity detection. This noise is then canceled by attenuating it in the time frequency domain. The accuracy of noise reduction is measured by SNR. Overlapping Group shrinkage algorithm reduces the effect of noise by attenuating them using hard or soft thresholding. Performance of this method was found to be far better compared to other methods such as Soft Thresholding and Block Thresholding.
    Keywords: Block thresholding; Activity detection; soft thresholding; overlapping group shrinkage.rnrn.

  • FUZZY WEIGHTED HISTOGRAM EQUALIZATION FOR CONTRAST ENHANCEMENT OF MAMMOGRAM IMAGES   Order a copy of this article
    by Magudeeswaran Veluchamy, K. Balasubramanian 
    Abstract: The early detection of breast cancer in the mammograms is very important in the field of medicine. Histogram equalization is mainly used for contrast enhancement. The histogram equalization (HE) usually results in excessive contrast enhancement because of lack of control on the level of enhancement. A novel technique, Fuzzy Weighted Histogram Equalization (FWHE) for Contrast Enhancement of Mammogram Images is presented in this paper. The proposed method consists of three stages. First, the gray level intensities of the original mammogram image are transformed to fuzzy plane and the amount of fuzziness is adjusted by using contrast intensification operator. In the second stage, the Probability Distribution Function (PDF) of the fuzzy matrix is modified by applying weighting and thresholding and then, the HE procedure is applied to the fuzzy plane of the mammogram image. Finally, the fuzzy plane is de-fuzzified to get contrast enhanced mammogram image. From the qualitative and quantitative measures, it is interesting to see that the proposed method provides optimum results by giving better contrast enhancement and preserving the local information of the original mammogram image.
    Keywords: Contrast Enhancement, Histogram Equalization, Entropy, Contrast Improvement Index, Mammogram images, Micro calcifications.rn

  • Feature Extraction using Pythagorean Means for Classification of Epileptic EEG Signals   Order a copy of this article
    by Muhammed Shanir P P, Sadaf Iqbal, Yusuf U. Khan, Omar Farooq 
    Abstract: Electroencephalogram (EEG) is a widely used tool for the study and diagnosis of epilepsy. The patients subjected to epilepsy require long term monitoring of EEG. Automatic seizure detection will eliminate chances of missing any seizure, make detection easy and reduce burden on physicians. In this work, different combination of Pythagorean means (time domain features) namely arithmetic (AM), geometric (GM), and harmonic (HM) mean of energy per epoch are used as features to classify EEG data into normal, seizure free and seizure classes by using a linear classifier. The classification accuracy of 100% is achieved in two and three class problem with a single feature/epoch and in five class problem with two features/epoch. The novelty of this work is use of new and simple features (in epileptic EEG signal classification), reduced complexity and high performance.
    Keywords: EEG; Epilepsy; Seizure; Time domain analysis; Pythagorean mean.

  • AN APPROACH TO EXTRACT EDGEMAPS IN INFRARED BASED BREAST IMAGES USING INVERSE PERONA MALIK DIFFUSION FILTER   Order a copy of this article
    by THAMIL SELVI JAYAVELU, GANESAN KAVITHA, C. MANOHARAN SUJATHA 
    Abstract: Infrared thermography is the adjunctive tool for early diagnosis of breast cancer. The infrared breast images are of low Signal to Noise Ratio (SNR) and amorphous in nature which makes analysis a challenging task. In this work, an attempt is made to extract the edge map from infrared breast images using Inverse Perona-Malik (PM) model. This nonlinear filter varies the diffusion near the interferences and edges using inverse gradient and new nearest neighbour scheme. The edge maps are extracted for various gradient thresholds. The statistical features such as average gradient, contrast, entropy and variance are extracted from the edge map to find the optimal gradient threshold. The diffused image of optimal gradient threshold value is validated using SNR. Results show that, the statistical features are found to have maximum value for the gradient threshold of 5. It is also observed that SNR obtained from the diffused image is improved by 30 dB compared to raw image. inverse PM Model is found to reduce the noise and enhance the edges. The integration of denoising and edge map extraction would result in accurate segmentation and aid for early diagnosis.
    Keywords: Breast thermal images, Inverse PM Model, Average gradient, Contrast, Entropy, Variance, and SNR

  • Peak frequency analysis for Schizophrenia using Electroencephalogram Power spectrum during Mental Activity   Order a copy of this article
    by Thilakavathi Bose, Shenbaga Devi S, Bhanu K 
    Abstract: The objective of this work is to identify Schizophrenia using EEG spectral feature. This work proposed two oddball paradigms to stimulate mental activity for cognitive process and Electroencephalogram is recorded during both rest and mental activity. 51 Schizophrenia and 26 normal subjects are used in this work. The maximum power in various bands and its corresponding frequency are estimated from the Electroencephalogram power spectrum and are called as peak power and peak frequency respectively. Statistical evaluations are made using Students T-Test and ANOVA. The theta peak frequency, beta peak frequency and beta peak power are identified as most significant features with a low value of p(p< 0.001) and alpha peak power with p<0.01 during mental activity. This work suggests that the schizophrenia subjects can be identified during mental activity than rest since the classification accuracy has been achieved 91.75% using SVM classifier.
    Keywords: Schizophrenia; Modified Odd ball paradigm; EEG; Spectrum Analysis; Peak Power; Peak Frequency; Rest; Mental activity; Students T test; ANOVA;SVM classifier

  • Multiresolution Transform Based Image Denoising and Fusion for Poisson Noise Suppression   Order a copy of this article
    by D. Mary Sugantharathnam, D. Manimegalai, T. Jayasree 
    Abstract: Noise removal is essential in medical imaging applications in order to enhance and recover anatomical details that may be hidden in the data. The issues of Poisson Noise occurrence in medical imaging due to the arrival of photon nature of light produced at the time of capturing of image have always been a concern. This paper addresses a novel approach for the removal of Poisson noise embedded in the biomedical images based on Multiresolution transform based denoising and fusion approach. In this technique, first, the images are denoised separately, by applying Discrete Wavelet Transform (DWT) /Stationary Wavelet Transform (SWT) and Fast Discrete Curvelet Transform (FDCT) integrated with RudinOsherFatemi (ROF) model. Next, the distinct features extracted from the denoised images are fused, resulting in an enhanced and denoised image. The proposed method was tested and compared with other denoising techniques on a set of biomedical images. Subjective and objective evaluations show better performance of this new approach compared to existing techniques.
    Keywords: Wavelet Transform, Curvelet Transform, Poisson noise, denoising, biomedical imaging

  • Theoretical Framework, Design and Implementation of Artificial Brain Architecture for Service Robots   Order a copy of this article
    by Naveen Kumar Malik, V.R. Singh 
    Abstract: In this investigation, a theoretical high level brain model of human intelligence is devised to develop a theoretical high level architecture for service robots, named as Artificial Brain Architecture for Service Robot (ABASR). It provides intelligent mechanism for service robots with multi heterogeneous input, meta reasoning, scientific inference engine and communication. The ABASR is a high level human inspired theory of intelligence. To validate ABASR, the prototype robotic wheelchair is designed. The multi heterogeneous inputs are android mobile phone and three IR sensor modules. The mobile phone uses its local reasoning to give user command to robotic wheelchair. Similarly, three IR sensor modules outputs are used to detect obstacle in path of robotic wheelchair. In Scientific Inference Engine (SIE), user command is confirmed with environment sensors to give correct navigation command to robotic wheelchair. The communication between wheelchair and its handler is done using fire detector sensor and global system for mobile (GSM) module. It have feature like obstacle avoidance, assisting user in mobility of wheelchair and emergency communication to handler. The developed robotic wheelchair is evaluated in room environment with four disable childrens suffering from muscular dystrophy (MD) and Cerebral Palsy (CP) and four caregivers. Findings confirm the importance of intelligent wheelchairs by providing independent mobility to user, reducing the cognitive workload of user, reducing the requirement of caregivers and bring confidence among its user.
    Keywords: Artificial Intelligence, Brain Model, Cognitive Architectures, Embedded System, Intelligent Wheelchair.

  • A TWO PHASE GENETIC LEARNING OF A NEURAL CLASSIFIER APPLICATION IN MEDICAL DIAGNOSTIC   Order a copy of this article
    by Mansouria Sekkal, Mohammed Amine Chikh 
    Abstract: In this paper, we propose a procedure to choose an initial population at the beginning of an evolutionary process in neural networks. In the first phase we take N examples of the learning base (N represents size of initial pop for second phase evaluation) and find the best classifier synaptic weights for each individual example using a Neuro-genetic classifier (NGC). In The second phase we use a global genetic learning database; as the initial population is represent by all final weights of the first learning phase. The objective of this method is to ameliorate the performance of neuro-genetic classifiers with a lower computational cost. The results show that our proposal considerably improved the efficiency of previous approaches. We use several medical databases to validate our results.
    Keywords: artificial neural networks; genetic algorithm; classification;choice of initial population.

  • Boundary Detection of Renal using Contour Segmentation   Order a copy of this article
    by Gomalavalli Ramesh, S. MUTHAN, P.M. VENKATA SAI 
    Abstract: In this paper, an active method for computer-aided renal segmentation on abdominal Computed tomography (CT) images with anatomic building attention is presented. The proposed segmentation system is considered to assist the medical practitioners in clinics and learning methodology. The planned method is a common sound segmentation of renal. The major elements of the proposed system are (i) Detect and check the objects; (ii) Region of interest of renal location is detected; (iii) Determination of Dice similarity coefficient(≤1) degree of accuracy is acquired; (iii) Novel work is to verify whether the neighboring organs are alarmed or not (DSC <0.8501); (iv) Statistical quality measurement of boundary is done. This is a compatible method to avoid clinical needle biopsy. To overcome the limitations present in the most of the cases, Active Contour Detection method is applied. The qualitative examination on 52 patients indicates the average comparison of 76.2% between the segmentation methods.
    Keywords: Keywords: Active contour detection; Segmentation; Neighboring organs; Sorensen dice similarity coefficient; Biopsy; Structural similarity index measure; Peak signal to noise ratio; Jaccard coefficient; Jaccard Distance; Mean squared error.

  • Bio Sensor based Feature Extraction and physiological parameters measurement for Bio Medical applications   Order a copy of this article
    by R. Jegan, K.V. Anusuya 
    Abstract: Physiological signal processing has significantly increased recently among the biomedical researchers for developing wearable standalone devices. Wearable devices are essential in hospital which is used for various biomedical applications such as Heart rate and blood pressure measurement. Heart rate and pulse rate parameter is an essential feature for estimating heart arrhythmias which can be measured from an acquired ECG and PPG signals. In noisy environment, producing an algorithm for the physiological signal processing and feature extraction is an essential task which depends on the physiological conditions. In this paper, the software based algorithms are developed for physiological signal processing and physiological parameter measurement. This paper presents bio sensor based real time acquisition, processing and peak detection of ECG and PPG signals for heart rate, pulse rate and blood pressure measurement. Peak detection is an essential method for finding heart rate and pulse rate measurement. This paper also propose a new adaptive Pulse Transit Time based blood pressure estimation. Here, the blood pressure is estimated from the pulse transit time which is calculation of peaks from PPG and ECG signals. ECG and PPG amplifiers are designed and the real time signals are acquired through analog devices and processed using LabVIEW and MatLab environment. The advantages of proposed work is very simple, low cost, easy integration with programming environment and gives continuous monitoring of physiological signals.
    Keywords: ECG signal; PPG signal; Heart Rate; Biomedical signal processing.

  • An enhanced filtering based approach to approximate volumetric ambient occlusion   Order a copy of this article
    by Naima Bahi, Mohamed Chaouki Babahenini 
    Abstract: Achieving, through shading, a good visualization of scientific volumetric data sets is prohibitive for interactive applications due to a significant amount of existing occlusion effects and lighting variation. Ambient occlusion, although allowing us to understand these data through soft shadows, often comes with an important cost of preprocessing which prevents its use especially in the applications based on the transfer function editing. In this paper, we present a new method for approximating ambient occlusion for volumetric data using an exponential function which allows for high quality hardware-accelerated filtering and leads us to achieve more compact information using a filterable representation in order to avoid the classic occlusion test with a binary manner. Our evaluation of a series of medical images demonstrates that the proposed algorithm provides smooth shading, producing high quality results, achieves an interactive rate and consumes less memory.
    Keywords: scientific 3D visualization; Scientific data sets; interactive application; volume rendering; shading; ambient occlusion; GPU based filtering; medical images;.

  • Automatic Segmentation of Multi-Class Images with Nonlinear Least Squares Model   Order a copy of this article
    by Kothapelli Punnam Chandar, Tirumala Satya Savithri, Baswaraju Swarnalatha 
    Abstract: In this paper automatic segmentation of multi-class images problem is considered. The 1D-histogram of the multi-class image is approximated using Gaussian functions and the unknown parameters of the Gaussian functions are estimated using Non-linear Least Squares (NLS) Optimization; thereby the problem of segmentation of unknown image class is modeled as an optimization problem. Further, the parameter estimation accuracy is improved by using the pearson linear correlation coefficient as a regularization term of the objective function. The experimental results demonstrates the NLS algorithm ability to estimate the parameters of the Gaussian functions and their by automatically determine the multi-thresholds for segmentation.
    Keywords: Image Segmentation; Thresholding; Non-linear Least Squares Optimization; Differential Evolution Optimization; Gaussian Mixtures.

  • Methods for the Elimination of Ocular Artifacts from EEG   Order a copy of this article
    by John William Carey Medithe, Usharani Nelakuditi 
    Abstract: Electroencephalogram (EEG) is a significant medical imaging tool which reflects the electrical activity of the brain. EEG extracts bio-potentials from the electrodes which are placed on the scalp, these bio- potentials are generated due to the firing of the neurons in the brain. These EEG potentials will be in an order of microvolt, which is low in amplitude. Moreover, most of the EEG recordings are prone to the artifacts such as electrical activities generated from human organs like Eye, Muscle and Heart etc. The overlapping of the Artifacts on normal signal may affect the physicians interpretation of EEG, finally leading to wrong diagnosis. There are many artifacts such as undesired bio-potentials from other organs such as Eye, an artifact from equipment used for acquisition of EEG and other external noises; of all these artifacts, Ocular artifact (OA) is the dominant artifact. This is because the OA caused by the eye is very much nearer to the psyche. This article gives the perspective of various methods used to filter the Ocular artifacts. The benefits, drawbacks of each method are also presented. Outcomes of the respective methods when the EEG signal applied are simulated using EEGLAB Toolbox for MATLAB and advanced signal processing toolkit of NI LabVIEW.
    Keywords: Electroencephalogram (EEG); ICA; Ocular Artifacts; PCA; Wavelet Decomposition.

  • Colour Retinal Images Enhancement using Modified Histogram Equalization Methods and Firefly Algorithm   Order a copy of this article
    by Krishna Gopal Dhal, Sanjoy Das 
    Abstract: Proper contrast enhancement of colour images of retinal fundus is important to detect the eye diseases and its severity like in the case of diabetic retinopathy, as in a retinal fundus image contrast between different segments like retinal vessels, optic disk remains very low. In this paper a novel parameterized variant of HE, called as Weighted and Entropy Based Thresholded Histogram Equalization (WEBTHE), has been proposed to enhance the retinal fundus images. WEBTHE is basically the combination of histogram modification based HE variant and entropy based thresholding method. Firefly Algorithm (FA) has been used to find the optimal values of the four parameters with diverse ranges corresponding to histogram modification of the proposed method by considering Peak-Signal to Noise ratio (PSNR) as objective function. PSNR imparts full automation in computation to the method within reasonable time complexity. Experimental results show the superiority of the proposed method over other existing methods visually and mathematically.
    Keywords: Contrast Enhancement. Modified Histogram Equalization. Retinal fundus images. Firefly Algorithm. PSNR. Entropy.

  • A hybridized neural network and optimization algorithms for prediction & classification of neurological disorders   Order a copy of this article
    by Pravin R. Kshirsagar, Sudhir G. Akojwar, Nidhi D. Bajaj 
    Abstract: Artificial Neural Network (ANN) techniques are considered to be most efficient in biomedical areas for their effective results in classifying several complex disorders. Application of standard optimization techniques in combination with ANN could highly optimize the parameters of this Network and make it even more reliable and efficient.In this paper, a hybrid model of Artificial Neural Network and Particle Swarm Optimization (PSO) Algorithm for the Classification & Prediction of various Neurological Disorders is designed. The proposed system works on the EEG signals obtained from patients suffering from Focal Epilepsy, Brain Dead, Slow-wave conditions, etc. It particularly is capable of performing Classification and Prediction of Neurological diseases based on the EEG signal input. Here Probabilistic Neural Network (PNN) is used as it is very efficient for classification purposes. Classification results are verified by using 10-fold cross validation technique. Prediction is performed by using Modified PSO. The EEG database is obtained from CIIMS Hospital, Nagpur. The results are highly reliable with graphs for Predicted signal and Prediction Error. Percentage of accuracy, sensitivity and mean squared error are calculated as well. With the help of this system classification of EEG signals can now be easily done with accuracy greater than 99% and in a short span of time.This paper gives a study of a novel approach for designing an ANN-PSO classifier and a new prediction technique. Furthermore, this work will be helpful in future to assist doctors in hospitals. As it is known that EEG signals are difficult to predict, since doctors take time to analyze them so the authors propose an automated approach to prediction, which may aid the physician.
    Keywords: Probablistic Neural Network; Partical Swarm Optimisation; Genetic Algorithm; Modified PSO; Prediction; Classification.

  • Automated Recognition of Obstructive Sleep Apnea Using Ensemble Support Vector Machine Classifier   Order a copy of this article
    by V. Kalaivani 
    Abstract: ECG is mainly used to diagnosis the Obstructive Sleep Apnea(OSA) with a high degree of accuracy in clinical care applications. We have developed a real time algorithm for the detection of Sleep apnea disease based on electrocardiograph (ECG). In this study, features from ECG signals were extracted from 12 normal and 58 OSA patients from the Physionet Apnea ECG database. The baseline noise, motion drift and muscle noise present in the raw ECG signals are removed using median filter and Daubechies wavelet filter. QRS detection algorithm extracts R-wave amplitude and R-wave time duration from the denoised signal. The proposed QRS detection algorithm contains four stages. The initial stage is derivative function which calculates the QRS-complex slope value using some five-point derivatives. The next stage is squaring function and it removes the negative data points using square the derivative values. The first two stages are used to calculate R-peak amplitude. Third stage is moving-window integration. It can calculate the R-peak slope value by using some sample rates. Final stage is fiducially marked which calculates the R-peak value and QRS complex time duration (width). EDR is generally based on the R-wave amplitude and R-wave time duration. Time domain features are calculated from the Heart Rate Variability and ECG-derived respiration. Sleep apnea disease is diagnosed by using time domain features. Support Vector Machine(SVM) and Ensemble Support Vector Machine techniques are used for the detection of Sleep Apnea. SVM classifier was used with Linear, Polynomial, Redial Basis Function(RBF) and Multilayer Perceptron.
    Keywords: Obstructive Sleep Apnea(OSA); Heart Rate Variability(HRV); ECG Derived Respiration(EDR); Support Vector Machine(SVM); Ensemble Support Vector Machine.

  • Multimodality Image Fusion using Centre-Based Genetic Algorithm and Fuzzy Logic   Order a copy of this article
    by S.P. Velmurugan, P. Sivakumar, M. Pallikonda Rajasekaran 
    Abstract: The Fusion method is used to detect and treatment for the disease in a successful manner which integrates various modalities. Nowadays, medical image fusion system is a demanding task in healthcare applications such as tumor detection, analysis, research, and treatment etc. In this paper, we propose a multimodality medical image fusion using center based genetic algorithm (CBGA) and fuzzy logic which is examined by the use of the quantitative measure. Here, at first, we estimate the segmentation map from the source images (MRI and CT). After that, the source images are decomposed based on lifting wavelet transform. Then, a fuzzy-based approach is used to fuse high-frequency wavelet coefficients of the MRI and CT images. Mainly, the output of three various fusion rules incorporated by fuzzy logic (weighted averaging, selection using pixel-based decision map (PDM), and selection using region-based decision map (RDM)), based on a dissimilarity measure of the source images. Then a CBGA is used to fuse the low-frequency wavelet coefficient of the MRI and CT images. At last, we combine low and high-frequency wavelet coefficients of the source images to obtain the fused image.
    Keywords: high frequency; low frequency; wavelet coefficient; fuzzy logic system; RDM; PDM; weighted averaging; lifting wavelet transform.

  • Inhomogeneity correction and hybrid based segmentation in cardiac MRI   Order a copy of this article
    by A. Venkata Nageswararao, S. Srinivasan, Ebenezer Priya 
    Abstract: Image segmentation is an important step in medical image analysis and segmentation of ventricles in Cardiac Magnetic Resonance (CMR) images is challenging due to an in-built artifact called intensity-inhomogeneity. The short axis cine Magnetic Resonance Images (MRI) recorded under a steady state free precision protocol were corrected for intensity-inhomogeneity using Bias Corrected Fuzzy C-means Method (BCFCM), Level Set (LS) and Multiplicative Intrinsic Component Optimization (MICO) methods. The statistical measures show that bias correction by BCFCM has better performance than MICO and LS. In addition, the original and bias corrected images are validated by Multifractal Analysis (MFA). The results show that in bias corrected images, the low frequency components are removed thereby enhancing the sharpness of the ventricular boundaries. Further, ventricular segmentation is performed using the proposed automatic hybrid Sobel edge detector with optimized level set method. The validation parameters of segmented results show that the ventricular detection in bias corrected images matches better with ground truth.
    Keywords: Cardiac Magnetic Resonance; Intensity-inhomogeneity; Bias Corrected Fuzzy C-means; Level Set; Multiplicative Intrinsic Component Optimization and multifractal analysis.

  • Hand punch movement kinematics of boxers with different qualification levels   Order a copy of this article
    by Yaodong Gu, Sergey Popik, Sergey Dobrovolsky 
    Abstract: This study focuses on qualitative and quantitative analysis of temporal and spatiotemporal characteristics of right hand cross of 18 boxers at various proficiency levels. Boxers carried out punches from different positions: 1) in full coordination; 2) with lower limbs fixed; 3) with lower limbs and trunk fixed. Analysis of punches allowed revealing kinematical features of cross punch and identification of causes for potential deviations in the technique of punching.
    Keywords: kinematical features; hand punch; temporal parameters; spatiotemporal characteristics; punch velocity; body parts.

  • A Secure Cloud-Based Multi-Agent Intelligent System for Mammogram Image Diagnosis   Order a copy of this article
    by Bhavani S R, Chilambuchelvan A, Senthilkumar J, Manjula D, Krishnamoorthy R, Kannan A 
    Abstract: Background: Significant and radical improvements in the healthcare industry today have facilitated the monitoring of patients through the internet. Breast cancer has become a widespread malaise across the globe, with many dependent on the internet for a diagnosis. A range of emerging technologies such as artificial intelligence, cloud computing and big data have been adopted in cancer diagnosis. Of late, a new framework for a cloud-based, multi-agent system to support secure intelligent mammogram image diagnosis for breast cancer detection has been developed. There is, as yet, no fully-automated, generic, multi-agent intervention system with a cloud infrastructure for breast cancer patients, and implementation guidelines are, at best, deficient. Objective: This study implements a generic, fully-automated, secure multi-agent intelligent system to support mammogram image diagnosis. The objective of this study is to enhance diagnostic performance, and increase scalability, response time and throughput. It focuses on a large group of patients, and is intended to test their new image with a high degree of efficiency and in minimal time. Methods: The proposed Secure Cloud-Based Multi-Agent Intelligent System for Mammogram Image Diagnosis (MCSIMIDx) framework has two phases an MCSIMIDx training phase and a test phase. Experiments on diagnostic accuracy, risk factors of breast cancer, and performance evaluation measures - such as response time and throughput - are obtained from the data provided by clients accessing this prototype. Results: The results obtained in this research fall into three categories. First, a formal framework is developed for classification accuracy using the proposed approach. It is found that it has a high ratio of acceptance from users and attains superior sensitivity of up to 99.25% and accuracy of up to 99.0%. Second, experiments are conducted on the risk factors that influence breast cancer through an online survey. Age, family history and the stages of breast cancer are significant factors. Finally, a performance analysis of the proposed framework is conducted for client-server and agent-based systems. Conclusion: This study hopes women across the world will use the secure cloud-based fully automated multi-agent system to test their new image and personally check out for themselves its high accuracy and privacy levels. It ensures rapid diagnostic results in minimal time.
    Keywords: Multi-agents; Cloud computing; Breast cancer; Representative Association rule; image diagnosis.

  • CLASSIFICATION OF SKIN DISEASE USING ENSEMBLE BASED CLASSIFIER   Order a copy of this article
    by Thenmozhi K., Rajesh Babu M 
    Abstract: Cancerous Skin disease such as melanoma ad nevi typically results from environmental factors (such as exposure to sunlight) among other causes. The necessary tools needed for early detection of these diseases are still not a reality in most communities. In this paper, the framework is proposed to deal with the detection and classification of various skin disease. The two techiques commonly used for reduction of dimensionality are feature extraction and feature selection. In feature extraction, features are extracted from original data using principal component analysis and linear discrimant analysis and then extracted feature is reduced by feature selection technique called fisher ratio method in which the subset of sufficient features is selected for classification. This technique improves the performance and enhances the speed of classifier. The ensemble based classifier such as Bayesian, self-organized map and support vector machine are used to classify the various skin disease from the dataset. The proposed technique achieves better accuracy and less execution time than existing approach.
    Keywords: skin cancer; melanoma; ensemble classifier; fisher ratio.

  • Microcalcifications segmentation from mammograms for breast cancer detection   Order a copy of this article
    by Ismahan Hadjidj, Amel Feroui, Aicha Belgherbi, Abdelhafid Bessaid 
    Abstract: The presence of microcalcifications (MCs) in X-ray mammograms provides an important early sign of women breast cancer. However, their detection still remains very complex due, to the diversity in shape, size, their distributions and to the low contrast between the cancerous areas and surrounding bright structures in mammograms. This paper presents an effective approach based on mathematical morphology for detection of (MCs) in digitized mammograms. The developed approach performs an initial step in order to extract the breast area and removing unwanted artifacts out of the mammogram. Subsequently, an enhancement process is applied to improve appearance and increase the contrast of images and to eliminate noise. Once the breast region has been found, a segmentation phase through morphological watershed is performed in order to detect (MCs). The performance of our approach is evaluated using a total of 22 mammograms extracted from the MIAS mammographic database, shows the presence of (MCs).The obtained results were compared with manual detection, marked by an expert mammographic radiologist. This results show that the system is very effective, especially in terms of sensitivity.
    Keywords: (Breast cancer; microcalcifications; mammograms; breast region; mathematical morphology; watershed transform.).

  • Analysis of brainstem in Alzheimer MR images using lattice Boltzmann level set   Order a copy of this article
    by Ramesh Munirathinam, Sujatha Chinnaswamy Manoharan 
    Abstract: Alzheimers Disease (AD) is a progressive neurological disorder resulting in the cognitive impairment of elderly people. Analysis of morphological variations before the onset of cognitive impairment is important for early diagnosis of AD. The brain stem is considered as a significant pathological core for the study of psychological and behavioral symptoms occurring before cognitive impairment. In this work, the brainstem is extracted from T1 weighted brain MR images using a region-based level set method. The segmentation results are validated using regional statistic and overlap measures. Geometric and texture features are extracted for analyzing the morphological variations. The results show that the region based segmentation is capable of extracting the brainstem more accurately by preserving the weak and blurred edges of the brainstem. The extracted geometric and textural features are able to show a significant difference in the normal and AD brain stem images. The feature values obtained from AD images are found to be less compared to the normal images. This might be due to the neuronal loss in the brain stem describing the atrophy. Hence, this analysis proved to be clinically significant.
    Keywords: Brainstem; Region based level set; Lattice Boltzmann method.

  • Three-Dimensional MRI Brain Tumor Classification using Hybrid Ant Colony Optimization and Gray Wolf Optimizer with Proximal Support Vector Machine   Order a copy of this article
    by Rajesh Sharma R, Akey Sungheetha, Marikkannu P 
    Abstract: A hybrid approach employing Ant Colony Optimization (ACO) and Gray Wolf Optimizer (GWO) is proposed in this paper along with proximal support vector machine classifier to carry out brain tumor classification for the given 3D MRI brain images. The proposed hybrid Ant Colony Optimization Gray Wolf Optimizer (ACO GWO) is employed for selecting the optimal features required for performing the classification process. Proximal Support Vector Machine (PSVM) is employed over the Support Vector Machine (SVM), Back Propagation Network (BPN) and K-Nearest Neighbor (k-NN) for evaluating the effectiveness of the classifier approach.
    Keywords: ACO; GWO; PSVM; BPN; K-NN.

  • Decision Support System for Type II diabetes and its risk factor prediction using Bee based harmony search and Decision tree Algorithm   Order a copy of this article
    by Selvakumar S, Sheik Abdullah A, R. Suganya 
    Abstract: Type II diabetes is one of the main causes of disability in adults as well as the main cause of death in most of the countries. The objective of this paper was to develop a prediction model for the investigation of type II diabetes and its risk factors which target towards the reduction of diabetic events. The risk factors related to type II diabetes has been considered for developing the predictive model. A total of 732 cases were collected from Government hospital in the district of Theni, Tamil Nadu, India. Predictive analysis was carried out using bee based harmony search algorithm and C4.5 decision tree algorithm with its splitting criterion. From the experimental results, and analysis it was found to be the risk corresponding to postprandial plasma glucose, A1c- Glycosulated Hemoglobin, mean blood glucose level, with a prediction accuracy of about 92.87% respectively. It is estimated that the age group corresponding to 34 to 73 was found more prevalent and the mathematical model proves that age, postprandial plasma glucose and mean blood glucose level have strong co-relation with its corresponding data values. There by, predictive data analysis could help in the identification of risk factors with respect to the subject of type II diabetes, with accordance to the therapeutic procedures and treatment analysis.
    Keywords: Decision support systems; Decision trees; Diabetes; Optimization; Risk analysis.

  • INVESTIGATION ON ROI SIZE AND LOCATION TO CLASSIFY MAMMOGRAMS   Order a copy of this article
    by Amit Kamra, Akshay Girdhar, Poonam Sood 
    Abstract: Abstract- Breast cancer is the major cause of death among women and early detection can lead to a longer survival. Computer Aided Diagnosis (CAD) system helps radiologists in the accurate detection of breast cancer. In medical images a Region of Interest (ROI) is a portion of image which carries the important information related to the diagnosis and it forms the basis for applying shape and texture techniques for cancer detection. Several ROI sizes and locations have been proposed for computer aided diagnosis systems. In the present work various ROI sizes have been used to determine the appropriate ROI size to classify fatty and dense mammograms. Two types of mammograms i.e. fatty and dense are used from the MIAS database. Various texture features have been determined from each ROI size for the analysis of texture characteristics. Fisher discriminant ratio is used to select the most relevant features for classification. Finally linear SVM is used for the purpose of classification. Highest classification accuracy of 96.1% was achieved for ROI size 200
    Keywords: ROI; Breast Cancer; Digital Mammograms; Breast Tissue; feature selection; classification.

  • Using worn out insole to express human foot   Order a copy of this article
    by Ahmad Yusairi Bani Hashim 
    Abstract: Human is the only primate that can perform ideal bipedal walking. Due to this configuration also, humans are not able to climb trees as efficient as a chimpanzee. As such, the human foot is unique by itself, which is evident in its print. There have been some studies that looked at the footprints and their relationship to the ideal bipedal walking. There has none, if a work has been done, on the determination of the foots work volume given a footprint. Five volunteers participated in the study who supplied their used shoes. The insole images were processed to find the effective regions using the binarization, inversion, and edge finding techniques. The spots that were suspected to be the resultant of the repeated applications of the ground reaction forces were identified, and twelve nodes were marked on the designated spots. The drawn footprints looked similar geometrically; however, each footprint had a unique node positions profile. The aspect ratio of the foot length, width, and height seemed to congregate to 3:1:1 and 30 degrees footprint angle. The actual plots revealed that the range of the ratio and angle range was 2.20 to 3.00, and 30 degrees to 45 degrees, respectively. Therefore, the human foot identity is based on the number of nodes uniquely localized on the footprint, which defines the foot workspace. It may be expressed by simple measurements of the foot height, the foot width, the foot height following the standardized node locations.
    Keywords: Ground reaction force; insole; footprint identity; image processing.

  • Study of Structural Complexity of Optimal Order Digital Filters for De-noising ECG Signal   Order a copy of this article
    by Seema Sande, M.K. Soni, Dipali Bansal 
    Abstract: Selection and implementation of optimal order digital filter for denoising ECG signal on FPGA based on Signal to Noise Ratio (SNR), error and accuracy using wavelet toolbox is a tedious task. To overcome this problem, an attempt has been made in MATLAB to obtain a noise free ECG signal based on SNR and Mean Square Error (MSE) to select optimal order digital filter. The filter with maximum SNR and minimum MSE is selected as an optimal order filter. An ECG sample from MIT-BIH Arrhythmia database is considered for investigation and the signal is artificially corrupted by adding noise and is filtered through different low pass IIR and FIR digital filters, which are designed and realized in MATLAB. Power Spectrum Density (PSD) and Fast Fourier Transform (FFT) are used to validate the performance of optimal order filters. The hardware complexity of optimal order digital filters structure is checked in terms of multipliers, adders and delays in MATLAB and their performance is compared based on the number of basic elements, PSD and visual inspections. A final summary report on the study of complexity of the structure of optimal order filters is presented. It is found that the Chebyshev-I and the Elliptic IIR filters require low filter order for a given specification to denoise ECG signal. Hence, requires less number of basic elements. Similarly, Kaiser, Hamming, Hanning window FIR filter require less number of basic elements. Hanning window gives undesirable results. Elliptic IIR digital filter and Kaiser Window FIR filter give better performance as compared to others from PSD graphs and visual inspections.
    Keywords: ECG signal; MIT-BIH; SNR; MSE; PSD; FFT.

  • Detection of masses in mammographic breast cancer images using Modified Histogram based Adaptive Thresholding (MHAT) method   Order a copy of this article
    by Bhagwaticharan Patel, G.R. Sinha, Dilip Soni 
    Abstract: Breast cancer is the leading type of cancer diagnosed in women nowadays and for breast screening, mammography is preferred to detect and diagnose the cancer by detecting the masses with the help of Computer-aided Diagnosis (CAD) system. It helps to assist radiologists in getting accurate diagnosis and its analysis for improving breast cancer prediction. Detection is the most effective way to reduce mortality rate and hence many countries have started mass screening programs that have resulted in a large increase in the number of mammograms requiring interpretation. An approach is proposed to effectively detect the masses in mammographic breast cancer images by using Modified Histogram based adaptive thresholding (MHAT) method. The proposed algorithm was tested over several images taken from the digital database. The algorithm has been tested over with 100 mammographic images and the experimental results show that the detection method has a sensitivity of 98.3% at 0.78 false positives with accuracy of 99 % per image. We evaluated the performance of our MHAT algorithm by comparing with respect to the ground-truth boundary drawn by an expert radiologist. The improvement is statistically significant. The results are clinically relevant, according to the radiologists who evaluated the results.
    Keywords: Adaptive thresholding; breast cancer; computer aided detection; mammography; mass; segmentation; screening.

  • Adaptive Thresholding of Wavelet Coefficients using Generalized False Discovery Rate to Compress ECG Signal   Order a copy of this article
    by Supriya Rajankar, Sanjay Talbar 
    Abstract: In signal compression the selection of an appropriate threshold is the challenging task. The paper proposes an algorithm to determine the signal adaptive threshold based on estimating wavelet coefficients by Generalized False Discovery Rate (FDR) to compress ECG signal. The hypothesis testing and thresholding are closely related. So, multiple hypotheses testing is used to determine an adaptive threshold called as False Discovery Threshold (FDT). The p-value of each wavelet detail coefficient is computed and arranged in an ascending manner. The dynamic critical significance levels are calculated using k-FWER and k-FDR. These significance levels are compared with the corresponding p-value to satisfy desired FDR, which provides the FDT. The run length encoding followed by Huffman coding provides compression. The paper also proposes a new performance evaluation parameter: mean Structural Similarity Index (mSSIM) to check the similarity between original and reconstructed ECG signals. Generalized FDR based thresholding provides very less PRD value compared to standard codecs in the literature and structural similarity very close to one, which signifies better reconstruction of the signal.
    Keywords: Generalized False Discovery Rate; step up procedure; BH procedure; k-FDR; k-FWER.

  • A New Heart Sounds Segmentation Approach Based on the Correlation between ECG and PCG signals   Order a copy of this article
    by FANDI Radia, HADJ SLIMANE Zine-Eddine 
    Abstract: During the cardiac cycle, both electrical and mechanical events are present. In fact, the electrocardiogram (ECG) allows the exploration of the electrical activity of the heart, while the phonocardiogram (PCG) constitutes a complementary tool to record the mechanical activity of the heart. The aim of our work is to develop a new approach for heart sounds segmentation based on the correlation between ECG and PCG signals for measurement of systolic time interval. Two different groups of simultaneous recordings of ECG and PCG signals were tested in this study. The performance of automatic heart sounds localization process is compared with that of manual measurements made by two experts. The results obtained are interesting especially for pathological cases heart sound.
    Keywords: ECG signal; PCG signal; Heart Sounds (HS); Pearson’s correlation coefficient; Automatic localization (AL); systolic duration (SD); manual annotation (MA).

  • SECURE AND INTELLIGENT ARCHITECTURE FOR CLOUD BASED HEALTH CARE APPLICATIONS IN WIRELESS BODY SENSOR NETWORKS   Order a copy of this article
    by Antony Rani, Baburaj  
    Abstract: Wireless Sensor Networks (WSNs) are becoming a significant enabling technology for a wide variety of applications. Advances in WSN have facilitated the realization of pervasive health monitoring for both homecare and hospital environments. Sensor nodes are capable of sensing, processing, and communicating one or more vital signs, and they can be used in Wireless Body Sensor Networks (WBSNs) for health monitoring. Many studies were performed and are ongoing in order to develop flexible, reliable, secure, real-time, and power-efficient WBSNs suitable for healthcare applications. This paper concentrates on the development of intelligent secure architecture for cloud based healthcare applications in Wireless Sensor Networks. This paper describes the applications, issues and challenges of BSN in healthcare, energy efficient body sensor network architecture using aggregation, secure data collection, storage and data sharing using an authentication algorithm and a novel prediction model which act as an expert system for disease management.
    Keywords: Cloud computing; e-health care system; Integrated secure authentication; Received signal strength; Wireless body area network.

  • Automatic detection of stereotyped movements in autistic children using the kinect sensor   Order a copy of this article
    by Maha Jazouli, Aicha Majda, Djamal Merad, Rachid Aalouane, Arsalane Zarghili 
    Abstract: Autism spectrum disorders (ASD) is a developmental disorder that affects communications, social skills or behaviours that can occur in some people. Children or adults with ASD often have repetitive motor movements or unusual behaviours. The objective of this work is to automatically detect stereotypical motor movements in real-time using Kinect sensor. The approach is based on the $P point-cloud recognizer to identify multi-stroke gestures as point-clouds. This paper presents new methodology to automatically detect five stereotypical motor movements: body rocking, hand flapping, fingers flapping, hand on the face and hands behind back. With many ASD-children, our proposed system gives us satisfactory results. That can help to implement a smart video surveillance system and then helps clinicians in the diagnosing ASD.
    Keywords: ASD; Autism; stereotyped movement; repetitive motor movements ; repetitive behaviours; gesture detection ; Kinect Sensor; point cloud; nearest neighbour classifier; gesture recognition.

  • Hybrid Approach towards Feature Selection for Breast Tumor classification from Screening Mammograms   Order a copy of this article
    by Sudha M.N, Selvarajan S 
    Abstract: A hybrid approach has been developed to extract the optimal features from the breast tumors using Hybrid Harmony Search and presented in this paper. The texture feature, intensity histogram feature, radial distance feature and shape features have been extracted and the optimal feature set has been obtained using Hybrid Harmony Search (HHS). The hybrid scheme for feature selection is obtained by combining cuckoo search and harmony search. The minimum distance classifier, k-NN classifier and SVM classifier are used for classification purpose and its produces 98.19%, 98.34% and 97.18% average classification accuracy respectively with minimum number of features. The performance of the new hybrid algorithm is compared with the Genetic Algorithm, Particle Swarm Optimization algorithm, Cuckoo Search and Harmony Search. The result shows that the hybrid of Cuckoo and Harmony search algorithm is more accurate than the other algorithm. The proposed system can provide valuable information to the physician in medical pathology.
    Keywords: Breast cancer classification; Segmentation; Feature Extraction; Hybrid Harmony Search.

  • Overlapping Group Sparse Denosing: A good choice for noise removal from EMG signal in intermittent masseter muscle activity   Order a copy of this article
    by Behrouz Alizadeh Savareh, Gholam Hossein Meftahi, Azadeh Bashiri, Boshra Hatef 
    Abstract: Purpose: Biological signals are often impregnated with a variety of noises and noise removal for precise processing is very important. The aim of this study is to test a method called Overlapping Group Sparse Denoising performance on removing noises from EMG of sequential masseter activity.rnMethod: Overlapping group sparse denoising method was studied on EMG signals obtained from the masseter muscle. The EMG signals obtained from three groups of people (control, migraine without aura and tension headache) was investigated in this study.rnResult: Four metrics (MSE, MAE, SNR and PSNR) calculated for analyzing the method performance in denoising EMG signals.rnConclusion: The results indicated that using mentioned method was successful. The method can be helpful for denoising signals with intervals of clustering activations and deactivation like sound signals.rn
    Keywords: EMG; Masseter; Overlapping; Group Sparse Denoising.

  • A Clique-Based Scheduling In Real-Time Query Processing Optimization for Cloud-Based Wireless Body Area Networks   Order a copy of this article
    by Smys S., Dinesh Kumar A 
    Abstract: A wireless body area network is a wireless network of wearable computing devices. BAN devices may be installed inside the body, inserts, may be surface-mounted on the body in an altered position or may be accompanied devices which people can convey in distinctive positions, in clothes pockets, by hand or in different bags for real time health monitoring of patients. However WBAN tackles serious problems such as degrading throughput, high query latency, energy consumption. In this paper, we proposed Clique based WBAN scheduling (CBWS) algorithm and Cloud based WBAN algorithm. In the first methodology, the sensors are not active together at the same time, so it can be clustered into different groups to avoid interference. So coloring based technique is used to schedule all groups in a time slot. And these sensor data are provided to the database for user query processing. In the second methodology, a cloud based technique is utilized to secure the stored information and also optimize the real time query processing is done to obtain energy minimization and query latency. Also Multi Queue Scheduling (MQS) algorithm is used. The MQS categorized the jobs as small, medium and long as per the burst time in a cloud environment. The experimental results show that we achieves minimal energy consumption, query latency and better throughput and also provide secure and powerful storage infrastructure in real-time environment.
    Keywords: WBAN sensors; Clique based technique; Cloud based technique; User query processing; Energy consumption.

  • AN APPROACH FOR DETECTION OF EDGES IN CAROTID ULTRASOUND IMAGES AND ANALYSIS OF INTIMA-MEDIA COMPLEX USING MORPHOLOGICAL FEATURES   Order a copy of this article
    by Sumathi Krishnaswamy, Mahesh Veezhinathan 
    Abstract: Atherosclerosis is the first clinical manifestation of cardiovascular disease. It is a complex vascular disease that causes a condition of narrowing, stiffening and hardening of artery walls. This condition leads to serious pathologies like heart attack and stroke. Progression of atherosclerosis is marked by Intima-media thickness which is proven to be an early indicator of the disease. In this work, an attempt is made to preserve the edges of Intima-Media Complex (IMC) using non linear Total Variation (TV) diffusion filter. The edge maps generated with optimal values of threshold are used as stopping boundary in segmenting a database of 100 longitudinal images of common carotid arteries using Variational Level Set method. To analyze the performance of segmentation method the results are validated against ground truth values. Geometric features are extracted from the segmented region and statistical analysis is performed. It is observed that the segmented IMC is found to have high correlation with ground truth values. Bland-Altman plots show that, the values between 95% confidence interval are with overall good fit with minimal bias between segmentation method and ground truth (manually segmented by an expert). Hence the edge map extracted using TV filter shall enhance the edges and improve the performance of automated segmentation. Further, the extracted features could discriminate the structural changes in abnormal images from normal. Analysis of features plays clinically a significant role in finding the pathological conditions of carotid arteries.
    Keywords: Cardiovascular disease; Atherosclerosis; Intima-Media Layer; Carotid artery; plaque; Stroke; Total Variation Diffusion Filter and Level set method.

  • Evaluation of heart rate dynamics during meditation using Poincare phase plane symbolic measures   Order a copy of this article
    by Chandrakar Kamath 
    Abstract: Meditation has long been known to affect human physiology which is mediated through autonomic nervous system. The main objective of this study was to assess dynamic changes in cardiac inter-beat intervals and autonomic nervous system during meditation hypothesizing that Poincar
    Keywords: Forbidden words; Heart rate variability; Meditation; Poincaré phase plane; RR interval time series; Symbolic complexity measures; Symbolic dynamic entropy.

  • Modified dual channel PCNN algorithm with hybrid edge enhancement approach for multimodality brain image fusion   Order a copy of this article
    by Kavitha Srinivasan, Bharathi B, Sasikala P, Chandraleka D, Ashwini V 
    Abstract: Image fusion plays a vital role for many applications in the field of computer vision, remote sensing, image robotics and medical imaging. This paper is focused on the fusion of multimodality brain images, using a Modified Dual Channel Pulse Coupled Neural Network (MDCPCNN) algorithm along with hybrid edge enhancement approach namely Canny and Ant Colony Optimization (ACO). In general, the fused image derived from PCNN algorithm has better tissue information and contrast even though a loss occurs in edge information. To overcome this drawback, a hybrid edge enhancement approach is proposed and applied along with MDCPCNN fusion algorithm. The proposed model is validated using four datasets of brain images from different modality, with the subjective and objective measures. The subjective measure is human interpretation, whereas the objective measure is quantitative evaluation calculated through statistical parameters such as entropy, standard deviation, average gradient, mutual information and fusion quality index. The fused image constructed from the proposed model consistently retains the edge information than the existing PCNNs, which is inferred from the metrics of fusion quality index and average gradient. Also, the contrast, edge and texture of the fused image are improved than the source images without false information or information loss. In addition, the proposed MDCPCNN is compared and analyzed with the existing PCNN fusion algorithms for validation and analysis.
    Keywords: Image fusion; Dual channel pulse coupled neural network; Multimodality brain images; Canny algorithm; Ant colony optimization.
    DOI: 10.1504/IJBET.2017.10006801
     
  • Performance Analysis of Iris-based Identification System based on Exudates   Order a copy of this article
    by D.M.D. PREETHI, V.E. JAYANTHI 
    Abstract: In the current scenario responsibility of the system administrator is to have a secured system is a challenging task. Iris recognition is proven to provide unique biometric data, very difficult in duplication. Exudate is one of the disorders that occur in the retinal part of eye. Exudate is an earliest and most prevalent symptom of diseases leading to blindness such as diabetic retinopathy and wet macular degeneration. Proposed work is to examine the effect of exudate present on iris and leads to improve the level of security or used to match the unmatched person due to the structural and textural changes of iris. Hough Transform (HT) is employed to identify the unique features in iris. STARE database is used for performance analysis of iris recognition system. Proposed system shows that structural changes and quality degradations are observed in exudate image, may lead to iris recognition system fail, reenrollment is essential.
    Keywords: diabetic retinopathy; structural changes; exudates; medical imaging; security;.

  • MIMO Human Handwriting Model in Stochastic Environment   Order a copy of this article
    by Ines Chihi, A. Abdelkrim 
    Abstract: The present paper deals with a Multi Inputs Multi Outputs (MIMO) human handwriting model to characterize the pen-tip displacement on the plan from two forearm muscles activities, called ElectroMyoGraphy signals (EMG). The proposed model takes into account perturbations and incertitude whish can affect the handwriting process (instability of the writing support, psychical state of the writer, brusque movement, etc). In this sense, an experimental approach was presented to record the displacements of a pen-tip moving on the plane and two EMG signals during the handwriting motion. The velocity of the writing and ARMAX structure are used to characterize this biological act. Recursive Extended Least Square algorithm (RELS) is used to estimate the parameters of the proposed handwriting model. The obtained structure shows good concordance with the experimental recorded data.
    Keywords: MIMO handwriting model; pen-tip displacement; ElectroMyoGraphy signals; perturbations and incertitude’s; velocity of the writing; ARMAX structure; Recursive Extended Least Square algorithm.

  • Viscoelastic Blood Flow Through Stenosed Artery in Presence of Magnetic Field   Order a copy of this article
    by M.D. ASIF IKBAL 
    Abstract: An unsteady analysis of non-Newtonian blood flow under stenotic condition in presence of a transverse magnetic field has been carried out. The flowing blood is characterized by generalised Oldroyd-B having shear-thinning rheology. The arterial wall is considered to be rigid having cosine shaped stenosis in its lumen. The governing equations of motion accompanied by appropriate choice of the initial and boundary conditions are solved numerically by MAC (Marker and Cell) method and the results are checked for numerical stability with desired degree of accuracy. The quantitative analysis has been carried out finally which includes the respective profiles of the flow-field. The key factors like the wall shear stress and flow separation are also examined for further qualitative insight into the flow through arterial stenosis. The present results show quite consistency with several existing results in the literature which substantiate sufficiently to validate the applicability of the model under consideration.
    Keywords: Non-Newtonian Fluid; Stenosis; MAC; Transverse Magnetic Field.

  • Biomechanical Analysis of Implantation of Polyamide/ Hydroxyapatite Shifted Architecture Porous Scaffold in a Injured Femur Bone   Order a copy of this article
    by Kumaresan Thavasiappan, Gandhinathan R, Ramu M, Gunaseelan M 
    Abstract: Femur bone is one of the strongest and important bones which supports the major weight of human body. Unexpected sudden impact on the femur bone during accidents may cause severe fractures. When this bone injury is not self repairable, bone scaffold is the only remedy. This research paper analyzes the biomechanical effects of the femur bone implanted with porous scaffold made of Polyamide/Hydroxyapatite material. Porous scaffolds are temporary load bearing members, consisting of 3D porous geometry to support internal cell growth. This study focuses on the study of suitability of the porous scaffold fixed on a damaged femur bone under different loading conditions. This research uses the CT scan data of femur bone of a 75 kg healthy person and presents detailed information on the biomechanical analysis of the femur bone during common physical activities using finite element analysis.
    Keywords: Femur bone; Biomechanical analysis; Polyamide (PA); Hydroxyapatite (HA); Finite Element Analysis (FEA); Porous Scaffold.

  • A Wavelet and Adaptive Threshold Based Contrast Enhancement of Masses in Mammograms For Visual Screening   Order a copy of this article
    by Pratap Vikhe, Vijaya Thool 
    Abstract: The screening of mammograms is a difficult task for the radiologist, due to variation in contrast and homogeneous structure of the masses and surrounding breast tissues. Therefore, an adaptive threshold based contrast enhancement method is proposed in this paper for enhancement of suspicious masses in mammograms. Homomorphic filtering andwavelet based denosing has been used prior to enhancement in the describe method. The approach contains, artifact suppression using pre-processing. Then wavelet transform is applied on the preprocessed mammogram, homomorphic filter is used to filter the approximate coefficient and wavelet shrinkage operator is applied on detail coefficients for denoising. Finally, contrast enhancement approach is used to enhance the suspicious region based on adaptive threshold technique. Two databases, namely Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS), were used to test proposed method. The obtain results using proposed method gives better visibility for suspicious masses for all types of mammograms.
    Keywords: Mammogram Screening; Contrast Enhancement;Wavelet transform;Adaptive threshold.

  • TBAC: Tree-Based Access Control Approach for Secure Access of PHR in Cloud   Order a copy of this article
    by Athena .J, Sumathy V 
    Abstract: Personal Health Record (PHR) system is a currently emerging patient-oriented model for sharing the health information through a cloud environment. Previously, single attribute authority-based security scheme was used for sharing the PHRs in the cloud. But, this security scheme is not practically applicable due to the security and privacy issues. The existing access control approaches require more time to encrypt and decrypt the PHR file. This paper proposes a Tree-Based Access Control (TBAC) approach for fine-grained and secure access of the PHR in the cloud environment. In our approach, Tree-based Group Diffie-Hellman (TBGDH) algorithm is used to generate the key instance for the encryption process. The Attribute-based Encryption (ABE) approach is used with different hierarchical levels of the users to protect the personal health data. The access policies are based on the user attribute.
    Keywords: Attribute-Based Encryption (ABE); Diffie-Hellman; Cloud Computing; Key Generation; Multi-Authority ABE (MA-ABE); Personal Health Record (PHR); Tree-based Access Control (TBAC) and Tree-based Group Diffie Hellman (TBGDH).
    DOI: 10.1504/IJBET.2016.10005093
     
  • An Effective Design of Parity Check Matrix for LDPC Codes Using Multi-Objective Gravitational Search Algorithm   Order a copy of this article
    by S. Suresh Kumar, M. Rajaram 
    Abstract: The low Density Parity-Check code (LDPC) is an efficient contender for capacity approaching error correction over many important channels. In this paper, we design a parity check matrix for error correction using Multi-Objective Gravitational Search Algorithm. The overall steps of the proposed technique are explained with three steps: (i) new objective function generation (ii) optimized parity check matrix generation using MGSA (iii) An LDPC encoding-decoding system design. At first, a multi-objective function is derived based on four efficient objectives like low density, maximum hamming minimum distance, maximum marginal entropy, and maximum cyclic lifting degree. Our GSA based approach is developed with efficient agent representation, fitness computation along with usual GSA operators. Once the parity check matrix is computed, this matrix is utilized for LDPC encoding. The proposed approach is evaluated through Bit Error rate (BER) measure. From the results, we ensure that the proposed technique outperformed the existing technique by achieving the BER of 0.0513, 0.0348, and 0.0270 in fourth iteration.
    Keywords: LDPC; parity check matrix; SNR; BER; MGSA; objective function.

  • NIBG: An Efficient Near-Infrared Spectroscopy Based Device For Telemonitoring Blood Glucose Level of Diabetes Outpatients in eHealth System   Order a copy of this article
    by Oladayo Olakanmi, Ismaila A. Kamil, Olayinka P. Atilola 
    Abstract: Major conventional blood glucose measuring systems pose a lot of inconveniences to diabetes patients, such as recurring pains incurred from finger-prick, infections from biosensor implant into the subcutaneous tissue, recurring costs incurred from the purchase of strips and biosensors, and inability to perform real time monitoring of blood glucose with such devices, making them unsuitable for e-Health systems. This paper proposes a pain-free, non-infectious and Non-Invasive Blood Glucometer (NIBG) for blood glucose measurement and monitoring. The device is based on Near Infrared (NIR) transmittance spectroscopy which does not involve pricking into the blood capillary during measurement thereby reducing the risk of microvascular complication associated with invasive methods. Also the approach may reduce blood glucose measurement apathy thereby preventing long term complications of diabetes. Both the validation and clinical trial tests results indicated that the device is clinically accurate.
    Keywords: non-invasive; spectroscopy;electronic health; near-infrared; diabetes.

  • Detection of Missing Tooth from Dental radiographic and photographic images in Forensic Odontology   Order a copy of this article
    by Jaffino G, Banumathi A, Ulaganathan Gurunathan, Vijayakumari B, Prabinjose J 
    Abstract: Victim identification using dental radiographs is receiving much attention nowadays, since tooth is the more robust key component for forensic odontology. Missing tooth detection is one of the notable issues in dental identification system. Hence this work proposes a novel method for identifying the persons by considering the missing tooth in addition with the contours of other teeth. Online Region based Active Contour Model (ORACM) is used for shape extraction, and distance based matching algorithm is used to identify the person by comparing both ante-mortem and post-mortem dental images. It concentrates on radiographs and photographs of dental images since adequate radiograph images may not be available for all circumstances. The proposed method is well suited for person identification, and it could assist forensic odontologists to identify the victims in an accurate manner.
    Keywords: Forensic odontology; missing tooth; Bitewing dental images; hit rate.

  • Performance Comparison of MeRMaId-ICA and Np-ICA in Composite Abdominal ElectroCardioGram Separation   Order a copy of this article
    by Anisha Milton, Kumar S.S, Benisha M 
    Abstract: Blind source separation strives to disintegrate a multivariate composite non invasive abdominal electrocardiogram signal into independent non-gaussian signals such as maternal and fetal electrocardiograms. This paper proffers two separation algorithms especially for fetal Electrocardiogram (FECG) extraction as it has a great role in diagnosing the fetal heart deformities namely Minimum Renyis Mutual Information called MeRMaId algorithm and Non parametric Independent Component Analysis (Np-ICA) algorithm. Both the algorithms are experimentally evaluated on synthetic and real abdominal data. Performance juxtaposition of these two algorithms is done by scrutinizing the signal to noise ratio at assorted noise levels and signal to interference ratio at assorted amplitude levels, and computing correlation coefficient () of the original and the estimated maternal and fetal electrocardiograms.rnrn
    Keywords: Minimum Renyi’s Mutual Information; Non parametric Independent Component Analysis; Maternal electrocardiograms and fetal electrocardiogram.rnrn.

  • Optimizing Brain Map for the Diagnosis of Schizophrenia   Order a copy of this article
    by Reza Boostani, Malihe Sabeti 
    Abstract: State-of-the-art diagnosis of schizophrenia is just carried out upon qualitative criteria (e.g. DSM-V) at which no physiological data is measured; consequently, other psychotic disorders such as schizoaffective or delusional disorder, which have the similar criteria, might be misdiagnosis as schizophrenia. To overcome this drawback, a quantitative diagnosis tool, in the form of a novel brain map, is proposed to reveal the schizophrenic-dependent changes which are spatially distributed on the brain of these patients. First electroencephalogram (EEG) signals from 20 schizophrenic and 20 control subjects were acquired and then five bands power (standard bands) were elicited from each EEG channel. Discriminative bands were extracted using genetic algorithm (GA), particle swarm optimization (PSO) and ant colony optimization (ACO) and then were fed to Fisher linear discriminant analysis (FLDA) to classify the two groups. Experimental results demonstrate 83.74%, 81.41% and 81.06% classification accuracy for PSO, ACO and GA feature selectors, respectively. According to the selected band at each channel, a brain map is constructed and an average on the successive brain maps of patients and control subjects using GA, ACO and PSO algorithms were separately drawn. The proposed brain map, optimized by PSO, confirms the most differences between the two groups that are observed at PET, fMRI and CT images.
    Keywords: Brain map; GA; PSO; ACO; EEG; schizophrenic; band power.

  • Time-Time Analysis of Electroencephalogram Signals for Epileptic Seizure Detection   Order a copy of this article
    by Poonam Sheoran, J.S. Saini 
    Abstract: The detection and classification of epileptic seizures using the Electroencephalography (EEG) signals has been actively worked upon by the researchers from past few decades. This paper attempts a novel application of Time-Time Transform for analysis of electroencephalogram time-series for epileptic seizure detection by transforming it into secondary time-limited local constituent time-series. This technique (TT-Transform) of time-time representation of the EEG time series is derived from S-transform, i.e., Stockwell Transform (an extension of the wavelets), a method that represents a non-stationary time series as a set of complex time-localized spectra. With the help of TT-transform, a more informative representation of the time features of EEG signals has been obtained, around a particular point on the time axis which has been seen to prove very effective in seizure detection. As the TT-transform is completely invertible, it indicates frequency filtering & signal to noise improvements in the time domain. Features obtained upon application of TT-transform on EEG time-series are classified using Quadratic Discriminant Analysis and the correct classification rate obtained is 100%.
    Keywords: Short time Fourier Transform (STFT); Stockwell Transform (ST); Time-Time Transform (TT); Electroencephalogram (EEG); Time-Frequency analysis; Quadratic Discriminant Analysis (QDA).

  • Flexible Naor and Reingold Key Based Data Encryption/Decryption Scheme for Secured Remote Health Monitoring of Cardiac Patient using WBAN   Order a copy of this article
    by Muthuvel Somasundaram, R. Sivakumar 
    Abstract: Wireless Body Area Networks (WBANs) increase the demand of healthcare service to improve the quality of patients life. In WBANs, the security issues arise during monitoring of the patient body function and recording. Recently, many research works have been designed for secured remote health monitoring services. However, there is a need for effective remote health monitoring service model for enhancing the security and privacy of patients medical report. In order to overcome such limitations, a secure patient activity data monitoring through privacy preservation technique in handling medical health care services of patient in remote locations is proposed. The privacy preservation technique introduced in this work is Flexible Naor and Reingold Key based Data Encryption/Decryption (FNRK-DED) model. The FNRK-DED model is flexible on providing the data security for the different size of information. The FNRK-DED model develops a Naor and Reingold Key based Data Encryption algorithm to encrypt the cardiac patients medical information of different formats by preserving their input length. In encryption process, input is given as the cardiac patients medical report that needs to be encrypted with secret key. The output of an encryption process is n bits of cipher text which is transmitted through a wireless network in order to achieve secured remote health monitoring services in WBANs. In recipient side, the decryption process is performed to extract the encrypted cardiac patients medical report by using Naor and Reingold Key based Data Decryption (NRKDD) algorithm. The FNRK-DED model conducts the simulation works on parameters such as data privacy rate, security ratio based on patients health information, energy consumption rate and response time.
    Keywords: Wireless Body Area Networks; healthcare service; patient’s; security; Naor and Reingold Key; privacy preservation; cipher text.

  • Analysis and Evaluation of Classification and Segmentation of Brain Tumor Images   Order a copy of this article
    by M.P. Thiruvenkatasuresh, V. Venkatachalam 
    Abstract: Apparently, the development of a model to detect the tumor part in Brain images is of utmost significance. This is because Brain tumor can be considered as one of the serious and life- threatening tumors actually created either by the abnormal and uncontrolled cell division within the brain or from cancers primarily present in other parts of the body. In the initial phase of our work, brain tumor database images are occurred to the preprocessing module using adaptive median filter technique to gain clarity of the image. In addition to the preprocessing process, feature extraction techniques are applied and extracted to the features then the classification method as Support Vector Machine (SVM) classifier is used to classify the images as normal and abnormal. After classification the abnormal images are observed for segmentation process using Fuzzy C-Means (FCM) clustering process along with the occupied optimization methods. For optimizing centroid, the FCM used Social Spider Optimization (SSO) technique with Genetic Algorithm, these optimization techniques are used and the segmentation sensitivity attains 99%. In the final stage, the optimal centroid is utilized to obtain the extracted tumor part of the image. The proposed scheme has attained the maximum accuracy when compared to existing classification technique ANFIS and segmentation technique FCM (GWO).
    Keywords: Brian tumor images; Support Vector Machine (SVM); Fuzzy C-Means (FCM); Social Spider Optimization (SSO) and Genetic Algorithm (GA).

  • Computer Aided Automatic Detection of Glioblastoma Tumor in Brain Using CANFIS Classifier   Order a copy of this article
    by C.G. Ravichandran, K. Rajesh 
    Abstract: Detection and diagnosis of brain tumor is complicated due to its similar characteristics between tumor pixels and non tumor pixels in brain image. This paper proposes an efficient methodology for the detection and segmentation of Glioblastoma tumor region in brain. The proposed methodology for Glioblastoma tumor classifications has the following stages as noise reduction, image fusion, feature extraction and classification. The median filter is used to remove the noises in the brain images and pixel level image fusion is applied to obtain the enhanced brain image. The features are extracted from the fused image and Co-Active Neuro Fuzzy Inference System (CANFIS) classifier is used to classify the brain image into either benign or malignant. Further, morphological operations are applied on the classified malignant brain image inorder to segment the Glioblastoma tumor region. The proposed methodology achieves 96.43% sensitivity, 99.99% specificity and 99.91% accuracy with respect to ground truth images.
    Keywords: Glioblastoma tumor; median filter; malignant; features; classification.

  • Adaptive Digital Medical image watermarking approach in 2D-Wavelet domain using speed up robust feature method   Order a copy of this article
    by YARABHAM GANGADHAR, Giridhar Akula V.S., Chenna Reddy P 
    Abstract: In the recent trends, the utilization of digital images had got their importance in many fields. One of the major fields which had the more prominence utilization of digital images is health care. The patients information is stored in digital images for maintaining privacy and there is a need for preserving the content of the images. Watermarking serves well for protecting digital images. In this paper, Adaptive Digital Medical image watermarking approach is proposed. This proposed method utilizes the 2D-Wavelt domain for converting the medical image in to number of sub-bands. The interesting points are identified using the Speed up robust feature method (SURF). The scaling parameter is calculated for the digital images using the bipolar sigmoid function. The control parameter is introduced to adjust the scaling parameter and it plays a crucial role in deciding the strength of the watermark. Experimental evaluation is carried out using three parameters, Peak Signal to Noise Ratio (PSNR), Structure Similarity Measure (SSIM) and Normalized correlation coefficient (NCC). The experimental results proved that the proposed method had superior performance in both visible and invisible watermarking.
    Keywords: 2D-Wavelet domain; Watermarking; Medical images; Region of interest; SURF.

  • Study & Analysis of the Effect of RF Mobile Phone Waves on Human Brain When Operating at Charging / not Charging Mode   Order a copy of this article
    by Anupriya Saini, Manoj Duhan 
    Abstract: In the era of this technology, cell phone is a great boon for the communication purpose but this has many effects on human health too. The harmful EM (Electromagnetic) radiations emitted from the cell phone are having increased adverse effects on human health due to excess usage of mobile phone. The negative health effects on human are brain tumors, weakening of the immune system, increasing blood pressure, genetic damage, memory errors and many others. The radiations emitted from cell phone are invisible & untouchable and hence are more dangerous. This paper discusses the experiment which was conducted to study the effects of RF mobile phone waves on human brain when operating in charging/not charging mode. Electroencephalogram (EEG) is the technique used in this method to measure the electrical activity of the brain. The data used in the experiment was collected in a laboratory with the help of 5 volunteers. The result shows that it is more dangerous to use mobile phone when it is operating in charging mode. The value of PSD (Power Spectral Density) is the maximum at frequency 0-4Hz, decreases at 4-8Hz and then increases at 8-12 Hz frequency and continues decreasing at higher frequencies. Especially, at charging mode, during ringing P3-O1 & T5-O1 channels of the brain are more affected and during call ongoing, channels P4-O2 & T6-O2 are severely affected. When call is ongoing, the most affected channel is P4-O2 during charging of mobile phone. Thus, in order to reduce the effects of EMF radiations on human brain, the mobile phone during the charging must be avoided and call must be attended after the removal of mobile phone from charging.
    Keywords: EEG; Electroencephalogram; EM; Electromagnetic; RF; Radio frequency; GSM; global system for mobile communication; DSP; digital signal processing; PSD; power spectral density; RMS; recorders and medicare system.

  • Fuzzy Prediction and early detection of stomach diseases by means of combined iteration fuzzy models   Order a copy of this article
    by Riad Taha Al-Kasasbeh, Nikolay Korenevskiy, Mahdi Salman Alshamasin, Florin Ionescu, Elena Boitсova, Etab Al-Kasasbeh 
    Abstract: The work discusses aspects of decision rule synthesis for prediction and early diagnostics of stomach diseases. The distinguishing feature of heterogeneous fuzzy rules of decision making is the fact that they use information about the energetic condition of biologically active points and also features traditionally used in medical practice such as alchohol consumption, smoking tobacco, inheritance, etc. Use of different types of the original data allows us to provide diagnostic efficiency in decisions at the level 0.9 or greater, which makes it possible to recommend the research outcome for medical practice.
    Keywords: stomach diseases; fuzzy logic biologically active points; membership functions.

  • CLASSIFICATION OF WALL SHEAR STRESS OF HUMAN COMMON CAROTID ARTERY AND ASCENDING AORTA ON THE BASIS OF AGE   Order a copy of this article
    by Renu Saini, Sharda Vashisth, Ruchika Bhatia 
    Abstract: Wall shear stress is one of the major factors responsible for increase in cardiovascular disease. The present work calculate the level of wall shear stress in the common carotid artery (CCA) and aorta to see which artery has more chance of having cardiovascular diseases and at which age. Wall shear stress (WSS) is determined in the CCA and aorta of presumed healthy volunteers, having age between 10 and 60 years. A real 2D model of both aorta and common carotid artery is constructed for different age groups using computational fluid dynamics (CFD). WSS of both the arteries is calculated and compared for different age groups. It is found that with increase in diameter of common carotid artery and ascending aorta with advancing age wall shear stress decreases. WSS of aorta is found less than common carotid artery.
    Keywords: Ageing; Blood flow; Carotid artery; aorta; Wall shear stress.

  • PERFORMANCE ANALYSIS OF WAVELET BASIS FUNCTION IN DE-TRENDING AND OCULAR ARTIFACT REMOVAL FROM ELECTROENCEPHALOGRAM   Order a copy of this article
    by P. Prema, T. Kesavamurthy, K. Ramadoss 
    Abstract: The Event Related Potential (ERP) Brain- Computer Interface (BCI) system extensively uses the scalp electroencephalogram (EEG) for communication and motor control. It is a non-invasive procedure and the signal record has ERPs buried in EEG due to its low strength and it is usually contaminated with artifacts. For BCI control applications, the ocular artifacts produced by eye movement and blink which are dominant over the other physiological artifacts are undesirable. The objective of the study is to effectively remove the ocular artifact from EEG using Discrete Wavelet Transform (DWT) combined with Recursive Least Mean Square (RLS) adaptive noise cancellation technique using the optimal basis function with Stein's Unbiased Risk Estimate (SURE) thresholding. The proposed methodology is tested on the datasets created from the experimental setup measuring the performance metrics - Mean Square Error (MSE), Artifact to Signal Ratio (ASR), correlation coefficient and coherence. The results show that db4 wavelet performs better in de-trending and ocular artifact suppression by providing better signal to noise ratio and high level of coherence from 5Hz onwards while preserving the original EEG signal.
    Keywords: Ocular artifacts; EEG; EOG; physiological interference; DWT; adaptive filter; brain-computer interface; coherence; correlation; performance metrics.

  • DESIGN AND IMPLEMENTATION OF TEXTILE ANTENNA AND THEIR COMPARATIVE ANALYSIS OF PERFORMANCE PARAMETERS WITH OFF AND ON BODY CONDITION   Order a copy of this article
    by E.Thanga Selvi, Meena Alias Jeyanthi 
    Abstract: A wearable antenna is an important part of body area network (BAN) to communicate the health care information and secured information to the central hub. This paper presents the comparative study of rectangular shaped microstrip patch textile antenna for different conductive textile materials and conductive non textile materials. The textile antenna is designed, evaluated using ADS 2013.06 software and measured by N9926A 14GHz Field Fox Handheld Vector Network Analyzer for the ISM(industrial, scientific and medical) band application operated at the resonant frequency of (2.4-2.485) GHz. These textile antennas are analyzed and compared by the performance parameters like VSWR, reflection coefficient, bandwidth, impedance, directivity and gain. The results of the proposed design shows the return loss of -53.32dB, the VSWR as 1, and 100% efficiency, narrow bandwidth, effective directional radiation pattern, 50 ohm impedance, highest gain and directivity of about 5dB and 5dBi. The micro strip patch antennas are good candidates for body-worn applications, as they radiate perpendicularly to the planar structure and their ground plane shields the body tissues efficiently. This proposed textile antenna may also be suitable for wearable tele communication, wearable tele medicine application, body centric area network, Wi-Fi, WLAN applications and for communication purposes such as tracking, navigation, mobile computing and public safety.
    Keywords: BAN(body area network),Inset feed; ISM band; pure copper polyester taffeta fabric; copper foil tape with conductive adhesive; copper sheet; N9926A 14GHz Field Fox Handheld Vector Network Analyzer.

  • A combined hierarchical algorithm of mammograms registration using mutual information and a point based matching approach   Order a copy of this article
    by Meryem Loucif, Bornia Tighuiouart 
    Abstract: Mammographic image registration is an important process in the comparative analysis of mammograms that aims to correctly interpret them. In this paper, we proposed a combined hierarchical framework for a non rigid mammograms registration. So, the conjoint use of the multiresolution and the multigrid hierarchical strategies allows to increase progressively the warp complexity with a fixe size of the manipulated data contributed then to a finest registration with acceptable computing cost. To perform registration process, a hybridization of an intensity-based registration method using mutual information and a point-based matching approach using the Thin Plat Spline approach is achieved. This hybridization allows not only to outperform the registration accuracy by using the mutual information as a similarity measure adapted to non similar images but also to decrease the algorithm convergence time. Registration performance evaluated by aligning mammograms from the MIAS database and results demonstrate the effectiveness of the proposed algorithm for mammograms registration.
    Keywords: mammograms registration; MIAS database; mutual information; geometric matching; multiresolution approach; Gaussian pyramid; combined hierarchical algorithm; progressive subdivision strategy; Thin Plat Spline.

  • A Comparison of sEMG and MMG signal Classification for automated muscle fatigue detection   Order a copy of this article
    by M.R. Al-Mulla, Francisco Sepulveda 
    Abstract: This study compares the classification performance of both sEMG and MMG signal from fatiguing dynamic contraction of the biceps brachii. Commonly used statistical features are compared with a recently developed evolved pseudo-wavelet. Based on the literature, wavelet-based methods are a promising feature extraction technique for both types of signals (sEMG and MMG) during dynamic contractions. MMG results show that the evolved pseudo-wavelet improved the classification rate of muscle fatigue by 4.70 percentage points to 27.94 percentage points when compared to other standard wavelet functions, giving an average correct classification of 80.63%, with statistical significance (p < 0.05). For sEMG signals the evolved pseudo-wavelet improved the classification rate of muscle fatigue by 4.45 percentage points to 14.96 percentage points when compared to other standard wavelet functions (p < 0.05), giving an average correct classification of 87.90%. The comparison demonstrates that for both the sEMG and the MMG signal, the feature giving best classification results was the evolved pseudo-wavelet.
    Keywords: Localised Muscle Fatigue; Electromyography; Mechanomyography; Wavelet analysis; Pseudo-wavelets.

  • Morphological Detection and Neuro-Genetic Classification of Masses and Calcifications in Mammograms for Computer-Aided Diagnosis.   Order a copy of this article
    by Fatma Zohra Reguieg, Nadjia Benblidia, Mhania Guerti 
    Abstract: Diagnosis of breast cancer is the main worry of oncologists of this era, which knows an anxiogenic increase of the incidence in the world. This paper is destined for the semi-automatic detection of breast neoplasm taken, from digital mammograms of MIAS database (Mammographic Image Analysis Society). This research is focusing on analysis of masses and, calcifications. Therefore, the first phase of the system consists, on pre-processing of pathological structures, by morphological transformations in order to refine, the segmentation. The second step, realizes extraction of clinical signs, according to adaptive deformable model which initialization is guided by, the annotated suspicious zone. The third block is to characterize abnormalities, by morphometric and textural attributes, to generate their signature. The ultimate systemic description, categorizes malignant and benign masses and calcifications from their knowledge, by a neuro-genetic classifier for computer-aided diagnosis. The elaborated decisional system, products, an accuracy of 99.25%, for the shape recognition.
    Keywords: Digital Mammogram; Deformable Model; Texture and Morphometry; Neuro-genetic Classification; Computer-Aided Diagnosis.

  • Analysis of Speech Imagery Using Brain Connectivity Estimators on Consonant-Vowel-Consonant (CVC) Words   Order a copy of this article
    by Sandhya Chengaiyan, Kavitha Anandan 
    Abstract: Speech imagery refers to the perceptual experience of uttering speech to oneself without any articulation. In this paper, the neural correlations between brain regions associated with articulated and imagined speech processes of Consonant-Vowel-Consonant (CVC) words are analyzed using brain connectivity estimators. EEG Coherence, a synchronization parameter establishes the correlation between several cortical areas. To analyze the causal dependence, Partial Directed Coherence (PDC) and Directed Transfer Function (DTF) estimators are derived from multi- channel EEG data. From inter and intra hemispheric coherences it has been observed that theta, beta and gamma frequencies were dominant and words with same vowel having one consonant common have similar coherence values. Results inferred from intra-hemispheric PDC and DTF parameters show that the frontal and temporal regions of the left hemisphere are more activated for all the given speech imagery tasks. Thus, the analysis provides a significant step in understanding the neural interactions of the brain while thinking and articulating processes.
    Keywords: Speech Imagery; Electroencephalography (EEG); EEG Coherence; Partial Directed Coherence(PDC); Directed Transfer Function(DTF); Consonant-Vowel-Consonant(CVC) words.

  • Wireless Speech Control System for Robotic Arm   Order a copy of this article
    by Biswajeet Champaty, Suraj K. Nayak, Ashirbad Pradhan, Sirsendu S. Ray, Biswajit Mohapatra, Indranil Banerjee, Arfat Anis, Kunal Pal 
    Abstract: Speech-controlled devices have been explored for potential applications in rehabilitation technology. These systems have shown great promises in improving the independence of differently-abled persons by providing hands-free operation of the rehabilitative aids. The present study delineates the development of a speech-activated wireless control system for controlling rehabilitative devices. A robotic arm was used as the representative rehabilitative device and this technology can be extended to operate other rehabilitative aids (e.g. wheelchairs). The performance of the device was evaluated using 10 volunteers. All the volunteers were able to accurately complete the desired movements of the robotic arm with relative ease. The developed device is simple and user-friendly.
    Keywords: Speech; Rehabilitative device; Robotic arm; XBee; Arduino.

  • Mix-Model for Optimization of Textural Features Applied to Multiple Sclerosis Lesion-Tumor Segmentation   Order a copy of this article
    by A. Lakshmi, T. Arivoli, Pallikonda Rajasekaran Murugan 
    Abstract: Segmentation of biomedical images plays an important role in many applications especially in medical imaging, forming an important step in enabling qualification in the field of medical research as well as clinical practices. Magnetic Resonance Imaging is normally used to distinguish and enumerate Multiple Sclerosis lesions in the brain. Recently Multiple Sclerosis lesion of segmentation is the challenging issue due to special variation, low size and unclear boundaries. Since usual technique for brain MRI tumor detection and classification is manual investigation but it is varied from person to person and also very time consuming. Many new methods have been proposed to segment lesions automatically. This paper proposed segmentation of MRI brain tumor using cellular automata and classification of tumor by Pointing Kernal Classifier (PKC). The utilization of modified Cuckoo Search with the priority values and the PKC in proposed Mix Model for Optimization of Textural Features (M-MOTF) provides the significant improvement in classification performance with low dimensionality. The proposed system has been validated with the support of real time data set from Frederick National Laboratory and the experimental results showed improved performance.
    Keywords: Pointing Kernal Classifier (PKC);Mix Model for Optimization of Textural Features (M-MOTF);Distributed Adaptive Median Filtering(DAMF);Multi-Angle Cellular Automata (M-ACA);Dynamic Angle Projection Pattern(DAPP).

  • Optimized DWT using cooperative particle Swarm Optimizer for hybrid domain based Medical and Natural Image Denoising   Order a copy of this article
    by A. Velayudham, K. Madhan Kumar, R. Kanthavel 
    Abstract: The quest for productive image denoising systems still is a valid challenge, at the intersection of practical investigation and measurements. In spite of the sophistication of the recently proposed systems, most calculations have not yet achieved an attractive level of applicability. In this research, an optimal wavelet filter coefficient design-based methodology is proposed for image denoising. The method utilizes new wavelet filter whose coefficients are derived by discrete wavelet (haar) transform using CPSO optimization and bilateral filter. The optimal wavelet coefficient based denoising methods minimize the noise, while bilateral filter further decreases the noise and increases the PSNR without any loss of relevant image information. Overall, the proposed approach consists of two stages namely, (i) Design of optimal wavelet filter, ii) Image denoising using a bilateral filter. At first, wavelet optimal coefficients are selected using cooperative particle swarm optimizer (CPSO). After that, the hybrid domain based algorithm (wavelet with bilateral filter) is applied to the noisy image which is helpful to obtain the denoised image. A comparative study of the performance of different existing approaches and the proposed denoised approach is made in terms of PSNR, SDME, SSIM and GP. When compared, the proposed algorithm gives better PSNR compared to the existing methods.
    Keywords: image denoising; optimal wavelet; bilateral filter; cooperative particle swarm optimizer; wavelet coefficient; sub-bands.

  • Effective Facial Expression Recognition System Based on Hybrid Classification Technique   Order a copy of this article
    by J. Sunetha, K. Sandhya Rani 
    Abstract: In our daily life, facial expression recognition has possible functions in various sectors but still it is not understand, because the absence of efficient expression identification methods. Many methods are used to develop the effectiveness of the identification through indicating issues in face detection and extraction aspects in identification expressions. In the first phase, the noise is eliminating from the image by using of preprocessing techniques and to obtain the quality image in order to decrease the computational complexity. The following phase is feature extraction phase. In this phase, we are extracting related features like eyes, mouth and nose. The shape feature of eye part can be extracted by Active Appearance Model (AAM). The texture feature of nose and mouth can be extracted using Gray-Level Co-Occurrence Matrix (GLCM). Then in the final phase, we have to categorize a facial expression for this categorization process by introducing an Adaptive Genetic Fuzzy Classifier (AGFS) and Neural Network (NN). Finally, score level fusion of this two classification result will be done to obtain the face emotions.
    Keywords: Dr.K.Sandhya Rani; M.Sc ; M.Tech; Ph.D is presently working as Computer Science Professor in Sri Padmavati Mahila Visvavidyalayam ( SPMVV ); Tirupati. This university is established in 1983 and a second women’s university in the country. She is a senior most faculty in the department. She is having 30 years of teaching experience & 18 years of research experience in SPMVV and published more than 50 papers in reputed National and International journals. Her thrust areas of research are Pattern Recognition; Data Mining and Big Data Analytics. She served the department and university in various positions such as Head; Dean Student Affairs; NAAC Coordinator and Dean Development.

  • Evaluation of the Effect of Posture on Carotid-to-Toe Pulse Transit Time Values Estimated Using System Identification   Order a copy of this article
    by Aws Zuhair Sameen, Rosmina Jaafar, Edmond Zahedi 
    Abstract: Pulse Transit Time (PTT), a marker of arterial stiffness, is defined as the time a pulse wave needs to travel from one point of the blood circulation to another point. Monitoring PTT values of a person is useful in non-invasive, cuff-less estimation of blood pressure measurement. The challenge is how to estimate the PTT values continuously from the subject with accurate readings. In this paper, PTT values estimated from two PPG signals from the reflective photoplethysmography of carotid and toe that are collected from 12 healthy subjects (8 males and 4 females) age 23.8
    Keywords: Pulse Transit Time (PTT); System Identification; Photoplethysmogram (PPG); ARX model; Time Delay Estimation.

  • GENETIC TIME SERIES MOTIF DISCOVERY FOR TIME SERIES CLASSIFICATION   Order a copy of this article
    by RAMANUJAM ELANGOVAN, Padmavathi S 
    Abstract: Time Series is a sequence of continuous data and unbounded group of observations found in many applications. Time series motif discovery is an essential and important task in time series mining. Several algorithms have been proposed to discover motifs in time series. These algorithms require user-defined parameters such as length of the motif, support or confidence. However, selection of these parameters is not an easy issue. To overcome the challenge, this paper proposes a Genetic Algorithm with constraints to discover good trade-off between representative and interesting motif. The discovered motifs are validated for their potential interest in Time Series Classification problem using Nearest Neighbor classifier. Extensive experiments show that the proposed approach can efficiently discover motifs with different length and to be more accurate and statistically significant than state-of-the-art time series techniques. Finally, the paper demonstrates the efficiency of motif discovery in large medical data from MIT-BIH-Arrhythmia database to classify the abnormal signals.
    Keywords: Genetic Algorithm; constraints; Time series classification; UCR Archive; MIT-BIH-Arrhythmia;.

  • Facial Expression Synthesis Images Using Hybrid Neural Network with Particle Swarm Optimization Techniques   Order a copy of this article
    by Deepti Chandra, Rajendra Hegadi, Sanjeev Karmakar 
    Abstract: In the advance life trend, the facial expression is the visual facial outer structure of the human affective state, intellectual action, and human interchanges and facial expression go about as the key role in the movement of communication. The human - computer interfaces are processed by the computer which is able to connect with people through facial expression and the above surfaces the path for the base of communication. This is further contrasted with the human-human association. In this paper, the facial expression synthesis performance is done using different facial expressions such as angry, sad, smile, surprise and cry of various peoples. The pre-processed image and the landmark points are shaped automatically by the viola-Jones algorithm. In the proposed method, two procedures are used namely Hybrid Neural Network (HNN) and Particle Swarm Optimization (PSO) algorithm. By training particle swarm optimization and hybrid neural network, we take the desired output. In the result section, various evaluation metrics namely Peak to Signal Noise Ratio (PSNR), Mean Square Error (MSE) and a Second-Derivative-Like Measure of Enhancement Value (SDME) is calculated using diverse algorithms. In this evaluation performance, the particle swarm optimization is given enhanced output while comparing it with other techniques and the existing methods of facial expression.
    Keywords: Facial expression; Hybrid Neural network; viola-Jones algorithm; Particle Swarm Optimization (PSO).

  • Embedded Binary PSO Integrating classical methods for Multilevel Improved Feature Selection in liver and kidney disease diagnosis   Order a copy of this article
    by Gunasundari Selvaraj, Janakiraman Subbiah, Meenambal Selvaraj 
    Abstract: Feature selection is an important preprocessing technique in the field of data mining. This process removes irrelevant data thereby reduces the number of features. This paper presents a new algorithm called embedded binary particle swarm optimization (BPSO) to improve the performance of BPSO for feature selection. Embedded BPSO incorporates classical methods to select elite feature subset. The population is refined or extended at regular intervals using the best features from sequential forward selection and sequential backward selection methods. In this study, probabilistic neural network and support vector machine with 3-fold cross validation are used to evaluate the particles. The embedded algorithm is verified in the feature selection module of the liver and kidney cancer diagnostic system. The elite features extracted from wrapper based embedded algorithm are used to characterize diseases using the classifier. Findings show that the proposed system is proficient in selecting the best features with minimum error rate.
    Keywords: Binary particle swarm optimization; feature selection; sequential forward selection; sequential backward selection; liver cancer; kidney cancer; computer-aided diagnostic system; medical imaging; benign; malignant.

  • Iterative Modelling of the Closing-based Differential Morphological Profile   Order a copy of this article
    by Arif Muntasa, Indah Agustien Siradjuddin 
    Abstract: One of an image processing applications is retinal image optic disk detection. The similarity of the retinal gray scale image between the object and background has been interesting many researchers to develop the research. In this research, the Closing based Differential Morphological Profile is proposed to detect the optic disc on the retinal image. The closing process is performed by iterative. It is started by pre-processing and followed by Different Morphological Profile based on the closing operation i.e. the dilation and erosion processes. The dilation process is iteratively performed and followed by erosion process. The process results are enhanced to obtain the better image when the binary image transformation is conducted. The noise removal process is also necessity to eliminate the detection error. Furthermore, determining of the point centre of the object detection result will be used to create the optic disk. The detection rates of the proposed approach show that the maximum detection accuracy outperformed to the other methods, i.e. 2D-Gaussian Filtering Based Mathematical Morphology Approach, Differential Morphological Profile, Morphological Reconstruction Techniques and Hybrid Fuzzy Classifier.
    Keywords: Differential morphological profile; iterative modelling; optic disk image detection; closing operation.

  • Aligning Large Biomedical Ontologies for Semantic Interoperability using Graph Partitioning   Order a copy of this article
    by Sangeetha Balachandran, Vidhyapriya Ranganathan, Divya Vetriveeran 
    Abstract: Ontologies, formal specifications of domain knowledge, play an imperative role in the semantic web and are developed by several domain experts in the biomedical field. Ontology alignment or mapping is the process of identifying correspondences among the concepts in the ontology to facilitate data integration between heterogeneous data sources. The alignments generated augment information retrieval process, web service composition, drug discovery, identifying new gene patterns in species. In particular, the proposed ontology mapping system addresses three pivotal issues: (i) To Facilitate the automated alignment process by incorporating Random Forests (RF), an ensemble learning system that is stable for outliers. In addition, it facilitates training the individual random trees in parallel, and thereby reducing the execution time (ii) To Improve the execution time by partitioning the ontologies using cluster-walktrap [24] methodology and identify the correspondence between the concepts in parallel and (iii) To identify equivalence and non-equivalence correspondences based on the description, labels and object properties associated with concepts in the ontologies. The ontologies subjected to the mapping system are partitioned into sub-ontologies and the sub-ontologies having higher cosine similarity measure is selected as the candidate ontologies for further mapping. The performance of the system is pragmatically evaluated on benchmark datasets in the anatomy and large biomedical ontology tracks of the Ontology Alignment and Evaluation Initiative (OAEI) 2013 and 2014. With the aid of the proposed system, quantifiable improvement is noticed to an extent of about 4.4% in average precision, recall and F-measure. The performance of the proposed ontology mapping process is improved to an extent of 3%, compared to the state-of-the-art ontology mapping tools, for large biomedical ontologies. The alignments generated are represented using Alignment API suggested by OAEI for consistent representation and further, to ease the process of evaluation.
    Keywords: Ontology alignment; Ontology Mapping; Semantic information retrieval; Data integration; Biomedical informatics; Semantic interoperability.

  • Characterization of Breast Tissue using compact Microstrip antenna   Order a copy of this article
    by Vanaja Selvaraj, Poonguzhali Srinivasan, Divya Baskaran, Rahul Krishnan 
    Abstract: This paper presents a more improved method to characterize the breast tissue by employing a unique microstrip antenna. The pattern of the proposed antenna consists of a radiating patch with a rectangular slot, three stubs, a feed-line and a partial ground plane. Several parameters are used to analyze the microstrip antenna. The antenna designed provides a wide usable frequency band range from 2.4-4.76 GHz. In order to observe the interaction between the antenna and breast tissue, a heterogeneous breast model having dielectric characteristics similar to the human tissue is used. The tumor in the breast tissue is analyzed by measuring the resonant frequency of the reflected signal. The results show that the shift in resonant frequency decreases as the size of tumor increases due to dielectric variation in the breast tissue.
    Keywords: wideband; heterogeneous; microstrip antenna; breast tissue.

  • A Hybrid K-Means Algorithm Improving Low-Density Map Based Medical Image Segmentation with Density Modification   Order a copy of this article
    by Srinivasa Reddy A., Pakanati Chenna Reddy 
    Abstract: Segmentation is grouping of a set of pixels, which are mapped from the structures inside the prostate and the background image. The main aim of this research is to provide a better segmentation technique for medical images by solving the drawbacks that currently exist in the density map based discriminability of feature values. In this paper, we have proposed a method for image segmentation based density map segmentation properties medical image. The accurateness of the resultant value possibly not up to the level of anticipation while the dimension of the dataset is high because we cannot say that the dataset chosen are free from noises and faults. The kernel change i.e. segmentation is made by using Hybrid K-means Clustering Algorithm. Thus this method is used to provide the segmentation processing information as well as also be noise free output in an efficient way. Hence, the developed model is implemented in the working platform of Matlab and the output is compared with the existing techniques such as FCM, K-means to evaluate the performance of our proposed system.
    Keywords: Medical Image Segmentation; Hybrid K-Means Algorithm; Skull striping; FCM; K-Means; Genetic Algorithm.

  • AN ENHANCED TBAHIBE-LBKQS TECHNIQUES FOR PRIVACY PRESERVATION IN CLOUD   Order a copy of this article
    by Rachel Nallathamby, Rene Robin CR 
    Abstract: In recent days, providing security to the data stored in cloud is an important and challenging task. For this purpose, several existing privacy preservation and encryption algorithms are proposed in the existing works. But, it has some drawbacks such as, high cost, required more amount of time for execution and low level security. In order to overcome all these drawbacks, this paper proposes a novel techniques such as, Tiered Blind and Anonymous Hierarchical Identity Based Encryption (TBAHIBE) and Location Based Keyword Query Search (LBKQS) for providing privacy preservation to the data stored in cloud environment. In this work, the privacy is provided to the medical data stored in the Electronic Health Record (EHR). It includes two modules such as, secure data storage and location based keyword query search. In the first module, the medical data of the egg and sperm donor, receptor, doctor and lab technician are stored in the encrypted format by using the proposed TBAHIBE technique. Here, the authenticated persons can view the medical data, for instance, the doctor can view the donor and receptor medical details. In the second module, the location based search is enabled based on the keyword and query. Here, the doctor, patient and other users can fetch the medical details in a filtered format. The main advantage of this paper is, it provides high privacy to the medical data in a secured way. The experimental results evaluate the performance of the proposed system in terms of computation cost, communication cost, query evaluation, encryption time, decryption time and key generation time.
    Keywords: Cloud Computing; Privacy Preservation; Egg Donor; Sperm Donor; Tiered Blind and Anonymous Hierarchical Identity Based Encryption (TBAHIBE) and Location Based Keyword Query Search (LBKQS); Electronic Health Record (EHR).

  • A Pervasive Multi-Distribution Perceptron and Hidden Markov Model For Context Aware Systems   Order a copy of this article
    by Shaheen H., Karthik S. 
    Abstract: Fueled by the recent advancements in pervasive environment, affluent context aware systems is among the rousing in computing today, including embedded environment, different wireless network technology, electronic communication and so on. Context-Aware Collaborative Filtering using Genetic Algorithm approach resulted in an improved mobile business model by determining optimal similarities between contexts. In this work, we plan to devise a hybrid framework called Multi-distribution Perceptron and Hidden Markov Model to smoothen the mobile networks with different degrees of context- confidence. Initially, Multi-distribution Layer Perceptron Model is designed aiming at improving the precision rate with the aid of Multi-distribution Bayesian Posterior measure. Experimental analysis shows that the M-PHMM framework is able to reduce the computational complexity for obtaining user patterns by 26.05% and improve the precision rate by 18.90% compared to the state-of-the-art works.
    Keywords: Context Aware; Collaborative Filtering; Genetic Algorithm approach; Multi-distribution Perceptron; Hidden Markov Model.

  • Low cost Device for early diagnosis of Chronic Obstructive Pulmonary Disease   Order a copy of this article
    by Monica Subashini Mohan Chandran, Tushar Talwar, Rohit Mazumder 
    Abstract: Chronic Obstructive Pulmonary Disease (COPD) is characterized by increasing breathlessness. Many people mistake their increased breathlessness and coughing as a normal part of aging. In the early stages of the disease, the symptoms are unnoticed. The symptoms in the more developed stages of the disease are seen. Thats why it is important that we have an easy to use device for diagnosis. All available devices in the market either need doctors help to interpret or are inaccurate. The proposed device solves the purpose of primary diagnosis of COPD, which enables the patient to do a self-test of his lungs capacity. The lung capacity is estimated by the amount of air the exhaled during the test. The sensor system of the device includes a rotary sensor which enables the patient to have precise and accurate information every time. The device has a modern and interactive application which gives the patient access to a detailed report on his lungs condition. The application also features exercise mode in which the patient can do simple breathing exercises to prevent and treat COPD from early stage. The device has been validated and processed by conducting self-diagnosis with people between ages of 20-45 with 87% accuracy. Thus our device can be used for primary diagnosis of COPD.
    Keywords: COPD;rotary sensor;lung capacity; diagnosis.

  • Power Efficient FIR Digital Filter Design Based on FFA using ERC-Multiplier   Order a copy of this article
    by R.P. Meenaakshi Sundhari, R. Anitha 
    Abstract: In this paper, we propose the Power Efficient FIR Digital Filter Design Based on FFA using ERC-Multiplier. At the expenditure of extra adders and multiplexers in preprocessing and post processing blocks the projected parallel FIR structures develop the inherent nature of symmetric coefficients dropping the quantity of multipliers in sub filter sector. Also filter design accomplishes power reduction at the expense of area. Using of registers, adders and mix, added to the area it will reduce the power consumption efficiently since conventional multiplier is substituted by the ERC multiplier that is designed.
    Keywords: Multiplier; ERC multiplier; FFA; Digital signal processing (DSP); fast finite-impulse response (FIR) algorithms (FFAs); parallel FIR; symmetric convolution.

  • Mathematical Model based ontology for Human Papillomavirus in India   Order a copy of this article
    by GEETHA RAJESH KUMAR, SIVASUBRAMANIAN S 
    Abstract: Cervical cancer is a life threatening disease contracting women population in great numbers. It is the fifth most common cancer having high impact on human mortality. The second most common cancer prevalent among women worldwide is cervical cancer. Cervical cancer is due to sexually transmitted virus known as Human Papillomavirus (HPV). In this paper a Mathematical model and Ontological representation of this model HPVMath ontology has been formulated to expose the viability of HPV which leads to cervical cancer in women. Mathematical models translate data in to trials which gives deep insights about women population: not suspected for HPV, suspected for HPV, with HPV without cervical cancer, with HPV with cervical cancer. These trials from short term findings can lead to long term health outcomes. In addition HPVMath ontology representation formalizes a common view for HPV prevalence which can in turn assist medical practitioners and generate awareness among common men. This paper explores and defines the circumstances of HPV in to an ethical focus in an age characterization by the worldwide environmental threats.
    Keywords: Cervical cancer; HPV; Mathematical model; Ontology.

  • Design and Developing a Photoplethysmographic Device Dedicated to the Evaluation of Representative Indexes in the Response to Vascular Filling Using Systolic Time Intervals   Order a copy of this article
    by Nasr Kaid Ali Moulhi, Mohammed Benabdellah, Amine Aissa Mokbil Ali 
    Abstract: In this study, we develop an interface (human -machine) for monitoring the cardiovascular-respiratory system, through the evaluation of analogous indices obtained from a finger photoplethysmography pulse oximetry waveform. This interface consists of sensors, electronics associated with these sensors, acquisition card to make the communication with a local computer post and a graphical interface developed in Visual Basic Environment for signals tracing and data archiving. In this work we achieved the evaluation of representative indexes for the response to vascular filling, using systolic time intervals (STIs) namely, pre ejection period (PEP), respiratory change in pre ejection period (ΔPEP), left ventricular ejection time (LVET) and systolic time ratio (STR). Given that STIs are highly correlated to the fundamental cardiac functions. In order to achieve this goal, a data collection study was conducted using synchronized acquisitions of electrocardiogram (ECG), photoplethysmogram (PPG) and pneumotachogram (PTG) signals.
    Keywords: ECG; PPG; PTG; PEP,ΔPEP; LVET; STR; STIs; RS232; Microcontroller; Visual Basic; Vascular Filling.

  • Integration of global and local features based on Hybrid Similarity Matching Scheme for Medical Image Retrieval System   Order a copy of this article
    by Ajitha Gladis 
    Abstract: Similarity measure is a challenging task in content-based medical image retrieval (CBMIR) systems and the matching scheme is designed to improve the retrieval performance. However, there are several major shortcomings with conventional approaches for a matching scheme which can extensively affect their application of medical image retrieval (MIR). To overcome the issues, in this paper a multi-level matching (MLM) method for MIR using hybrid feature similarity is proposed. Here, images are represented by multi -level features including local level and global level. The Color and edge directivity descriptor (CEDD) is used as a color and edge based descriptor. Speeded-up Robust Features (SURF) and Local binary pattern (LBP) is used as a local descriptor. The hybrid of both global and local features yields enhanced retrieval accuracy, which is analyzed over collected image databases. From the experiment, the proposed method achieves better accuracy value about 92%, which is higher than other methods.
    Keywords: CBIR; local features; global features; multi-level matching; hybrid; similarity; descriptor; CEDD; LBP; SURF.

  • Automatic stenosis grading system for diagnosing coronary artery disease using coronary angiogram   Order a copy of this article
    by NANDHU KISHORE A.H., JAYANTHI VE. 
    Abstract: The coronary angiogram is considered as the golden standard for diagnosing the coronary artery disease. The paper proposes a system that helps to describe the level of stenosis in coronary angiogram image by using mathematical morphology and thresholding technique. A novel method is introduced to determine the percentage of stenosis and its grading. Based on the diagnostic results, myocardial infarction (MI) is treated well-in-advance. A real time clinical dataset consisting of 25 conventional coronary angiographies with 865 frames is used to evaluate the performance of the proposed system. The execution of the proposed system is inspected by a cardiologist and confirmed the system has produced excellent segmentation and stenosis grading automatically. Sensitivity, specificity, accuracy and precision of the system are 94.74%, 83.33%, 92% and 94.74% respectively with an average computational time of 0.84 sec. Kappa value also shows perfect system agreement for stenosis grading.
    Keywords: coronary artery disease; coronary angiogram; coronary artery segmentation; stenosis detection; stenosis grading.

  • Particle Swarm Optimization aided Weighted Averaging Fusion Strategy for CT and MRI Medical Images   Order a copy of this article
    by Madheswari Kanmani, Venkateswaran Narasimhan 
    Abstract: Multimodal medical image fusion is a technique that combines two or more images into a single output image in order to enhance the accuracy of clinical diagnosis. In this paper, a non-subsampled contourlet transform (NSCT) image fusion framework that combines CT and MRI images is proposed. The proposed method decomposes the source images into low and high frequency bands using NSCT and the information across the bands are combined using weighted averaging fusion rule. The weights are optimized by particle swarm optimization (PSO) with an objective function that jointly maximizes the entropy and minimizes root mean square error to give improved image quality, which makes different from existing fusion methods in NSCT domain. The performance of the proposed fusion framework is illustrated using five sets of CT and MRI images and various performance metrics indicate that the proposed method is highly efficient and suitable for medical application in better decision making.
    Keywords: Image fusion; CT image; MRI image; NSCT; PSO; Weighted average fusion strategy.

  • Design of artificial pancreas based on the SMGC and self-tuning PI control in type-I diabetic patient   Order a copy of this article
    by Akshaya Kumar Patra, Pravat Kumar Rout 
    Abstract: Optimal closed loop control of blood glucose (BG) level has been a major focus for the past so many years to realize an artificial self regulating insulin device for Type-I Diabetes Mellitus (TIDM) patients. There is urgency for controlled drug delivery system to design with appropriate controller not only to regulate the blood glucose but also for other chronic clinical disorders requiring continuous long term medication. As a solution to the above problem, a novel optimal self-tuning PI controller is proposed whose gains dynamically vary with respect to the error signal. The controller is verified with a nonlinear model of the diabetic patient under various uncertainties arises in various physiological conditions and wide range of disturbances. A comparative analysis of self-tuning PI controller performance has been done with the sliding mode Gaussian control (SMGC) and other optimal control techniques. Obtained results clearly reveal the better performance of the proposed method to regulate the BG level within the normoglycaemic range (70-120 mg/dl) in terms of accuracy, robustness and handling uncertainties.
    Keywords: type-I diabetes mellitus; insulin dose; artificial pancreas; micro-insulin dispenser; SMGC; self-tuning PI control.

  • Optimized Denoising scheme via Opposition based Self-adaptive learning PSO algorithm for Wavelet Based ECG Signal Noise Reduction   Order a copy of this article
    by Vinu Sundararaj 
    Abstract: Electrocardiographic (ECG) signal is significant to diagnose cardiac arrhythmia among various biological signals. The accurate analysis of noisy Electrocardiographic (ECG) signal is very motivating challenge. According to this automated analysis, the noises present in Electrocardiogram signal need to be removed for perfect diagnosis. Numerous investigators have been reported different techniques for denoising the Electrocardiographic signal in recent years. In this paper, an efficient scheme for denoising electrocardiogram (ECG) signals is proposed based on a wavelet based threshold mechanism. This scheme is based on an Opposition based Self-Adaptive Learning particle swarm optimization (OSLPSO) in dual tree complex wavelet packet scheme, in which the OSLPSO is utilized to for threshold optimization. Different abnormal and normal Electrocardiographic signals are tested to evaluate this approach from MIT/BIH arrhythmia database, by artificially adding white Gaussian noises with variation of 5dB, 10dB and 15dB. Simulation result illustrate that the proposed system is well performance in various noise level, and obtains better visual quality compare with other methods.
    Keywords: Electrocardiogram; denoising; DTCWPT; Self-Adaptive Learning; Opposition learning; Particle swarm optimization; MIT/BIH arrhythmia; Thresholding.

  • Optimal ECC Based Signcryption Algorithm for Secured Video Compression Process in H.264 Encoder   Order a copy of this article
    by S. Rajagopal, A. Shenbagavalli 
    Abstract: Combination of cryptography method and video technology is a Video encryption. Video encryption process is a total and demonstrable security of video data. For the purpose of protecting the video sequence, we have intended to recommend a video compression procedure along with its encryption for providing secured video compression framework. In this document we have suggested a method for ECC based Signcryption algorithm for Secured video compression process. At first, encryption process will be used on the motion vector by applying ECC (Elliptic Curve Cryptography) based Signcryption algorithm. The suggested method uses ECC method for the generation of public and private key. At the point when contrasted with the other encryption algorithms like small key, more security, increased velocity, little storage space and low data transfer capacity ECC has particular preferences. The suggested method employs the Improved Artificial Bee Colony algorithm (IABC) in order to optimize the private key. Next the optimal selection of private key applied to encrypt the motion vector. By means of different security attacks such as Man in Middle (MiM) attack, Brute Force and Denial of Service (DOS) attacks, the security of the suggested method will be examined.
    Keywords: Video encryption; Video compression; signcryption; Elliptic Curve Cryptography; Improved artificial Bee Colony algorithm; Brute force; DOS attack.

  • Automatic biometric verification algorithm based on the bifurcation points and crossovers of the retinal vasculature branches   Order a copy of this article
    by Talib Hichem Betaouaf, Etienne Decenciere, Abdelhafid Bessaid 
    Abstract: Biometric identification systems allow for the automatic recognition of individuals on one or more biometric characteristics. In this paper, we propose an automatic identity verification algorithm based on the structure of the vascular network of the human retina. More precisely, the biometric template consists of the geometric coordinates of bifurcation points and crossovers of the vascular network branches. The main goal of our work is to achieve an efficient system while minimizing the processing time and the size of the data handled. Therefore, this algorithm uses a novel combination of powerful techniques for feature extraction based on mathematical morphology, like the watershed transformation for the segmentation of the retinal vasculature and Hit-or-Miss transform for the detection of bifurcation points and crossovers.We detail each step of the method from acquisition and enhancement of retinal images to signature comparison through automatic registration.We test our algorithm on a retinal images database (DRIVE). Finally, we present and discuss the evaluation results of our algorithm, and compare it with some of the literature.
    Keywords: Biometrics; biometric verification; retinal blood vessel; image segmentation; bifurcation points.

  • Detection of Fovea Region in Retinal Images Using Optimization based Modified FCM and ARMD disease classification with SVM   Order a copy of this article
    by T. Vandarkuzhali, C.S. Ravichandran 
    Abstract: The underlying motive resting with the current investigation is invested in designing a superior recognition system for locating the fovea region from the retinal image by significantly steering clear of the roadblocks encountered at present. The significant scheme streams through three specific processes particularly, Blood-vessel segmentation, Optic-disc detection, Fovea detection and ARMD disease classification. In the initial stage, the retinal images are enhanced with the help of AHE approach and then segmented by adaptive-watershed technique. The successive stage opens up with recognition of optic-disc by means of MRG system. And, in the last stage, the fovea region is effectively spotted with the help of OBMFCM technique. Along with the fovea-region segmentation, analysis is made for the classification of dry/wet ARMD with SVM classifier. The record-breaking technique is performed in the platform of Matlab2014 and its charismatic upshots are assessed and contrasted with those of the parallel fovea recognition approach.
    Keywords: Optimization based modified Fuzzy C-Means (OBMFCM); Age Related Macula Degeneration (ARMD); Adaptive Histogram Equalization (AHE); Modified Region Growing (MRG); Support Vector Machine (SVM);.

  • Detection and Diagnosis of Dilated Cardiomyopathy from the Left Ventricular parameters in Echo-cardiogram sequences   Order a copy of this article
    by G.N. Balaji, T.S. Subashini, A. Suresh, M.S. Prashanth 
    Abstract: The heart has a complicated anatomy and is in constant movement. The cardiologist use echocardiogram to visualize the anatomy and its movement. It is difficult for the cardiologist to prognosticate or affirm the diseases like heart muscle damage, valvular problems etc., due to presence of less information in echocardiograms. In this paper a system is proposed which automatically segments the left ventricle from the given echocardiogram video sequences using the combination of fuzzy C-means clustering and morphological operations and from which the left ventricle parameters and shape features are evoked. These features are then employed to linear discriminant analysis, K- nearest neighbor and Hopfield neural network to determine whether the heart is normal or affected with DCM. With LV parameters evaluated and shape features extracted it was found that HNN was able to model normal and abnormal hearts very well with an accuracy of 88% compared to LDA and K-NN.
    Keywords: Echocardiogram; Left Ventricle (LV); Dilated Cardiomyopathy (DCM); Fuzzy C-Means clustering (FCM) and Morphological operations.

  • Detection of Epilepsy using Discrete Cosine Harmonic Wavelet Transform based features and Neural Network Classifier   Order a copy of this article
    by G.R. Kiranmayi, V. Udayashankara 
    Abstract: Epilepsy is a neurological disorder caused by the sudden hyper activity in certain parts of the brain. Electroencephalogram (EEG) is the commonly used cost effective modality for the detection of epilepsy. This paper presents a method to detect epilepsy using Discrete Cosine Harmonic Wavelet Transform (DCHWT) and a neural network classifier. DCHWT is a Harmonic Wavelet Transform (HWT) based on Discrete Cosine Transform (DCT), which is proved to be a spectral estimation technique with reduced bias is used in this work. The proposed method involves decomposition of EEG signals into DCHWT subbands, extraction of features from sub bands and classification using an artificial neural network (ANN) classifier. The main focus of this study is the automatic detection of epilepsy from interictal EEG. This is still a challenge to the researchers as interictal EEG looks like normal EEG which makes the detection difficult. The proposed method is giving classification accuracy of 93.33% to 100% for various classes.
    Keywords: epilepsy; harmonic wavelet transform; HWT; discrete cosine harmonic wavelet transform; DCHWT; ictal EEG; interictal EEG; EEG subbands; neural network classifier.

  • 2D MRI Intermodal Hybrid Brain Image Fusion using Stationary Wavelet Transform   Order a copy of this article
    by Babu Gopal, Sivakumar Rajagopal 
    Abstract: Medical image fusion involves combination of multimodal sensor images to obtain both anatomical and functional data to be used by radiologists for the purpose of disease diagnosis, monitoring and research. This paper provides a comparative analysis of multiple fusion techniques that can be used to obtain accurate information from the intermodal MRI T1 T2 images. The source images are initially decomposed using Stationary Wavelet Transform (SWT) into approximation and detail components while the approximation components are reconstructed by Discrete Curvelet Transform (DCT), the SWT and DCT are good for point and line discontinuities. This paper also provides a comparative study of the different types of image fusion techniques available for MRI image decomposition. These approximation and detail components are fused using the different fusion rules. Final fused image is obtained by inverse SWT transformation. The fused image is used to localize the abnormality of brain images that lead to accurate identification of brain diseases such as 95.7% of brain lesion, 97.3% of Alzheimer's disease and 98% of brain tumor. Various performance parameters are evaluated to compare the fusion techniques and the proposed method which provides better result is analyzed. This comparison is done based on the method which provided the fused image with more Entropy, Average pixel intensity, Standard deviation and Correlation coefficient and Edge strength.
    Keywords: Inter-modal Image Fusion; MRI T1-T2; Stationary Wavelet Transform; Discrete Curvelet Transform; Principal Component Analysis.

  • Design of Wireless Contact-lens antenna for Intraocular Pressure monitoring   Order a copy of this article
    by Priya Lakshmipathy, Vijitha J, Alagappan M 
    Abstract: Intraocular pressure is an important aspect in the evaluation of patients at risk from glaucoma. Glaucoma is an ocular disorder that results in the damage of optic nerve, often associated with increased aqueous pressure in the eye. Wireless technology reduces discomfort, risk of infection and monitor patients in remote places by providing timely health information. In order to transmit the ocular pressure through the wireless media a proposed design of wireless contact-lens antenna has been designed. The contact-lens coupled structure antenna was designed for the betterment of reflection co-efficient and for minimizing the density of materials by gap-coupled configuration in comparison with the conventional on-lens loop antennas. The return loss of the designed contact lens antenna was -21 dB at 2.6 GHz with a diameter ranging from 14 to 15 mm. The simulation result of designed antenna return loss was obtained using Advanced Design System.
    Keywords: Ocular pressure; reflection co-efficient; wireless technology; coupler antenna; glaucoma; conventional on-lens loop antenna; return loss; Advance Design System; aqueous pressure; ocular disorder.

  • Effect of repetitive Transcranial Magnetic Stimulation on motor function and spasticity in spastic cerebral palsy   Order a copy of this article
    by Meena Gupta, Bablu Lal Rajak, Dinesh Bhatia, Arun Mukherjee 
    Abstract: To study the effectiveness of repetitive Transcranial magnetic stimulation (r-TMS) therapy in recovery of motor disability by normalizing muscle tones in spastic cerebral palsy (SCP) patients. Twenty SCP participants were selected from UDAAN-for the disabled, Delhi and were divided equally into two groups - control group (CG) and experimental group (EG). Ten participants in CG (mean age 8.11+SD4.09) were given physical therapy for 30 minutes daily for 20 days and those in EG (mean age 7.93+SD4.85) were administered 5Hz r-TMS frequency for 15 minutes consisting of 1500 pulses daily followed by physical therapy of same duration as provided to CG. Universally accepted - Modified Ashworth Scale and Gross Motor Function was used as outcome measures. The pre and post assessment was completed in both study groups. The GMFM result showed improvement in motor function of EG by 1.95% as compared to 0.55% in CG. Additionally, MAS score of EG showed significant spasticity reduction in muscle of lower extremity as compared to CG. Thus, our study demonstrates that r-TMS therapy followed by PT was responsible for improving the motor performance by decreasing spasticity in SCP patients in limited number of sessions.
    Keywords: motor disability; spasticity; spastic cerebral palsy; physical therapy; Transcranial magnetic stimulation.

  • An optimized pixel-based classification approach for automatic white blood cells segmentation   Order a copy of this article
    by SETTOUTI Nesma, BECHAR Mohammed El Amine, CHIKH Mohammed Amine 
    Abstract: Pixel-based classification is a potential process for image segmentation. In this process, the image is segmented into subsets by assigning a label region for each pixel. It is an important step towards pattern detection and recognition. In this paper, we are interested in the cooperation of the pixel classification and the region growing methods for the automatic recognition of WBC (White Blood Cells). The pixel-based classification is an automatic approach for classifying all pixels in image, and do not take into account the spatial information of the region of interest. On the other hand, region growing methods take the spatial repartition of the pixels into account, where neighborhood relations are considered. However, region-growing methods have a major drawback, indeed they need pixel groups called "point of interest" to initialize the growing process. We propose an optimized pixel based-classification by the cooperation of region growing strategy performed in two phases: the first, is a learning step with a characterization of each pixel of the image. The second, is a region-growing application by neighboring pixel classification from pixels of interest extracted by the ultimate erosion technique. This process has proved that the cooperation allows to obtain a nucleus and cytoplasm segmentation as closer to what is expected by human experts (as expected in the reference images).
    Keywords: Automatic white blood cell segmentation ; Region growing approach ; pixel-based classification ; mathematical morphology ; Random Forest.

  • The analysis of foot loadings in high-level table tennis athletes during short topspin ball between forehand and backhand serve   Order a copy of this article
    by Yaodong Gu, Changxiao Yu, Shirui Shao 
    Abstract: The quality of backswing has a close relationship with forward swing, which could raise more power for next phase and help athletes be in an active status. The purposes of this study are to help coaches to improve understanding of backswing motion and as a guidance to improve athletic performance in practice. Twelve high-level male table tennis athletes have been selected, and their foot loadings during short topspin ball were measured by Emed force plate. Anterior-posterior center of pressure (COP) displacement in backhand serve showed significantly shorter compared with forehand at backward-end stage. Mean and peak pressures were higher under the big toe and lateral forefoot of the front foot in forehand than backhand serves during backswing. Including above two regions and lateral mid-foot of the front foot, contact areas were also higher for forehand serve compared with backhand. Otherwise, for backhand serves, the COP velocity was much faster than forehand during backswing. Compared with backhand serves, our results showed that the forehand serve at backward-end has a more sufficient preparation that can accumulate more power for improving the racket speed for forward swing. For forehand serve, it not only mainly used lateralis of front foot off the ground, but also showed larger contact areas on them compared with backhand at backswing-end. Results indicated that forehand serves of short topspin ball showed stronger and more stable than backhand.
    Keywords: Foot loading; pressure distribution; service stance style; COP velocity ratio.

  • A Locally Adaptive Edge Preserving Filter for Denoising of Low Dose CT using Multi-level Fuzzy Reasoning Concept   Order a copy of this article
    by Priyank Saxena, R. Sukesh Kumar 
    Abstract: To reduce the radiation exposure, low dose CT (LDCT) imaging has been particularly used in modern medical practice. The fundamental difficulty for LDCT lies in its heavy noise pollution in the projection data which leads to the deterioration of the image quality and diagnostic accuracy. In this study, a novel two-stage locally adaptive edge preserving filter based on multi-level fuzzy reasoning (LAEPMLFR) concept is proposed as an image space de-noising method for LDCT images. The first stage of structured pixel region employs multi-level fuzzy reasoning to handle uncertainty present in the local information introduced by noise. The second stage employs a Gaussian filter to smooth both structured and non-structured pixel region in order to retain the low frequency information of the noisy image. Comparing with traditional de-noising methods, the proposed method demonstrated noticeable improvement on noise reduction while maintaining the image contrast and edge details of LDCT images.
    Keywords: Multi-level fuzzy reasoning; Noise reduction; Bilateral filtering; Low dose CT; Edge detection; Image smoothing; Peak Signal to Noise Ratio; Image Quality Index; Gaussian filter.

  • Edge preserving de-noising method for efficient segmentation of cochlear nerve by magnetic resonance imaging   Order a copy of this article
    by Jeevakala Singarayan, A.Brintha Therese 
    Abstract: This article presents a de-noising method to improve the visual quality, edge preservation, and segmentation of cochlear nerve (CN) from Magnetic resonance (MR) images. The de-noising method is based on Non-local means (NLM) filter combining with stationary wavelet transform (SWT). The edge information is extracted from the residue of the NLM filter by processing it through the cycle spinning (CS). The visual interpretation of the proposed approach shows that it not only preserves CN edges but, also reduces the Gibbs phenomenon at their edges. The de-noising abilities of the proposed method strategy are assessed utilizing parameters such as root mean square error (RMSE), signal to noise ratio (SNR), image quality index (IQI) and feature similarity index (FSIM). The efficiencies of the proposed methods are further illustrated by segmenting the cochlear nerve (CN) of the inner ear by the region growing technique. The segmentation efficiencies are evaluated by calculating the cross- sectional area (CSA) of the CN for different de-noising methods. The comparative results show the significant improvement in edge preservation of CN from MR images after de-noising the image with proposed technique.
    Keywords: Non-Local Means (NLM); Stationary Wavelet Transform (SWT); de-noising; Rician noise; cochlear nerve (CN); MR images; SNR.

  • Feature Based Classification and Segmentation of Mitral Regurgitation Echocardiography Images Quantification Using PISA Method   Order a copy of this article
    by Pinjari Abdul Khayum, R. Sudheer Babu 
    Abstract: Echocardiography is the enormously admired scientific specification for the evaluation of valvular regurgitation and gives significant knowledge on the bareness of Mitral Regurgitation (MR). MR is a general heart disease which does not cause indications till its final phase. A technique is advanced for jet area separation and quantification in MR assessment in arithmetical expressions. Previous to this separation method count preprocessing and some attributes are mined from the record to arrangement method. From the cataloging method Support Vector Machine (SVM) classifier developed to confidential echocardiogram images. Entire abnormal images to the Modified Region Growing (MRG) separation method to segment jet area of MR. This segmented jet area in MR quantification process passed out with the support of Proximal Isovelocity Surface Area (PISA). This procedure is based on mass diverse limitations like blood flow rate, regurgitant fraction, and EROA etc. From the outcomes this projected effort associated with the current method fuzzy with PISA quantification process, the projected work attained accuracy rate 99.05% in the study of jet area segmenting and quantification method.
    Keywords: Echocardiogram; Mitral valve; Mitral Regurgitation; classification; segmentation and quantification.

  • Multi-Objective Particle Swarm Optimization for mental task classification using Hybrid features and Hierarchical Neural Network Classifier   Order a copy of this article
    by MADHURI BAWANE 
    Abstract: Recognition of mental tasks using Electroencephalograph (EEG) signals is of prime importance in man machine interface and assistive technologies. Considerably low recognition rate of mental tasks is still an issue. This work combines Power Spectral Density (PSD) features and Lazy Wavelet Transform (LWT) coefficients to present a new approach to feature extraction from EEG signals. A simple but novel neural network classifier called hierarchical neural network is proposed for the task recognition. A novel methodology based on Multi Objective Particle Swarm Optimization (MOPSO) to select discriminative features and the number of hidden layer nodes is proposed. The extracted features are presented to the hierarchical classifier to discriminate left-hand movement, right-hand movement and word generation task. Features in the time frequency domain are extracted using LWT, while those in time domain are extracted using PSD. The hybrid features present complementary information about the task represented by EEG. The features are applied to MOPSO to select the prominent features and decide number of hidden nodes of the neural network classifier. These features train the Hierarchical neural network with hidden layer neurons decided by the MOPSO. Effective selection of the features and the number of hidden layer nodes of the hierarchical classifier improve the classification accuracy. The results are verified on standard brain computer interface (BCI) database and our own B-alert experimental system database. The benchmarking indicates that the proposed work outperforms the state of the art.
    Keywords: Mental task classification; MOPSO; LWT; Hybrid features; Hierarchical Classifier.

  • Energy efficient and low noise OTA with improved NEF for Neural Recording Applications   Order a copy of this article
    by Bellamkonda Saidulu, Arun Manohran 
    Abstract: Analog Front End (AFE) design plays a prominent role to specify the overall performance of neural recording systems. In this paper, we present a power efficient low noise Operational Transconductance Amplifier (OTA)which is power consumable block for multichannel neural recording system with shared structure. Inversion Coefficient(IC)methodology is used to size the transistors. This work focuses on the neural recording applications which show >40dB and up to 7.2 kHz bandwidth. The proposed architecture, which is referred as partial sharing operational transconductance amplifier with source degeneration, results in reduced noise, hence improving NEF. Simulation results are carried in UMC 0.18m and show an improved gain of 66 dB, the phase margin of 94, input-referred voltage noise 0.6V/sqrt(Hz) and power consumption of 2.15Wwith supply of 1.8V.
    Keywords: Neural Amplifier; Telescopic Cascode; Partial OTA Sharing Structure; Self-cascode Composite Current Mirror; Source Degeneration; NEF.

  • Comparison of Missing tooth and Dental work detection using Dental radiographs in Human Identification   Order a copy of this article
    by Jaffino George Peter, Banumathi A, Ulaganathan Gurunathan, Prabin Jose J 
    Abstract: Victim identification plays a vital role for identifying a person in major disasters at the time of critical situation when all the other biometric information was lost. At that time there is a less chance for identifying a person. The major issues of dental radiographs are dental work and missing or broken tooth was addressed in this paper. This algorithm can be established by comparing both ante mortem (AM) and postmortem (PM) dental images. This research work is mainly focuses on the detection of dental work and broken tooth or missing tooth, then comparison of active contour model with mathematical model based shape extraction for dental radiographic images are proposed. In this work, a new mathematical tooth approximation is presented and it is compared with Online Region based Active Contour Model (ORACM) is used for shape extraction. Similarity and distance based technique gives better matching about both the AM and PM dental radiographs. Exact prediction of each method has been calculated and it is validated with suitable performance measures. The accuracy achieved for contour method is 94%, graph partition method is 96% and finally the hit rate of this method is plotted with Cumulative Matching Characteristic (CMC) curve.
    Keywords: Victim identification; dental work; missing tooth; Active Contour Model; Isoperimetric graph partitioning; CMC curve.rnrn.

  • Design and prototyping of a novel low stiffness cementless hip stem   Order a copy of this article
    by Ibrahim Eldesouky, Hassan Elhofy 
    Abstract: Present biocompatible materials that are suitable for load bearing implants have high stiffness compared to the natural human bone. This mechanical mismatch causes a condition known as stress shielding. The current trend for overcoming this problem is to use porous scaffold instead of solid implants to reduce the implant stiffness. Due to the wide spread of metal additive manufacturing machines, porous orthopaedic implants can be mass produced. In this regard, a porous scaffold is incorporated in the design of a low stiffness hip stem. A 3D finite element analysis is performed to evaluate the performance of the new stem with the patient descending the stairs. The results of the numerical study show that the proposed design improves stress and strain distributions in the proximal region which reduce the stress shielding effect. Finally, a prototype of the proposed design is produced using a 3D printer as proof of concept.
    Keywords: 3D printing; additive manufacturing; auxetic scaffold; low stiffness; stress shielding.

  • Image Analysis for Brain Tumour Detection using GA-SVM with Auto-Report Generation Technique   Order a copy of this article
    by Nilesh Bhaskarrao Bahadure, Arun Kumar Ray, Har Pal Thethi 
    Abstract: In this study, we have presented image analysis for the brain tumour segmentation and detection based on Berkeley wavelet transformation, enabled by genetic algorithm and support vector machine. The proposed system uses double classification analysis to conclude tumour type. The decision on the tumour type i.e. benign or malignant is facilitated by the classifier on the basis of the features extraction and on the basis of area of the tumour. The improvement in the accuracy of the classifier has been investigated through double decision-making system. The proposed system also investigated autoreport generation technique using user-friendly graphical user interface in matlab. It is the first kind of its study, to aid with the feature of auto-report generation technique invented for quick and improved diagnosis analysis by the radiologists or clinical supervisors. The experimental results of proposed technique is been evaluated and validated for performance and quality analysis on magnetic resonance (MR) medical images based on accuracy, sensitivity, specificity and dice similarity index coefficient. The experimental results achieved 97.77% accuracy, 98.98% sensitivity, 94.44% specificity and an average of 0.9849 dice similarity index coefficient, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from MR images. The experimental result is validated by extracting 89 features and selecting the relevant features appropriately using Genetic algorithm optimize by support vector machine. The simulation results prove the significance in terms of quality analysis on segmentation score and classification accuracy in comparison to the state of the art techniques.
    Keywords: Berkeley Wavelet Transformation; Feature Extraction; GeneticrnAlgorithm; Magnetic Resonance Imaging (MRI); Support Vector Machine.

  • Evaluation of endothelial response to reactive hyperemia in peripheral arteries using a physiological model   Order a copy of this article
    by Mohammad Habib Parsafar, Edmond Zahedi, Bijan Vosoughi Vahdat 
    Abstract: A common approach for the non-invasive evaluation of endothelial function - a good predictor of cardiovascular events - is the measurement of brachial artery diameter changes in flow-mediated dilation (FMD) during reactive hyperemia using ultrasound imaging. However, this method is both costly and operator-dependent, limiting its application to research cases. In this study, an attempt is made toward model-based evaluation of endothelial response to reactive hyperemia. To this end, a physiological model between normalized central blood pressure and finger photoplethysmogram (FPPG) is proposed. The genetic algorithm is utilized for estimating the models parameters in thirty subjects grouped as: normal BP (N=10), high BP (N=10) and elderly (N=10). The change in beat-to-beat fitness between model output and measured FPPG (BB_fit index) during the cuff-release interval is fairly described with a first order dynamic. Results show that the time constant of this first order system is significantly greater for normal BP compared to high BP (p-value=0.004) and elderly subjects (p-value=0.01). Indeed, endothelial response to reactive hyperemia is more pronounced in normal BP and young subjects compared to high BP and elderly, delaying the return of the vasculature to the baseline state. Our findings hint that the proposed model can be utilized in physiological model-based studies of cardiovascular health, resulting eventually in a reliable index for vascular characterization using conventional FMD test.
    Keywords: flow-mediated dilation; photoplethysmography; endothelial function; cardiovascular modeling; viscoelasticity; tube-load model.

  • Automated ECG beat classification using DWT and Hilbert transform based PCA-SVM classifier   Order a copy of this article
    by Santanu Sahoo, Monalisa Mohanty, Sukanta Sabut 
    Abstract: The analysis of electrocardiogram (ECG) signals provides valuable information for automatic recognition of arrhythmia conditions. The objective of this work is to classify five types of arrhythmia beat using wavelet and Hilbert transform based feature extraction techniques. In pre-processing, wavelet transform is used to remove noise interference in recorded signal and the Hilbert transform method is applied to identify the precise R-peaks. A combination of wavelet, temporal and morphological or heartbeat interval features has been extracted from the processed signal for classification. The principal component analysis (PCA) is used to select the informative features from the extracted features and fed as input to the support vector machine (SVM) classifier to classify arrhythmia beats automatically. We obtained better performance results in the PCA-SVM based classifier with an average accuracy, sensitivity and specificity of 98.50%, 95.68% and 99.18% respectively in cubic-SVM classifier for classifying five types of ECG beats at fold eight in ten-fold cross validation technique. The effectiveness of our method is found to be better compared to published results, therefore the proposed method may be used efficiently in the ECG analysis.
    Keywords: Electrocardiogram; Wavelet; Hilbert transform; support vector machine; principal component analysis; arrhythmia.

  • Impact-induced traumatic brain injury: Effect of human head model on tissue responses of the brain   Order a copy of this article
    by Hesam Moghaddam, Asghar Rezaei, Ghodrat Karami, Mariusz Ziejewski 
    Abstract: The objective of this research is twofold; first to understand the role of the finite element (FE) head model in predicting tissue responses of the brain, and second to investigate the fidelity of pressure response in validating FE head models. Two validated FE head models are impacted in two directions under two impact severities and their tissue responses are compared. ICP peak values are less sensitive to the head model and brain material. Maximum ICPs occur on the outer surface, vanishing linearly toward the center of the brain. It is concluded that while different head models may simply reproduce the results of ICP variations due to impact, shear stress is affected by the head model, impact condition, and brain material.
    Keywords: Intracranial pressure (ICP); shear stress; injury mechanism; finite element head model; brain injury; reproducibility.

  • Selection of Surface Electrodes for Electrogastrography and Analysis of Normal and Abnormal Electrogastrograms using Hjorth Information   Order a copy of this article
    by Paramasivam Alagumariappan, Kamalanand Krishnamurthy, Ponnuswamy Mannar Jawahar 
    Abstract: Electrogastrogram (EGG) signals recorded non-invasively using surface electrodes, represent the electrical activity of the stomach muscles and are used to diagnose several digestive abnormalities. The surface electrodes play a significant role in the acquisition of EGG signals from human digestive system. In this work, an attempt has been made to demonstrate the role of contact area of surface electrodes for efficient measurement of EGG signals. Two different surface electrodes with contact diameter of 16 mm and 19 mm have been adopted for acquisition of EGG signals. Further, the Hjorth parameters of the EGG signals acquired from normal and abnormal cases suffering from diarrhea, vomiting and stomach ulcer were analyzed. Results demonstrate that the activity, mobility and complexity of the EGG signals increases with increase in contact area of the surface electrodes. Further, it is observed that there is a significant variation in Hjorth parameters for normal and abnormal cases.
    Keywords: Surface electrodes; contact area; electrogastrogram; activity; mobility; complexity; Hjorth parameters; Information measures.

  • Plasma cell identification based on evidential segmentation and supervised learning   Order a copy of this article
    by Ismahan Baghli, Mourtada Benazzouz, Mohamed Amine Chikh 
    Abstract: Myeloma disease is among the most common type of cancer, it is characterized by proliferation of plasma cells, kind of white blood cell (textsc{wbc}). Early diagnosis of the disease can improve the patient's survival rate. The manual diagnosis involves clinicians to visually examine microscopic bone marrow images for any signs of cells proliferation. This step is often laborious and can be highly subjective due to clinician's expertise. Automatic system based on textsc{wbc} identification and counting provides more accurate result than manual method. This system is mainly based on three major steps: cell's segmentation, cell's characterization and cell's classification. In the proposed system, microscopic images of bone marrow blood are segmented by the combination of watershed transform and the evidence theory, the segmented cells are characterized with shape and Colour texture features, and then classified into plasma cells or not plasma cells with three supervised classifiers; Support Vector Machines, K Nearest Neighbour and Decision Tree. Experimental results show that the recognition of plasma cells with the K nearest neighbour achieved 97% of correct rate with 100% of specificity.
    Keywords: Myeloma; Plasma cell; Bone marrow images; Segmentation; Evidence theory; Watershed; Characterization; Shape; Colour texture; Classification.

  • Engineering Approaches for ECG Artifact Removal from EEG: A Review   Order a copy of this article
    by Chinmayee Dora, Pradyut Kumar Biswal 
    Abstract: Electroencephalograms (EEG) signal, obtained by recording the brain waves are used to analyze health problems related to neurology and clinicalrnneurophysiology. This signal is often contaminated by a range of physiological and non-physiological artifacts, which leads to a misinterpretation in EEG signal analysis. Hence, artifact removal is one of the preprocessing step required for clinical usefulness of the EEG signal. One of the physiological artifact i.e. Electrocardiogram (ECG) contaminated EEG can affect the clinical analysis and diagnosis of brain health in various ways. This paper presents a review of engineering approaches adopted till date for ECG artifact identification and removal from contaminated EEG signal. In addition, the technical approach, computational extensiveness, input requirement and the results achieved with every method is discussed. Along with that, the feasibility study for real time implementation of the algorithms is discussed. Also, an analysis of these methods has been reported based on their performance.
    Keywords: EEG; ECG; Artifacts; ICA; Wavelet; EMD; EAS; ANC; Autoregression; ANFIS; TVD; SVM.

  • Assessment of the risk factors of Type II Diabetes using improved combination of Particle Swarm Optimization and Decision Trees by evaluation with Fishers Linear Discriminant Analysis   Order a copy of this article
    by Sheik Abdullah A, Selvakumar S 
    Abstract: The key objective of this research work is to evaluate and to develop a predictive model which aims towards the exploration of risk factors related to type II diabetic event. The model developed with the consideration of type II diabetic risk, parameter values with its signified levels. The experimental study involves 732 records collected from a government regional hospital, Tamil Nadu, India. Experimental investigation has been carried out using the improved combination of Particle Swarm Optimization with Decision Trees and its various splitting measures. From the result analysis, it has been observed that the risk factor corresponding to postprandial plasma glucose (PPG), glycosylated hemoglobin (A1c), Mean Blood Glucose (MBG), Fasting Plasma Glucose (FPG) with an improved accuracy of about 98.60% respectively. The efficiency of the model has been tested using Fishers Linear Discriminant Analysis. The within class co-variance has also been calculated the test interpretation results proves that the signified which is significantly greater that the probabilistic-ally observed value with . Hence there occurs a strong relationship between PPG, A1c, MBG and FPG with the risk corresponding to Type II diabetes. There by, predictive analytics can be deployed over the risk corresponding to chronic diseases such as Type II diabetes, Coronary Heart Disease, and Kidney disease.
    Keywords: Data Classification; Data mining; Data Analytics; Decision Trees; Discriminant Analysis; Optimization; Prediction; Swarm Intelligence; Type II Diabetes.

  • Regenerative Pixel Mode and Tumor Locus Algorithm Development for Brain Tumor Analysis - A New Computational Technique for Precise Medical Imaging   Order a copy of this article
    by Sunil Bangare, G. Pradeepini, Shrishailappa Patil 
    Abstract: This Paper provide Regenerative Pixel Mode (RPM) and Tumor Locus algorithm (TLA), an alternative technique for effective anti-aliased extraction of complicated tumor locus. We developed this technology to eliminate disadvantages of positron emission tomography (PET) scan technology where radioactive material proved as a risk for the patient. The presented technology can be an alternative to PET scan processes and is very cost effective technique as compared to PET scan. RPM Algorithm makes use of the pixel sampling, sub-pixel filter mode to build a compressed, tumor manifestation in each and every pixel through the elimination of impurities. Along with RPM Algorithm, TLA is further used for identification of tumor locus by a sub-clustering method where the high-intensity region of the brain tumor is extracted. Finally, RPM and TLA processing provide final results which are undoubtedly visible for health practitioner reviews for pre and post or even during surgical activities.
    Keywords: Regenerative Pixel Mode (RPM); Tumor Locus algorithm (TLA); Magnetic Resonance Imaging (MRI); positron emission tomography (PET); Brain Tumor; Clustering; Groebner bases.

  • New Scheme for Breast Cancer Detection and Staging Using Ant Colony Algorithm   Order a copy of this article
    by Priyadarshini Velusamy, Porkumaran Karantharaj, S. Prabakar 
    Abstract: The Ant colony optimization (ACO) is an optimization technique which first proposed Ant-based metaheuristic developed by Marco Dorigo. The stimulating source of ant colony optimization is a searching behavior of real ant colonies. The proposed hybrid method consists of an enhanced ACO algorithm, Discrete Wavelet Transform (DWT), Principle component analysis (PCA) and TNM (The size of the breast tumour (T), nearby lymph nodes (N), Metastasized (M)) system for detecting the edges of the tumour, Feature Extraction, Feature Reduction and tumour staging. For the early detection of breast cancer and staging the proposed analysis has been done with two different image modalities which is mammogram images and PET images.
    Keywords: Ant colony optimization; Discrete Wavelet Transform; Principle component analysis; TNM staging; mammogram images and PET images.

  • Enhanced Cache Sharing through Cooperative Data Cache Approach in MANET   Order a copy of this article
    by Lilly Sheeba S., Yogesh P 
    Abstract: In a Mobile Adhoc NETwork (MANET) under normal cache sharing scenarios, when the data is transmitted from source to destination, all the nodes along the path store the information on the cache layer before reaching the destination. This may result in increased node overhead, increased cache memory utility and very high end-to-end delay. In this paper, we propose an Enhanced Cache Sharing through Cooperative Data Cache (ECSCDC) approach for MANETs. During the transmission of desired data from the Data Centre back to the request originator, the data packets will be cached by the intermediate caching nodes only if required, by using the asymmetric cooperative cache approach. Those caching nodes that can retain the data in its cache, for future data retrieval is selected based on scaled power community index. By simulation results, we show that the proposed technique reduces the communication overhead, access latency and average traffic ratio near the data centre while increasing the cache hit ratio.
    Keywords: Mobile ad hoc network; caching; cache sharing; cache replacement.

  • Quality Function Deployment Model Using Fuzzy Programming with Optimization Technique for Customer Satisfaction   Order a copy of this article
    by Mago Stalany V., Sudhahar C. 
    Abstract: Quality Function Deployment (QFD) is a customer-driven superiority organization and product expansion scheme for attaining advanced consumer approval. This document is to inspect the execution of QFD at fuzzy surroundings and to expand equivalent events to contract by the fuzzy data. At this time, regard as the consumer approval limitations are ease, refund and safeness in FQFD (Fuzzy QFD) study using Fuzzy Logic Controller (FLC) by optimization method. This optimization method to develop the accurateness values of FLC in QFD procedure, now PSO is utilized for optimization method. For hard data production, dissimilar relationship utility is employed to the comparative inclination association on fuzzy statistics, it is not essential to develop two fuzzy statistics to obtain standard masses in FQFD. Since, the outcome of fuzzy to recognizing the precedence stage of the consumer approval and utmost accurateness stage of the FQFD procedure.
    Keywords: Fuzzy quality function deployment; Quality Function Deployment; Customer requirements; design quality; Relative preference relation.

  • Concordance between serum and transcutaneous bilirubin levels with the Bilispect   Order a copy of this article
    by Adriana Montealegre, Nathalie Charpak, Zandra Grosso, Yaris Vargas, Julieta Villegas 
    Abstract: Screening and follow-up of neonatal hyperbilirubinemia has been done with the use of bilirubin serum levels. This method is invasive and exposes patients to anaemia. A transcutaneous measurement, the Bilispect
    Keywords: Bilirubin; jaundice; neonatal; correlation study.

  • Influence of hip geometry to intracapsular fractures in Sri Lankan women: prediction of country specific values   Order a copy of this article
    by Shanika Arachchi, Narendra Pinto 
    Abstract: Falls are very common in daily life. Hip is a highly vulnerable location during a fall. Trochanter can be compressed due to side falls resulting either intracapsular or extracapsular fracture. The relationship of bone geometry to the fracture risk can be analyzed as a determinant of mechanical resistance of the bone, as well as a promising fracture prediction tool. Intracapsular fractures are highly depend on the hip geometry compared to the extracapsular fractures. This study aims to find out the influence of hip geometry to the intracapsular fractures among Sri Lankan women. HAL, NSA, FNW and moment arm length of intracapsular patients have compared with a normal group. Concurrently, the moment applied to the proximal femur during the sideway fall is computed and compared with a normal group. We observed that fractured group has greater NSA, HAL and FNW compared to the normal group. Furthermore, intracapsular fracture females have longer moment arm of the force in the sideway fall resulting a greater load on femoral neck compared to the normal group.
    Keywords: falls; hip fractures; hip geometry; Neck Shaft Angle; Femoral Neck Width.

  • FLUID STRUCTURE INTERACTION STUDY ON STRAIGHT AND UNDULATED HOLLOW FIBER HEMODIALYSER MEMBRANES   Order a copy of this article
    by Sangeetha M S, Kandaswamy A 
    Abstract: In hemodialysis therapy, the dialyser is subjected to blood flow continuously for several hours and is also being reused; the stress experienced by the fibers owing to blood flow is of utmost importance because it reflects on the mechanical stability of the membrane. It is tedious to study the stress experienced by an individual fiber in real-time; computer aided techniques enables to gain better insights about the load bearing capacity of the membrane. A finite-element strategy is implemented to study the effect of flow induced stress in hemodialyser membrane. A 3D model of the membrane was developed in straight and undulated (crimped) fiber orientations. Fluid structure interaction study was conducted to analyse the stress distribution due to varying blood flow. It is observed that in both the fiber orientations, the stress varies inversely with the blood flow rate. The effect of varying the length of the fiber, wall thickness and crimp frequency is also studied. From the analysis it is found that the crimped fibers experiences less stress compared to straight fiber. Such analysis aids to predict and evaluate the performance of the hemodialyser membrane. Keywords: finite-element strategy; hemodialyser membrane; crimping; fluid structure interaction; computer aided techniques
    Keywords: finite-element strategy; hemodialyser membrane; crimping; fluid structure interaction; computer aided techniques.

  • A NOVEL CLASSIFICATION APPROACH TO DETECT THE PRESENCE OF FETAL CARDIAC ANOMALY FROM FETAL ELECTROCARDIOGRAM   Order a copy of this article
    by Anisha M, Kumar S.S, Benisha M 
    Abstract: Fetal cardiac anomaly interpretation from Fetal Electrocardiogram (FECG) is a challenging effort. Fetal cardiac activity can be assessed by scrutinizing FECG because clinically crucial features are hidden in the amplitudes and waveform time duration of FECG, and Fetal Heart Rate (FHR). These features are vital in fetal cardiac anomaly interpretation. Hence here an attempt is made to detect the presence of fetal cardiac anomaly using Support Vector Machine (SVM) classifier with polynomial kernel based on the patterns extricated from FHR, frequency domain of FECG signals, fetal cardiac time intervals and FECG morphology. Performance evaluation is done on real FECG signals with different combination of features set and the obtained results are compared. SVM showed good performance with 92% of classification accuracy when all the features are fed to the classifiers. Results evince that the proposed approach has immense prospective and guarantee in early fetal cardiac anomaly detection from FECG.
    Keywords: Fetal Electrocardiogram; Fetal Heart Rate; SVM; fetal cardiac anomaly; fetal cardiac activity.

  • A Multimodal Biometric Approach for the Recognition of Finger Print, Palm Print and Hand Vein using Fuzzy Vault   Order a copy of this article
    by R. Vinothkanna, Amitabh Wahi 
    Abstract: For the security reasons, Person Identification has got primary place by means of some of the physiological features. For this a biometric person recognition system is used, which decides who the user is. In this paper, multimodal biometry is utilized for the person identification with the help of 3 physiological features such as finger print, palm print and hand vein. Initially, in the pre-processing stage, the unwanted portions, noise content and the blur effects are removed from the input finger print, palm print and hand vein images. Then the features from these three modalities are extracted. Finger print features are extracted directly from the pre-processed image , palm print and hand vein features are extracted using maximum curvature points in the image cross-sectional profile. Then using chaff points and all the extracted feature points, a combined feature vector point is obtained. After getting the combined feature vector points, the sectret key points are added with the combined feature vector points to generate the fuzzy vault. Finally, in the Recognition stage, test persons combined vector is compared with the fuzzy vault data base. If the combined vector is matched with the fuzzy vault, then the authentication is granted and then the secret key is generated to confirm with the person. Otherwise, the authentication is denied. Now we can obtain the corresponding finger print, hand vein and palm print images.
    Keywords: Multimodal biometric; Maximum curvature points; Cross-sectional profile; Chaff points; Fuzzy Vault.

  • Estimation of a point along overlapping Cervical Cell Nuclei in Pap smear image using Color Space Conversion   Order a copy of this article
    by Deepa T.P., A. Nagaraja Rao 
    Abstract: The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system. It is even more difficult when cells are overlapped, as abnormal cells are hidden below normal cells and affects their visibility. Hence, there is need for algorithm which segments cells in the cluster formed by overlapped cells which can be achieved using image processing techniques. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. The segmentation of nuclei helps to find cell count which is one of the important features in Pap smear analysis. There is a need for method which can simultaneously segment disjoint and overlapped nuclei. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps and plays important role in segmenting overlapped cells. This paper discusses such method which segment disjoint nuclei and identifies the point of intersection called as Concavity point in the cluster of cells where only nuclei are overlapped.
    Keywords: Papanicolaou Smear; Overlapping; Morphological and Microscopic Findings; cell nuclei.

  • Multiobjective Pareto optimization of a pharmaceutical product formulation using radial basis function network and nondominated sorting differential evolution   Order a copy of this article
    by Satyaeswari Jujjavarapu 
    Abstract: Purpose In a pharmaceutical formulation involving several composition factors and responses, its optimal formulation requires the best configuration of formulation variables that satisfy the multiple and conflicting response characteristics. This work aims at developing a novel multiobjective optimization strategy by integrating an evolutionary optimization algorithm with an artificial intelligence model and evaluates it for optimal formulation of a pharmaceutical product. Methods A multiobjective Pareto optimization strategy is developed by combining a radial basis function network (RBFN) with a non-dominated sorting differential evolution (NSDE) and applied for optimal formulation of a trapidil product involving conflicting response characteristics. Results RBFN models are developed using spherical central composite design data of trapidil formulation variables representing the amounts of microcrystalline cellulose, hydroxypropyl methylcellulose and compression pressure, and the corresponding response characteristic data of release order and rate constant. The RBFN models are combined with NSDE and Pareto optimal solutions are generated by augmenting it with Na
    Keywords: Pharmaceutical formulation; Multiple regression model; Response surface method; Radial basis function network; Differential evolution; Multiobjective optimization.

  • Implementation of Circular Hough transform on MRI Images for Eye Globe Volume Estimation   Order a copy of this article
    by Tengku Ahmad Iskandar Tengku Alang, Tian Swee Tan, Azhany Yaakub 
    Abstract: Eye globe volume estimation have gained attention in both medical and biomedical engineering field. However, most of the methods used manual analysis which is tedious and prone to errors due to various inter- or intraoperator variability studies. In the present study, we estimated the volume of eye globe, in MRI images of normal eye globe condition using the Circular Hough transform (CHT) algorithm. To test the performance of the proposed method, 24 Magnetic Resonance images which constitute 14 males and 10 females (normal eye globe condition) with T1-weighted MRI images are randomly selected from the database. The mean (
    Keywords: Circular Hough transform (CHT); Magnetic Resonance Imaging (MRI); MRI images; eye globe detection; T1-weighted.

  • Electroencephalogram (EEG) Signal Quality Enhancement by Total Variation Denoising Using Non-Convex Regularizer   Order a copy of this article
    by PADMESH TRIPATHI 
    Abstract: Medical practitioners have great interest in getting the denoised signal before analysing it. EEG is widely used in detecting several neurological diseases such as epilepsy, narcolepsy, dementia, sleep apnea syndrome, alzheimers, insomnia, parasomnia, Creutzfeldt-Jakob diseases (CJD) and schizophrenia etc. In the process of EEG recordings, a lot of background noise and other kind of physiological artefacts are present, hence, data is contaminated. Therefore, to analyse EEG properly, it is necessary to denoise it first. Total variation denoising is expressed as an optimization problem. Solution of this problem is obtained by using a non-convex penalty (regularizer) in the total variation denoising. In this article, non-convex penalty is used for denoising the EEG signal. The result has been compared with wavelet methods. Signal to noise ratio (SNR) and root mean square error have been computed to measure the performance of the method. It has been observed that the approach used here works well in denoising the EEG signal and hence enhancing its quality.
    Keywords: Electroencephalogram; wavelet; artefact; denoising; regularizer; convex optimization; epilepsy; tumors; empirical mode decomposition; principal component anslysis; total variation.

  • IDENTIFYING THE ANOMALY IN LV WALL MOTION USING EIGEN SPACE   Order a copy of this article
    by Wiselin Jiji 
    Abstract: In this paper, we have experimented Left Ventricular (LV) Wall motion abnormalities using Eigen LV Space. We employ three phases of operations in order to perform efficient identification of LV motion abnormalities. In the First phase, LV border detection technique was used to detect LV area. In the second phase, Eigen LV spaces of six abnormalities are to be converged as the search space. In the third phase, query is projected on this search space which leads matching of closest Disease. The results proved using Receiver Operating Characteristic (ROC) curve show that the proposed architecture provides high contribute to Computer-Aided Diagnosis. Experiments were made on a set of 20 Abnormal and 20 Normal cases. We trained with 8 Normal & 8 Abnormal cases and yielded an accuracy of 88.8% for the proposed works and 75.81% and 79% respectively for earlier works. Our empirical evaluation has a superior diagnosis performance when compared to the performance of other recent works.
    Keywords: Eigen Space; LV BORDER DETECTION,Indexing.

  • Recent advances on Ankle Foot Orthosis for Gait Rehabilitation: A Review   Order a copy of this article
    by Jitumani Sarma, Nitin Sahai, Dinesh Bhatia 
    Abstract: Since the early 1980s, hydraulic and pneumatic device are used to explore methods of orthotic devices for lower limb. Over the past decades, significant development has been made by researchers in rehabilitation robotics associating assistive orthotic device for the lower limb extremities. The aim in writing this review article is to present a detailed insight towards the development of the controlled Ankle Foot Orthotic (AFO) device for enhancing the functionality of people disabled by injury to the lower limb or by neuromuscular disorders such as multiple sclerosis, spinal muscular atrophy etc. Different types of approaches towards design, actuation and control strategies of passive and active AFOs are analyzed in this article considering gait rehabilitation. In currently available commercialized ankle foot orthotic devices for lower limb, to overcome the weakness and instability produced by drop foot and to follow natural gait is still a challenge. This paper also focuses the impact of active control of AFO device mainly to enhance the functionality of lower limb reducing the deformities. Researchers have put in huge amount of efforts in terms of modeling, simulating and controlling of such devices mainly for gait rehabilitation with kinematic and dynamics analysis.
    Keywords: Foot drop; Ankle Foot Orthosis; Gait; dorsiflexion; plantarflexion.

  • Computer Aided Designing and Finite Element Analysis for development of porous 3-D tissue scaffold-A review   Order a copy of this article
    by Nitin Sahai, Manashjit Gogoi 
    Abstract: Biodegradable porous tissue scaffolds plays a crucial role in development of tissue/organ and development of these biomimetic porous tissue scaffold with accurate porosity could be achieved with the help of latest analysis techniques known as Computer Aided Tissue Engineering (CATE) which consists of Computer Tomography(CT) scan, Magnetic Resonance Imagining (MRI), Functional Magnetic Resonance Imagining FMRI, Computer Aided Designing (CAD), Finite Element Method (FEM) and other modern design and manufacturing technologies for development of 3-D architecture of porous tissue scaffolds can be fabricated with reproducible accuracy in pore size. The aim of this paper is to review and elaborate the various recent methods developed in Computer Aided Designing, Finite Element Analysis and Solid Freeform Fabrication (SFF) for development of porous 3 Dimensional tissue scaffolds.
    Keywords: Biomaterials; Scaffolds; Tissue Engineering; Computer Aided Tissue Engineering; Finite Element Method.

  • Investigation on staging of breast cancer using miR-21 as a biomarker in the serum   Order a copy of this article
    by Bindu SALIM, Athira M V, Kandaswamy Arumugam, Madhulika Vijayakumar 
    Abstract: Circulating microRNAs (miRNA) are a novel class of stable, minimally invasive disease biomarkers that are valuable in diagnostics and therapeutics. MiR-21 is an oncogenic miRNA that regulates the expression of multiple cancer-related target genes and it is highly expressed in the patients serum suffering from breast cancer. The focus of the present study was on measuring the expression profile of the most significantly up-regulated miR-21 in breast cancer patients serum to evaluate their correlation with the clinical stage of cancer by using molecular beacon probe. miR-21 expression was also quantitatively analyzed by TaqMan real-time PCR techniques. Ten serum samples from the confirmed breast cancer patients and one healthy control sample were used for the evaluation of miR-21 gene expression. The expression levels of miR-21 were significantly high in breast cancer serum samples compared to healthy control samples with significant differences corresponding to clinical stages of II, III, and IV. The findings indicate that serum miR-21 would serve as a potential marker for therapeutic regimes as well as monitoring the patient status by simple blood test.
    Keywords: Breast Cancer; Biomarker; miR-21; Clinical stage; Real-time PCR.

  • Pose and Occlusion Invariant Face Recognition System for Video Surveillance Using Extensive Feature Set   Order a copy of this article
    by A. Vivek Yoganand, A. Celine Kavida 
    Abstract: Face recognition presents a challenging problem in the field of image analysis and computer vision. Different video sequences of the same subject may contain variations in resolution, illumination, pose, and facial expressions. These variations contribute to the challenges in designing an effective video-based face-recognition algorithm. In this proposed method, we are presenting a face recognition method from video sequence with various pose and occlusion. Initially, shot segmentation process is done to separate the video sequence into frames. Then, Face part is detected from each frame for further processing. Face detection is the first stage of a face recognition system. After detecting the face exactly the facial features are extracted. Here SURF features, appearance features, and holo-entropy is used to find out the uniqueness of the face image. The Active appearance model (AAM) can be used to find out the appearance based features in the face image. These features are used to select the optimal key frame in the video sequence which is based on the supervised learning method, Modified Artificial Neural Network (MANN) using Bat algorithm. Here bat algorithm is used for optimizing the weights of Neurons. Finally, based on the feature library, the face image can be recognized.
    Keywords: face recognition; Active appearance model; Modified Artificial Neural Network; bat algorithm.

  • Automatic segmentation of Nasopharyngeal carcinoma from CT images   Order a copy of this article
    by Bilel Daoud, Ali Khalfallah, Leila Farhat, Wafa Mnejja, Ken’ichi Morooka, Med Salim Bouhlel, Jamel Daoud 
    Abstract: The nasopharyngeal carcinoma (NPC) called also Cavum cancer becomes a public health problem for the Maghreb countries and Southeast Asia. The detection of this cancer could be carried out from computed tomography (CT) scans. In this context, we proposed two approaches based on image clustering to locate affected tissues by the Cavum cancer. These approaches are based respectively on E-M and Otsu segmentation. Compared to the physician manual contouring, our automatic detection proves that the detection of the cancer while using the Otsu clustering in terms of precision, recall and F-measure is more efficient than E-M. Then, we merged the results of these two methods by using the AND and the OR logical operators. The AND fusion yields to an increase of the precision while the OR fusion raises the recall. However, the detection of the NPC using Otsu remain the best solution in terms of F-Measure. Compared to previous studies that provide a surface analysis of the NPC, our approach provides a 3D estimation of this tumor ensuring a better analysis of the patient folder.
    Keywords: Cavum Cancer; DICOM images; image segmentation; E-M; Otsu; recall; precision; F-measure.

  • Descendant Adaptive Filter to Remove Different Noises from ECG Signals   Order a copy of this article
    by Mangesh Ramaji Kose, Mitul Kumar Ahirwal, Rekh Ram Janghel 
    Abstract: Electrocardiogram (ECG) signals are electrical signals generated corresponding to activity of heart. ECG signals are recorded and analyzed to monitor heart condition. In initial raw form, ECG signals are contaminated with different types of noises. These noises may be electrode motion artifact noise, baseline wander noise and muscle noise also known as electromyogram (EMG) noise etc. In this paper a descendent structure consists of adaptive filters is used to eliminate the three different types of noises (i.e. motion artifact noise, baseline wander noise and muscle noise). Two different adaptive filtering algorithms have been implemented; least mean square (LMS) and recursive least square (RLS) algorithm. Performance of these filters are compared on the basis of different fidelity parameters such as mean square error (MSE), normalized root mean squared error (NRMSE), signal-to-noise ratio (SNR), percentage root mean squared difference (PRD), and maximum error (ME) has been observed.
    Keywords: Adaptive Filters; ECG; Artifacts; LMS; RLS; SMA.

  • Epileptic Seizure Detection in EEG Using Improved Entropy   Order a copy of this article
    by A. Phareson Gini, M.P. Flower Queen 
    Abstract: Epilepsy is a chronic disorder of the brain that impacts people all around the world. This is categorized by recurrent seizure and it is difficult to recognize when someone is consuming an epileptic seizure. The electroencephalogram (EEG) signal plays a significant part in the recognition of epilepsy. The EEG signal generates complex information and it has been stowed in EEG recording schemes. It is tremendously challenging to investigate the chronicled EEG signal and the analysis of the epileptic activity in a time consuming procedure. In this article, we suggest a novel ANN based Epileptic Seizure Detection in EEG signal with the help of the Improved Entropy technique. The anticipated technique comprises pre-processing, feature abstraction and EEG organization which utilizing artificial neural network. In primary phase we sample all the input information set. In the second phase, a fuzzy entropy algorithm is utilized to abstract the features of experimented signal. In organization segment, we utilize artificial neural network for to recognize Epilepsy seizures in exaggerated patient. Lastly, we associated the anticipated technique with prevailing technique for the perceiving epileptic sections. The function is utilized to compute the following parameters like accuracy, specificity, FAR, sensitivity, FRR, GAR which established the effectiveness of the anticipated Epilepsy seizure recognition system.
    Keywords: Entropy; EEG; ANN.

  • Kurtosis Maximization for Blind Speech Separation in Hindi Speech Processing System using Swarm Intelligence and ICA   Order a copy of this article
    by Meena Patil, J.S. Chitode 
    Abstract: Blind Source Separation (BSS) method divides mixed signals blindly without any data on the mixing scheme. This is a main issue in an actual period world whether have to identify a specific person in the crowd or it is a zone of speech signal is removed. Besides, these BSS approaches are collective with shape and also statistical features to authenticate the performance of each one in outline classification. For resolving this issue proposes an active BSS algorithm on the basis of the Group Search Optimization (GSO). The kurtosis of the signals is used as the objective performance and the GSO is utilized to resolve it in the suggested algorithm. Primarily, source signals are taken into account as the Independent Component Analysis (ICA) to generate the mixing signals to BSS yield the maximum kurtosis. The source signal constituent that is divided out is then smeared off from mixtures with the help of the deflation technique. Each and every source signals establish that important development of the computation amount and the quality of signal separation is attained using the projected BSS-GSO algorithm if associated with the preceding algorithms.
    Keywords: Blind source separation (BSS); Speech signal; optimization; ICA; Mixing signals and Unknown signals.

  • Electrocardiogram compression using the Non-Linear Iterative Partial Least Squares algorithm: a comparison between adaptive and non-adaptive approach   Order a copy of this article
    by Pier Ricchetti, Denys Nicolosi 
    Abstract: Data Compression is applicable in reducing amount of data to be stored and it can be applied in several data collecting processes, being generated by lossy or lossless compression algorithms. Due to its large amount of data, the use of compression is desirable in ECG signals. In this work, we present the accepted Non-Linear Iterative Partial Least Squares (NIPALS) method as an option to ECG compression method, as recommended by Nicolosi. In addition, we compare the results based in an adaptive and non-adaptive version of this method, by using the MIT Arrhythmia Database. As a help to obtain a better comparison, we have developed an abnormality indicator related to possible abnormalities in the waveform, and a decision method that helps to choose between adaptive or non-adaptive approach. Results showed that the adaptive approach is better than the non-adaptive approach, for the NIPALS compression algorithm.
    Keywords: data compression; component analysis; adaptive; comparison; PCA; principal component analysis; nipals; nonlinear iterative partial least squares; ECG; electrocardiogram; compression algorithms.

  • A tumour segmentation approach from flair MRI brain images using SVM and genetic algorithm   Order a copy of this article
    by S.U. Aswathy, G. Glan Devadhas, S.S. Kumar 
    Abstract: This paper puts forth a framework of a medical image analysis system for brain tumor segmentation. Image segmentation helps to segregate objects right from the background, thus proving to be a powerful tool in Medical Image Processing.This paper presents an improved segmentation algorithm rooted in Support Vector Machine and Genetic Algorithm. SVM are the basis technique used for segmentation and classification of medical images. The MRI database used consists of FLAIR images. The proposed system consists of two stages. The first Stage perform pre-processing the MRI image, followed by block division. The Second Stage includes feature extraction, feature selection and finally, the SVM based training and testing. The feature extraction is done by first order histogram and co-occurrence matrix and GA using KNN is used to select subset features. The performance of the proposed system is evaluated in terms of specificity, sensitivity, accuracy, time elapsed and figure of merit.
    Keywords: segmentation; support vector machine; genetic algorithm; k nearest neighbors.

  • Dual Modality Tran-Admittance Mammography and Ultrasound Reflection to Improve Accuracy of Breast Cancer Detection   Order a copy of this article
    by Khusnul Ain 
    Abstract: Breast tissue and cancer have high impedance ratio. Imaging impedance can produce high contrast images. TAM (Trans-admittance mammography) is one of prototype based on impedance to detect breast cancer. The TAM is only able to produce a projection image. It needs ratio between anomalous and normal admittance to obtain anomalous volume. Size and ratio of anomalous are very important to know precisely because it is associated with the stage and type of cancer. Acoustic data produces depth and volume anomalies appropriately. Combining TAM data and acoustic data are expected to provide promising results. The study was conducted by measuring trans-admittance of breast phantom by the TAM. It is conducted at a frequency 0.5; 1; 5; 10; 50 and 100 kHz. The acoustic data obtained by scanning breast phantom. Combination of depth and anomaly volume from ultrasonic reflection on the TAM device can provide the right information for ratio of conductivity anomalies and reference.
    Keywords: dual modality; trans-admittance mammography; ultrasound reflection; accurate; breast cancer.

  • Low Power DNA Protein Sequence alignment using FSM State Transition controller   Order a copy of this article
    by Sancarapu Nagaraju, Penubolu Sudhakara Reddy 
    Abstract: In this paper we proposed an efficient computation technique for DNA patterns on reconfigurable hardware (FPGAs) platform. The paper also presents the results of a comparative study between existing dynamic and heuristic programming methods of the widely-used Smith-Waterman pair-wise sequence alignment algorithm with FSM based core implementation. Traditional software implication based sequence alignment methods cant meet the actual data rate requirements. Hardware based approach will give high scalability and one can process parallel tasks with a large number of new databases. This paper explains FSM (Finite State Machine) based core processing element to classify the protein sequence. In addition, we analyze the performance of bit based sequence alignment algorithms and present the inner stage pipelined FPGA (Field Programmable Gate Array) architecture for sequence alignment implementations. Here synchronized controllers are used to carry out parallel sequence alignment. The complete architecture is designed to carry out parallel processing in hardware, with FSM based bit wised pattern comparison with scalability as well as with a minimum number of computations. Finally, the proposed design proved to be high performance and its efficiency in terms of resource utilization is proved on FPGA implementation.
    Keywords: DNA; Protein Sequence; FSM; Smith-Waterman algorithm; FPGA; Low Power.

  • A review on multimodal medical image fusion   Order a copy of this article
    by BYRA REDDY G R, Dr. Prasanna Kumar H 
    Abstract: Medical image fusion is defined as combining two or more images from single or multiple imaging modalities like Ultrasound, Computerized Tomography, Magnetic Resonance Imaging, Single Photon Emission Computed Tomography, Positron Emission Tomography and Mammography. Medical image fusion is used to optimize the storage capacity, minimizes the redundancy and to improve quality of the image. The goal of medical image fusion is to combine complementary information from multiple imaging modalities of the same scene. This review paper describes about different imaging modalities, fusion methods and major application domains.
    Keywords: Image fusion; Ultrasound; Mammography; Magnetic Resonance,Computed Tomography.

  • Heart Sound Interference Cancellation from Lung Sound Using Dynamic Neighborhood Learning-Particle Swarm Optimizer Based Optimal Recursive Least Square Algorithm   Order a copy of this article
    by Mary Mekala A, Srimathi Chandrasekaran 
    Abstract: Cancellation of acoustic interferences from the lung sound recordings is a challenging task. Lung sound signals provide critical analysis of lung functions. Thus lung related diseases can be diagnosed with noiseless lung sound signals. A Recursive Least Square (RLS) algorithm based adaptive noise cancellation technique can be used to reduce the heart sounds from lung sounds are proposed in this paper. In RLS, the forgetting factor is the major parameter which determines the performance of the filter. Finding the optimal forgetting factor for the given input is the vital step in RLS operation. An improved PSO algorithm is used to find the optimal forgetting factor for the proposed RLS algorithm. Three different normal breath sounds mixed with heart sound signals are used to test the algorithm. The results are assessed with the correlation coefficient between the original uncorrupted lung sound signal and the interference cancelled lung signals by the proposed optimal filter. The power spectral density plots are also used to measure the accuracy of the proposed optimal RLS algorithm.
    Keywords: Lung sound signals;Dynamic Neighborhood Learning; Recursive Least Square; Adaptive noise cancellation; Optimization;Forgetting Factor;Heart Sound Signals;Correlation Coefficient;Power Spectral Density;Bronchial Sound.

  • Prediction of Risk Factors for Prediabetes using a Frequent Pattern based Outlier Detection   Order a copy of this article
    by Rajeswari A.M., Deisy C. 
    Abstract: Prediabetes is the forerunner stage of diabetes. Prediabetes develops type-2 diabetes slowly without any predominant symptoms. Hence, prediabetes has to be predicted apriori to stay healthier. The risk factors for prediabetes are abnormal in nature and are found to be present in a few negative test samples (without diabetes) of Pima Indian Diabetes data. The conventional classifiers will not be able to spot these abnormal samples among the negative samples as a separate group. Hence, we propose an algorithm Frequent Pattern Based Outlier Detection (FPBOD) to spot such abnormal samples (outliers) as a separate group. FPBOD uses an associative classification technique with few surprising measures like Lift, Leverage and Dependency degree to detect outliers. Among which, Lift measure detects more precise outliers that are able to correctly classify the person who didnt have diabetes, but just takes the risky chance of being a diabetic patient.
    Keywords: outlier detection; prediabetes; frequent pattern based outlier detection; associative classification; surprising measure.

  • Design of Analytic Wavelet Transform with Optimal Filter Coefficients for Cancer Diagnosis Using Genomic Signals   Order a copy of this article
    by Deepa Grover, Sonica Sondhi, Banerji B. 
    Abstract: DNA sequence analysis and gene expression analysis through genomic signal processing played an important role in cancer diagnosis in recent years. Cancer diagnosis through gene expression data, Discrete Fourier transform, Discrete Wavelet transform (DWT) and IIR Low pass filter are frequently used but suffer from drawbacks like longer essential time-support. Analytic wavelet transform with optimal filter coefficients for cancer diagnosis using genomic signals is designed in this paper. The proposed technique consists of three modules namely, pre-processing module, optimization module and transform and cancer diagnosis module. Initially the filter coefficients are optimally found out using Group Search Optimizer. Then, the optimal coefficients and the pre-processed DNA sequence is applied to analytic wavelet transform and subsequently, diagnosis for the cancer cell is made based on the threshold. DNA sequences obtained from National Centre for Biotechnology Information (NCBI) forms the database for the evaluation. Evaluation metrics parameters employed are sensitivity, specificity and accuracy. Comparison is made to the base method and analytic transform technique for more analysis. From the results, we can observe that the proposed technique has achieved good results attaining accuracy of 91.6% which is better than other compared techniques.
    Keywords: Genomic Signal Processing (GSP); Cancer diagnosis; GSO; Analytic transform; thresholding.

  • A Review of Non-Invasive BCI Devices   Order a copy of this article
    by Veena N., Anitha N. 
    Abstract: BCI provisions humans beings to control various devices with the help of brain waves. It is quite useful for the people who are totally paralyzed from neuromuscular diseases such as spinal cord injury, brain stem stoke. BCI permits a muscular free channel for conveying the user intent into action which help the people with motor disabilities to control their surroundings. Various non-invasive technologies like Electroencephalogram (EEG), Magnetoencephalography (MEG), functional Magnetic Resonance Imaging (fMRI) etc, are available for capturing the brain signal. In this article, various non-invasive BCI devices are analysed and nature of signals captured by it are reported. We also explore the use of signals for diseases diagnosis, there features and availability of those devices in the market.
    Keywords: EEG; MEG; fMRI; Non-invasive; Psychological; Physiological.

  • R peak Detection for Wireless ECG using DWT and Entropy of coefficients   Order a copy of this article
    by Tejal Dave, Utpal Pandya 
    Abstract: Investigation of patients Electrocardiogram helps to diagnose various heart related diseases. With correct R peak detection in ECG wave, classification of arrhythmia can be carried out accurately. However, accurate R peak detection is a big challenge especially in wireless patient monitoring system. In wireless ECG system, in order to reduce the power consumption; it is desirable to capture ECG at lower sampling rate. This paper proposes an algorithm for R peak detection using discrete wavelet transform in which detailed coefficients are selected based on entropy. The proposed algorithm is validated with MIT-BIH database and its performance is compared with similar work. For MIT-BIH case, positive predictivity and sensitivity for proposed algorithm are 99.85 and 99.73, respectively. Application of proposed algorithm on wireless ECG, acquired at adjustable sampling rate from different subjects using prototyped Bluetooth ECG module, shows efficacy of algorithm to detect R-peak of ECG with high accuracy.
    Keywords: Electrocardiogram; Wireless Monitoring System; Entropy; Discrete Wavelet Transform.

  • Muscle fatigue and performance analysis during fundamental laparoscopic surgery tasks   Order a copy of this article
    by Ali Keshavarz Panahi, Sohyung Cho, Michael Awad 
    Abstract: A limited working area and impaired degree of freedom have led surgeons to encounter ergonomic challenges when performing minimally invasive surgery (MIS). As a result, they become vulnerable to associated risks such as muscle fatigue, potentially impacting their performance and causing critical errors in operations. The goal of this study is to first establish the extent of muscle fatigue and time-to-fatigue in vulnerable muscle groups, before determining whether the former has any effect on surgical performance. In the experiment, surface electromyography (sEMG) was deployed to record the muscle activations of 12 subjects (6 males and 6 females) while performing fundamentals of laparoscopic surgery (FLS) tasks for a total of 3 hours. In all, 16 muscle groups were tested. The resultant data were then reconstructed using recurrence quantification analysis (RQA) to achieve the first goal. In addition, a subjective fatigue assessment was conducted to draw comparisons with the RQA results. The subjects performance was also investigated via a FLS task performance analysis, the results demonstrating that RQA can detect muscle fatigue in 12 muscle groups. The same approach also enabled an estimation of time-to-fatigue for said groups. The results also indicated that RQA and subjective fatigue assessment are very closely correlated (p-value <0.05). Although muscle fatigue was established in all 12 groups, the performance analysis results showed that the subjects execution of their duties improved over time.
    Keywords: Minimally Invasive Surgery; Fatigue Analysis; Recurrence Quantification Analysis; FLS Task Performance Analysis; Subjective Fatigue Assessment.

  • Automatic Diagnosis of Stomach Adenocarcinoma using Riesz Wavelet   Order a copy of this article
    by ANISHIYA P, Sasikala M 
    Abstract: Adenocarcinoma originates from the glands. It causes changes in the gland architecture. The detection of adenocarcinoma requires histopathological examination of tissue specimens. At present, diagnosis and grading of the cancer depends on the visual interpretation of the biopsy samples by pathologist and thus, it may lead to a considerable amount of inter and intra-observer variability. To overcome this drawback and to reduce the reliance on the human interpretation and thereby reducing the workload of pathologists, many methods have been proposed. In this paper, a novel method to quantify a tissue for the purpose of automated cancer diagnosis and grading is introduced. The stomach tissue images are preprocessed to compensate for color variations. The Riesz wavelet transform is applied to the preprocessed stomach tissue images. From Riesz wavelet coefficients, 14 different statistical features were extracted. Wrapper based feature selection is used. The reliability check on the final dataset is performed using ANOVA. In diagnosis, the tissue is classified into normal(non-malignant), well differentiated, moderately differentiated, poorly differentiated and tissue. The proposed system yielded a classification accuracy of 93.2% in diagnosing and 98.33% in Grading.
    Keywords: Stomach adenocarcinoma; histopathological image analysis; Color Normalization; Riesz wavelet transform; cancer diagnosis; Hilbert transform; Simoncelli wavelet; ANOVA; Support Vector Machine.

  • Generalized Warblet Transform Based Analysis of Biceps Brachii Muscles Contraction Using Surface Electromyography Signals   Order a copy of this article
    by Diptasree MaitraGhosh, Ramakrishnan Swaminathan 
    Abstract: In this work, an attempt has been made to utilize the time-frequency spectrum obtained using Generalized Warblet Transform (GWT) for fatigue analysis. Signals are acquired from the biceps brachii muscles of twenty healthy volunteers during isometric contractions. The first and last 500 ms lengths of a signal are assumed as nonfatigue and fatigue zones respectively. Further, the signals from these zones are subjected to GWT for the computation of time-frequency spectrum. Features such as Instantaneous Mean Frequency (IMNF), Instantaneous Median Frequency (IMDF), Instantaneous Spectral Entropy (ISPEn), and Instantaneous Spectral Skewness (ISSkw) are estimated. The results show that the IMNF, IMDF and ISPEn increased by 24%, 34% and 36% respectively in nonfatigue condition. In contrast, 22% higher ISSkw is observed for fatigue condition. The statistical analysis indicates that the features are significant with p<0.001. It appears that the current method is useful in analyzing muscle fatigue disorders using sEMG signals.
    Keywords: sEMG; biceps brachii; muscle fatigue; GWT.

  • Automated Emotion State Classification using Higher Order Spectra and Interval features of EEG   Order a copy of this article
    by Rashima Mahajan 
    Abstract: Automated analysis of electroencephalogram (EEG) signals for emotion state analysis has been emerging progressively towards the development of affective brain computer interfaces. However, conventional EEG signal analysis techniques such as event related potential (ERP) and power spectrum estimation fail to provide high emotion state classification rates due to Fourier phase suppression when utilized with distinct machine learning tools. Further, only limited types of emotions has been explored for automated recognition using EEG, even though there are varieties of emotional states to illustrate the humans feelings. An attempt has been made to develop an efficient emotion classification algorithm via EEG utilizing statistics of fourth order spectra. A four-dimensional emotional model in terms of arousal, valence, liking and dominance is proposed using emotion specific EEG signals from DEAP dataset. A compact set of five temporal peak/interval related features and three trispectrum based features have been extracted to map the feature space. Through the feature map, a multiclass-support vector machine (SVM) based classifier using one-against-one algorithm is configured to yield a maximum classification accuracy of 81.6% using while classifying four emotional states. A comparison of multiclass-SVM with other classifiers such as feed forward neural network (FFNN) and radial basis function network (RBF) has been made. Significant improvement using a proposed compact hybrid EEG feature set and a multiclass -SVM has been achieved for automated emotion state classification.
    Keywords: Brain Computer Interface (BCI); Electroencephalogram (EEG); Emotions; Multiclass-SVM; Trispectrum; Temporal; DEAP.

Special Issue on: Soft Computing Techniques for Bio-Medical Signal and Image Processing

  • Microfluidic device for separating mesenchymal stem cells from blood cells in amniotic fluid using cross flow filtration technique   Order a copy of this article
    by Sabitha Balasubramanian, Muniraj N.J.R 
    Abstract: Amniotic fluid, which surrounds the fetus in the womb, contains fetal cells including mesenchymal stem cells, which are able to make a variety of tissues. Women during her prenatal period elect to have the process of amniocentesis that is extracting amniotic fluid to test for chromosome defects. The extracted fluid contains mesenchymal stem cells, blood cells, and tissues of the baby. The primary objective of this research is to the separate the mesenchymal stem cells and the blood cell by cross flow filtration technique. A microfluidic system is designed to separate the cell which is more effective and accurate than conventional type.
    Keywords: Amniotic fluid; Microfluidics; Cross flow filtration; COMSOL Multiphysics; Mesenchymal stem cells; Blood cells; Amniocentesis; Separation; Prenatal period; Fetus; CFD analysis.

  • Mitigation Strategy against SSDF Attack for Health Care in Cognitive Radio Networks   Order a copy of this article
    by Chaitanya Duggineni, K. Manjunatha Chari 
    Abstract: Wireless communications have a rapid growth that leads to huge demand on the deployment of new wireless services in both licensed and unlicensed frequency spectrum. The performance of cooperative spectrum sensing (CSS) in cognitive radio is based on two factors: cooperative gain and cooperative overhead. There are many other dominating factors that affect the performance of CSS like the presence of attacks, energy efficiency, sensing time and delay, spectrum efficiency, etc. The major threat to CSS is spectrum sensing data falsification (SSDF) attack. Existing methods to mitigate the SSDF attack doesnt focus on energy efficiency which is performed here. To deal with these challenges, we propose an energy efficient mechanism against SSDF attack for health care application in cognitive radio networks (CRN). We propose a malicious node identification algorithm (MIA) to mitigate the problem of SSDF attack in the network and to eliminate the redundant data at the fusion center, balanced cluster based redundancy check aggregation (BCRCA) mechanism is proposed. Finally, the decision taken by the fusion center is based on weighted selection combining (WSC) technique that improves spectrum decision accuracy.
    Keywords: Cooperative spectrum sensing; Data aggregation; SSDF Attacks; Weighted selection combining.

  • Bit Error Rate Minimization using SLM Technique in TFT - OFDM for Mobile Large-Scale MIMO Systems   Order a copy of this article
    by MEENAKSHI RENGASAYEE, Indumathi Pushpam 
    Abstract: In the case of large-scale Multiple-Input Multiple-Output (MIMO) systems, the Time-Frequency Training (TFT) of OFDM and their transmission schemes can solve the high dimensional problems of channel estimation in the wireless communication systems. In the wireless technologies, their physical layer can carry out the process of transmission inside the variable channels. The noise that was induced by these channels may also degrade the performance of the system that concerns Bit Error Rate (BER). So, in this paper, a Selection Mapping Technique (SLM) in the TFT OFDM for the Mobile Large-Scale MIMO Systems has been proposed for minimizing the BER. This SLM technique tends to product the data with these phase vectors for discovering the candidate vectors and also the IFFT operation which is done on the TFT OFDM symbol that obtains a minimum BER that has to be transmitted. This scheme performance has been compared with that of the existing TDM OFDM with bit error rate. The results of this experiments prove that the proposed scheme achieves a better performance than that of the existing schemes.
    Keywords: TFT OFDM-MIMO systems; SLM; BER.

  • Dominator Chromatic Number of m-Splitting graph and m-Shadow graph of path graph   Order a copy of this article
    by T. Manjula, R. Rajeswari 
    Abstract: Graph theory techniques are applied to several biological domains. The application of graph coloring and domination in the field of biology and medicine includes identifying drug targets, determining the role of proteins, genes of unknown function. The area obtained by combining graph coloring and domination is called the dominator coloring of a graph. This is defined as proper coloring of vertices in which every vertex of the graph dominates all vertices of at least one color class. The least number of colors required for a dominator coloring of a graph is called the dominator chromatic number. The dominator chromatic number and domination number are obtained for m-Splitting graph and m-Shadow graph of path graph and a relationship between them is expressed in this paper.
    Keywords: domination; coloring; dominator coloring; m-Splitting graph; m-Shadow graph; path graph.

  • A Novel and Efficient Instrumentation Technique for Human Blood Pressure Measurement Using Computational Intelligence Method   Order a copy of this article
    by SAMSON ISAAC, PORKUMARAN K 
    Abstract: Blood pressure is one of the vital parameter in the evaluation of cardiovascular function and status. It has been generally accepted that blood pressure is significantly affected by the resistance in the peripheral vessels during systole and cardiac output during diastole respectively. A novel and efficient instrumentation system for the measurement of human blood pressure using computational intelligence techniques has been proposed. On the basis of this physiological foundation, change in blood pressure can be evaluated by monitoring the change in blood flow. Over 20 volunteers participated in this trials with the body mass index (BMI) fall in the wide ranges from 19 to 28. An efficient technique for removal of motion artifacts were proposed using signal processing that improves the accuracy of the measurements and the results were calibrated against gold standard. Computational intelligence method was used to compute the relationship between features of PPG signal with the calibrated blood pressure readings. The real time measurements were carried out using LabVIEW 2011 software tool. The accuracy of the result was accounted for calibrating the calculated Blood Pressure levels with the standard values. The promising results indicate the feasibility of using the method as a non-invasive blood pressure measurement system in humans.
    Keywords: instrumentation; photoplethysmograph; blood pressure; computational intelligence; accuracy; Calibration;.

  • Numerical Modeling of Ultra Wide Band Signal Propagation in Human Abdominal Region   Order a copy of this article
    by Thirumaraiselvan Packirisamy, Jayashri S 
    Abstract: Due to the growing need for developing implantable wireless transceivers in Body Area Networks (BAN), it becomes necessary to characterize the wireless channel in Ultra Wide Band (UWB) frequency range. In case of BAN with implantable sensors, in-vivo measurement is not practically feasible. Therefore, modeling the electromagnetic wave propagation inside the human body through numerical simulations and characterizing the wireless channel would be a good solution. This paper discusses the various steps involved in the development of a generic channel model and proposes an approach using modified raytracing to predict the channel path loss characteristics of an Implantable Body Area Network in the Ultra Wide Band (UWB) frequency range. As the human body is a heterogeneous and multilayer environment, the path loss at different depth inside the body is predicted with a four layer human abdomen model and the results are compared with the measured data.
    Keywords: electromagnetic wave propagation; pathloss; raytracing; body area network;ultra wide band;numerical modeling.

  • A LOW POWER VLSI IMPLEMENTATION OF DISTORTION CORRECTION IN IMAGE PROCESSING ASIC   Order a copy of this article
    by M. Mohankumar, V. Gopalakrishnan, S. Yasotha 
    Abstract: Digital video surveillance has emerged to become widely employed in public, Medical and private locations like government buildings, military bases, car parks, and banks, and so on. Conventional monitoring cameras can have coverage of only a small area, resulting in blind spots. They are capable of monitoring an area which covers about 180
    Keywords: Barrel distortion correction; non-linear method; Surveillance; Chaotic Polynomial Maps.

  • Indoor Air Quality Investigations in Hospital Patient Room   Order a copy of this article
    by I. Daniel Lawrernce, S. Jayabal, P. Thirumal 
    Abstract: Indoor air quality has a vital role in health considerations, Its relates to the thermal and human comfort of the indoor occupants, especially patient room in Hospital building. Indoor to gain further more insight into the patient room an air quality monitoring was conducted to identity the comfortable perspective. The monitoring was carried out on three different systems such as naturally ventilated, passive split ventilated and active ventilation in centralized unit in Hospital Building for Two different human load conditions. Its also identical thermal comfort and human comfort on preserved patient occupied room. The use of these findings predicted the relationship between the indoor and outdoor environment about the variable parameters of fresh air supply, temperature flow and human load. The thermal comfort determined through temperature and relative humidity and the improvement of human comfort obtained from the improvement of the reduction of oxides and particulates of measured ventilated patient room. The studied patient room demonstrates that by the Air quality monitoring system evaluations various aspects regarding comfortable indoor enhancement, by complying the Indoor monitoring factors that successfully ensured the comfort living space. The monitoring results explore how different ventilations could manage comfort indoor, and therefore, benefit patient and occupant health.
    Keywords: Indoor air quality; Ventilation; Human load; Fresh air supply; Temperature.

Special Issue on: Machine Learning Techniques for Medical and Biological Applications

  • PHASE BASED FRAME INTERPOLATION METHOD FOR VIDEOS WITH HIGH ACCURACY USING ODD FRAMES   Order a copy of this article
    by Amutha S, Vinsley SS 
    Abstract: In this project, an innovative complexity motion that has lowvector processing algorithm at the end side is proposed for motion-compensated video vector frame interpolation or frame rate up-conversion. By processing this algorithm we normally shows the problems of broken edges and deformed structure problems in an frame interpolation by hierarchically refining motion vectors on different block sizes. Such broken edges are taken out using frame interpolation method by taking the odd frames and interpolate that image so that to have the high quality resolution of images so that blur in the images obtained from the video is being removed. By using blending techniques it is easy to remove the image blur and also to improve the quality of the image obtained from the video. So the image has been obtained with high resolution. In the proposed method the input has been taken as video instead of images in the existing system and the recovery output is taken as images and further process has been undergone to get the output as video. There are some different techniques in this method such as phase based interpolation technique, multistage motion compensated interpolation etc are commonly used to get high purpose image with reduced blur in the images to get the clear image of the input videos. Experimental results prove that the proposed system visual quality to be better and is also rugged, even in video sequences comprising of fast motions and complex scenes.
    Keywords: MCFI,BMA; phase based interpolation; steerable pyramid; blending technique.

Special Issue on: Bioscience and Computational Methods

  • Dual Tree Complex Wavelet Transform Incorporating SVD and Bilateral Filter for Image Denoising   Order a copy of this article
    by Mohan Laavanya, Marappan Karthikeyan 
    Abstract: In recent years massive production of digital images increased the need for image denoising. The effect of noise can be removed by using spatial and frequency domain approaches. Discrete Wavelet Transforms (DWT) is a frequency domain approach, which removes the noise by shrinking the wavelet coefficients using simple threshold value. Even though wavelet transform is popularly used in image processing applications, shift variance and poor directional selectivity are the two noteworthy limitations. In order to overcome these limitations, Dual Tree Complex Wavelet Transform (DTCWT) is used for perfect reconstruction of noisy image. A DTCWT incorporating Singular Value Decomposition (SVD) with frobenius energy correcting factor and bilateral filter for image denoising using bivariate shrinkage function for thresholding the image is proposed in this paper. The denoising performance of the proposed method in terms of PSNR and it indicates that the proposed method outperforms over other existing techniques.
    Keywords: Bilateral Filter; Bivariate Shrinkage; DTCWT; Image Denoising; SVD; Thresholding Technique; Wavelet Transform.

  • Tri Texture Feature Extraction and Region Growing Level Set Segmentation in Breast Cancer Diagnosis   Order a copy of this article
    by Aarthy S L, Prabu Sevugan 
    Abstract: Computer Aided Diagnosis (CAD) systems utilizes the computer technology to detect and classify the normal and abnormal (distortion, asymmetry, masses and micro calcification) levels in breast cancer analysis. The operating stages in CAD of breast cancer are segmentation, feature extraction and classification. The preservation of characteristics of tumors (boundaries) and the multi-angular texture features contribute the clear image analysis. This paper employs the series of feature extraction and the novel segmentation methods to improve the performance of automatic abnormality analysis in breast cancer image. Initially, the Tri-Texture (TT) feature extraction method such as Gray Level Co-occurrence Matrix (30 and 45 degree variations), Gabor and wavelet extracts the set of texture features from the segmented output. More number of features increases the computational complexity in classification. Hence, this paper employs the hybrid Genetic Algorithm (GA)-Particle Swarm Optimization (PSO) to select the relevant features for classification. Besides, the proposed work employs the two classifiers such as Support Vector Machine (SVM) (to classify normal and abnormal level) and Neural Network (NN) (to label the distortion, asymmetry, masses and micro calcification). The hybrid Region Growing and Level set methods (RGL) provides the segmented output to analyze the abnormal categories. The utilization of multiple methods improves the abnormality analysis of breast cancer diagnosis applications. The comparative analysis between the proposed RGLTT with the existing segmentation and feature extraction methods regarding the parameters of accuracy, sensitivity, specificity and likelihood (positive and negative) confirms the effectiveness of RGLTT in medical diagnosis.
    Keywords: Breast Cancer Image Analysis; Gray Level Co-occurrence Matrix; Level set; Neural Network Classifier; Region Growing; Support Vector Machine; Texture Feature Extraction;.

  • Pharmacovigilance Predictive Analysis using NLP based Cloud   Order a copy of this article
    by Madhan E.S. 
    Abstract: Nowadays, healthcare, on big data are a major research area in computer science field. This paper presents a mysterious analysis of Pharmacovigilance from reviewers using NLP (Natural Language Processing) Cloud environment. The system of approach explored by the variation of offline and online feedbacks of patients and it reveals through Sentimental analysis in the NLP Cloud system. Pharmacovigilance in NLP Cloud analysis process identified the emotional analysis of the patient medicine intake data. The existing conventional methods of Pharmacovigilance are taken upon clinical trials and small groups of tests data. The comparison result helps to find quicker analysis of medicine intake of the patients and protect from adverse drug event. Our approach will gain with the effort by the Pharmacovigilance in Cloud for patients. This innovation furnishes patients and specialists with openness to data that can enhance health care by investigating the primary as well as secondary data.
    Keywords: Cloud computing; Pharmacovigilance; Natural Languge Processing; Bigdata;IOT;Adverse Drug Reaction (ADR); Health Care.

  • BURST COMMUNICATION BY USING SELF ADAPTIVE BUFFER ALLOCATION WITH ENERGY EFFICIENT IN BODY SENSOR NETWORKS   Order a copy of this article
    by SANGEETHA PRIYA NACHIMUTHU, Sasikala Ramasamy, Srinivasan Alavandar 
    Abstract: The revolution of wireless sensory devices inrnhealth care services is Monitoring of human movements.rnSuch type of motion analysis, uses humans inertialrninformation. This study is achieved by using Body SensorrnNetwork (BSN) which many wireless sensor nodes placed onrndifferent parts of the body. Disease is recognized by sharedrnprocessing of sensor information from multiple locations ofrnthe body. Eventhough this platform has high potential inrnhealth care; the commercialization of these systems isrndifficult because of power requirements and wearabilityrnproblems. In this paper, a Self-Adaptive Greedy bufferrnallocation and scheduling algorithm (SGBAS) is presentedrnfor optimization of communication model for BSNrnapplications which uses self-adaptive buffers for limitation ofrncommunication to short bursts, power usage and transmittingrnsensed data to the backend servers periodically. Thernoptimization of Qos is achieved by introducing buffers. Thisrnproject provides a self-adaptive heuristic scheme which isrnformulated to reduce transmissions among sensor nodes. Forrnearly diagnosis, it sends the data at right time for the analysisrnof health care professionals. Several experimental evaluationrnand simulations is to be done to assess the proposed SGBASrntechnique for allocation of buffers in real-time under variousrnsimulation setups. Experimentally demonstrate therneffectiveness of SGBAS power reduction techniques.
    Keywords: Body Sensor Networks (BSN); Sensed DatarnProcessing; Burst Communications; Adaptive Buffer Allocation,rnBuffer resizing; Energy Optimization and Self-Adaptive Greedyrnbuffer allocation and scheduling algorithm (SGBAS).

  • Biclustering of Gene Expression data using Biclustering Iterative Signature Algorithm and Biclustering Coherent Column   Order a copy of this article
    by Saravana Kumar E., Vengatesan K, Singh RP, Rajan C 
    Abstract: Clustering has various methods for solving the different research problems in the biological domain. Analysis of gene expression data in the biomedical field is the very critical task, in which various algorithms are proposed under different experimental conditions. In this proposed work the gene expression data are tested with Biclustering Bimax and Biclustering Iterative Signature Algorithm (ISA) and Biclustering Coherent Column, the experimental result shows the Biclustering ISA has demonstrated a coherent manifestation contour only in the surfeit of subset of microarray experiments and produced a momentous result.
    Keywords: Clustering; Gene expression; Biclustering; Iterative Signature Algorithm formatting.

  • Automatic Glioblastoma Multiforme detection using Hybrid SVM with Improved Particle Swarm Optimization   Order a copy of this article
    by Sountharrajan S., Suganya E, Karthiga M, Rajan C 
    Abstract: Gliomas is one of the harmful life frightening brain dementia which occurs unnecessary growth of cells within the brain. In medical field detection of brain tumors is a challenging task. Medical Resonance Imaging (MRI) is one of the best techniques to identify the tumors. Gaussian filters are used in preprocessing to increase the image quality. Gray-level co-occurrence matrix (GLCM) is used to extract the features by using spatial relationship between the image pixels. In this paper, an advanced classification technique called Hybrid SVM is introduced to classify the brain image with reduced features. To improve the efficiency Hybrid SVM is used with Radial Basis Function (RBF) kernel. The proposed algorithm classifies the brain tumour classes intelligently. Hybrid SVM with Improved Particle Swarm Optimization is used to overcome the drawback of hyperplane selection. The experimental results analysis of the proposed work outperforms the other recent classifiers with 92.75% accuracy rate.
    Keywords: Gliomas; Gaussian Filters; Gray-level co-occurrence matrix; Improved Particle Swarm Optimization.

  • Quantifying Speech Signal of Deaf Speakers with Territory Specific Utterances to Understand the Acoustic Characteristics   Order a copy of this article
    by Nirmaladevi J., Bommanna Raja 
    Abstract: Hearing loss, deafness, hard of hearing, anacrusis and hearing impairment are the various terms used in the deaf community as a condition for inability to hear either partial or total impairment. The hearing loss in most of the deaf persons affects the language development and cause difficulty to lead their personal life and career. Consequently to support the deaf speakers by means of a proper assistive method, extensive work is carried out to understand the acoustic characteristics of the speech parameters by estimating the differences in comparison with the normal speakers. The speech signals are procured from the 32 territory specific normal and deaf speakers by uttering 10 words in each group. The speakers are from Indian natives, Tamil language speaking persons. The parameters analysed are pitch, formants, fundamental frequency variation (jitter) and amplitude variation (shimmer). From the overall results obtained for the parameters, it is observed that acoustic characteristics differ significantly for the deaf speakers. And the quantitative values of the parameters for the selected words are controlled by the normal speakers. The description of the work revealed that using the acoustic characteristics the informative part of speech for the normal group and deaf group may be identified. Further the acoustic parameters may be used as a correction factor for the deaf speech signal such that the listeners can understand the speech uttered by them.
    Keywords: Deaf Speaker; Hard of Hearing; Deaf Speech Processing; Assistive Mechanism for Deaf Speaker; Speech Synthesization; Speech Signal Processing.

  • NOVEL ENERGY EFFICIENT PREDICTIVE LINK QUALITY BASED RELIABLE ROUTING (EEPLQRR) FOR WIRELESS MULTIMEDIA BIO-SENSOR NETWORKS IN BIO-MEDICAL INVENTION RESEARCH AND BIONIC UTILITIES MONITORING APPLICATION   Order a copy of this article
    by Kirubasri G. Kirubasri, UmaMaheswari Natarajan, Venkatesh Ramalingam 
    Abstract: Abstract: With recent advancements and cheaper availability of small wireless devices capable of harvesting multimedia contents such as audio, video streams, imageries, and scalar information, Wireless Multimedia Sensor Networks (WMSNs) are used in large number of applications such as sensor surveillance network, industrialized monitoring, traffic congestion control, and other real time multimedia applications which requires high Quality of Service (QoS). The harvested data from sensor nodes need to be transmitted to base station which is far away from the sensor node directly or through intermediate nodes. For extended network lifetimes and better QoS, there is a need for optimal energy and reliable routing. Satisfying these QoS requirements along with reliability and energy efficiency is a resource-constrained problem that provides new challenges to routing. In this paper, we present an in-depth study on the impact of Link State Estimates (LSE) and propose an Energy Efficient Predictive Link Quality Based Reliable Routing (EEPLQRR) Scheme for WMSNs in concert with the reimbursement of energy efficiency and reliability. Our proposed scheme calculates the reliability scores of various paths with better energy level. It further predicts the link quality of the paths with optimal energy and finalizes the reliable route. Several experimental analysis and simulations were done to evaluate the proposed technique. This technique has conserved around 3 to 8 Joules of energy in 50 seconds compared to adaptive reliable routing based on clustering hierarchy (ARCH) and Multimedia Reliable Energy Efficient routing Protocol (MREEP). Our proposed technique has also reduced 3 to 9% of packet drops with almost constant delay and higher throughput. This EEPLQRR had achieved 13-22% of increased network life time without affecting the network throughput, delay and packet loss.
    Keywords: Wireless Multimedia Sensor Networks (WMSNs); Link State Estimates (LSE); Residual Energy; Reliability; predictive link quality routing; Received Signal Strength indicator (RSSI);.

  • An Intelligent technique for uniquely recognizing Face and Finger image Using Learning Vector Quantization (LVQ) based Template Key Generation   Order a copy of this article
    by C.V. Arulkumar, P. Vivekanandan 
    Abstract: In current days, to identify, verify and detect the humans by using the bio recognition based on multimodal biometric was speedily developed which focus to necessitate the security keys in the authentication process of industries/organization. The main goal of this organization system is to integrate the instability biometric feature of the users and it is also used to formulate the key unguessable to an unauthorized person. In this proposed work, in multimodal biometrics methods particularly face and fingerprint based novel pattern matching is described. There are three modules to be used for exact Feature extraction; Multimodal biometric pattern generation and pattern matching are used to achieve better result this proposed work. At first, from the face images and finger prints the minutiae points, face features and some other features are extracted. Consequently, by using a density based score level fusion, the extracted features are merged together at match score level to create the multi - biometric pattern. After that, Learning Vector Quantization (LVQ) is used to perform the pattern matching. The assessment process was performed using large scale subjects to enter the system proving the ability of the proposed system over the state of art.
    Keywords: Face; Finger image; Multimodal biometric pattern generation; feature extraction; density based score level fusion and Learning Vector Quantization (LVQ); key generation.

  • Identity and Access Management as a Service in EHealth Care Cloud   Order a copy of this article
    by Dhanabagyam S.N., Karpagam G.R. 
    Abstract: Data in cloud are, protected, sensitive, confidential and is only accessible to actual individuals like certain identity. The resources are accessible through modification of the access control policies based on the user request. During the implementation of this online, the challenges like providing security to the identity and getting access to the resources through the refactoring of access control policies are to be dealt with. Here introduced a framework for getting over these challenges. Federated identity management along with single sign on could be utilized for providing security of identity to the user. Therefore the goal is the enhancement of the security of identity along with the availability of resources in multi tier cloud and to provide inter link cloud federation. The workflow offers an insight concerned with the identity and access management in the form of a service to Ehealth Care Cloud and thereafter a case scenario is studied.
    Keywords: Identity and Access Management(IAM),Attribute Based Access Control,Ehealth.

  • Denoising of Images using Principal Component Analysis and Undecimated Dual Tree Complex Wavelet Transform   Order a copy of this article
    by Veeramani VIJAYARAGHAVAN, Marappan KARTHIKEYAN 
    Abstract: Here, a method based on the combination of Undecimated Discrete Wavelet Transform (UDWT) and Dual Tree Complex Wavelet Transform (DTCWT) with Principal Component Analysis (PCA) for denoising images corrupted by Gaussian noise is proposed. The blend of UDWT and DTCWT results in Undecimated DTCWT (UDTCWT) which is a one-to-one relationship between co-located complex coefficients in all sub-bands and offers improved lower scale sub-band localization together with improved directional selectivity [10]. The proposed method uses UDTCWT with PCA for better dimensionality reduction and to obtain the compaction of signal energy in to a few principal components by spreading the noise over all the transformed coefficients. These properties of UDTCWT-PCA with a suitable locally adaptive window shrinkage function restore the noisy coefficients. This denoising method is tested on standard test images. The experimental results show that this method is better than existing methods in terms of Peak Signal to Noise Ratio (PSNR).
    Keywords: Complex Coefficient; Directional Selectivity; Image Denoising; Principal Component; Shrinkage.

Special Issue on: Developments and Issues in Medical Imaging

  • REGION BASED SEED POINT CELL SEGMENTATION AND DETECTION FOR BIOMEDICAL IMAGE ANALYSIS   Order a copy of this article
    by Arulmurugan R, Anandakumar H 
    Abstract: Salient region detection and segmentation from biological images is often a crucial step for image understanding, minimizing the content analysis complexity of images. This is because the initial contour selection during segmentation being a competent task and wrong differentiation between the foreground and background colors compromises the cell detection performance. In this paper, to improve the cell detection performance from biological images, a region-based cell detection and segmentation method called Histogram Color Contrast Seed Point Selection (HCC-SPS) is proposed.By defining salient value for each pixel, the Histogram Color Contrast model is able to group similar colour values, therefore addressing colour contrast in visual signal, resulting in accurate recovery of desired edge points. Second,considering the energy function, Region-based Seed Point Selection fine-tunes the salient value and makes differentiation between salient and background points more easily at the cell detected area.Third, due to salient mapping function with pixel representation, the method segments biological images, more accurately and naturally. The HCC-SPS when applied to biological images shows comparatively better than the available cell detection and segmentation methods. The experimental results on benchmark data sets further in comparison with the previous state-of-the-art cell detection and segmentation methods showed efficiency in terms of cell detection accuracy, segmentation time , false positive rate,segmentation accuracy and mapping efficiency.
    Keywords: Cell detection; Image segmentation; Seed Point Selection; Histogram; Color Contrast.

  • Rapid Estimation of Object Movements in Magnetic Induction Tomography   Order a copy of this article
    by Yasin Mamatjan, Ali Roula, Shabuerjiang Wubuli 
    Abstract: Magnetic induction tomography (MIT) is a contactless, inexpensive and non-invasive technique for imaging the conductivity distribution inside a body. A time-difference imaging can be used for monitoring the progression of stroke or oedema. However, MIT signals are more sensitive to body movements than the conductivity changes inside the body, because small movements during data acquisition can overwhelm the signals of interest and cause significant image artefacts. Thus, it is crucial to accurately estimate and compensate body movements for image reconstruction or alert clinicians to avoid misinterpretation. We propose frequency domain analysis and statistical approaches for identifying and estimating object movements from MIT data prior to the image reconstruction step. Results show that high amounts of movements totally distorted the images, whereas the proposed approaches produced good performance on elimination of image artefacts and its estimation while maintaining good computational efficiency for patient monitoring.
    Keywords: Magnetic induction tomography; movement estimation; movement compensation; Fast Fourier Transform (FFT) and Independent Component Analysis (ICA).

  • Domain Specific Approach for segmentation of NucleusCytoplasm in Bone Cancer Histopathology for Malignancy Analysis   Order a copy of this article
    by P.J. Antony, B.S. Vandana, R. Alva Sathyavathi 
    Abstract: Bone cancer is prevalent and early detection of disease is need of the day. Most of the computer assisted diagnosis tools of research pertain to various other parts of the body because of its simple tissue structure. Proposed research focuses on specific Ewing sarcoma stained with Hematoxylin and Eosin (H&E) data set wherein nucleus and cytoplasm features are extracted to define cancer. Two domain specific segmentation algorithms are proposed: 1) Model based clustering 2) Gradient based watershed segmentation methods are applied to extract nucleus and cytoplasm. H&E component of image are separated to improve quality of segmentation. Segmentation algorithms applied in parallel on H&E images to improve time factor. Morphological and texture features extracted from segmented images are used to train Support Vector Machine (SVM) for classification of malignancy.30 images of varying features are selected to train SVM classifier and 30 images are used for validation and the accuracy obtained is 94.5%.
    Keywords: Keywords: Nucleus-Cytoplasm Segmentation; malignancy level classification; bone cancer histopathologyrnrn.

  • A New Neural Network Method for Peripheral Vestibular Disorder Recognition using VNG Parameter Optimization   Order a copy of this article
    by Amine Ben Slama, Aymen Mouelhi, Hanene Sahli, Sondes Manoubi, Rim Lahiani, Mamia Ben Salah, Hedi Trabelsi, Mounir Sayadi 
    Abstract: The peripheral vestibular disorder (VD) diagnosis is a required task to ensure the efficiency of the treatment that needs complementary examinations of vertigo. In clinical practice, different tests of videonystagmography (VNG) technique are used to detect the presence of vestibular dysfunction disease. The topographical diagnosis of this disease presents a large diversity in its characteristics that show a mixture of problems for usual etiological analysis methods. In this paper, we propose an automatic classification method of VD by analyzing and reducing the VNG parameters based on a determined criterion. Therefore, a multilayer neural network (MNN) classifier is applied for VNG dataset based on the fundamental measurements of normal and patients affected by VD. The experimental results confirm that the proposed approach is very interesting and helpful for an accurate diagnostic of this disease.
    Keywords: Vertigo; Videonystagmography; Vestibular tests; Nystagmus; Fisher Linear Discriminant analysis (FLDA); Multilayer Neural Network (MNN).

  • PET image reconstruction based on Bayesian inference regularised maximum likelihood expectation maximisation (MLEM) method   Order a copy of this article
    by Abdelwahhab BOUDJELAL, Zoubeida Messali, Bilal Attallah 
    Abstract: A better quality of an image can be achieved through iterative image reconstruction for positron emission tomography (PET) as it employs spatial regularisation that minimises the difference of image intensity among adjacent pixels. In this paper, the Bayesian inference rule is applied to devise a novel approach to address the ill-posed inverse problem associated with the iterative maximum-likelihood Expectation-Maximisation (MLEM)algorithm by proposing a regularised constraint probability model. The proposed algorithm is more robust than the standard MLEM and in background noise removal with preserving edges to suppress the out of focus slice blur, which is the existent image artefact. The quality measurements and visual inspections show a significant improvement in image quality compared to conventional MLEM and the stateof-the-art regularised algorithms.
    Keywords: Image reconstruction; Positron Emission tomography; post-reconstruction; pre-reconstruction; MLEM algorithm; Bayesian inference; Iterative algorithms.