International Journal of Healthcare Technology and Management http://www.inderscience.com/browse/index.php?journalID=16&year=2011&vol=12&issue=5/6 Inderscience Publishers Ltd en-uk International Journal of Healthcare Technology and Management 1368-2156 1741-5144 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijhtm_scoverijhtm.jpg http://www.inderscience.com/browse/index.php?journalID=16&year=2011&vol=12&issue=5/6 http://www.inderscience.com/link.php?id=42367 Late potentials in ECG take place in the terminal portion of the QRS complex and are characterised by tiny amplitudes and larger frequencies. The occurrence of late potentials may signify underlying distribution of electrical activity of the cells in the heart and provides a substrate for production of arrhythmias (Rama Raju et al., 2008; Rama Raju and Malleswara Rao, 2009a). The problem of late potentials causes high levels of signal power to be seen at frequencies not representing the original signal (Rama Raju et al., 2008; Rama Raju and Malleswara Rao, 2009a). The present work describes the application of wavelet transform to provide a more accurate picture of the localised time-scale features indicative of the late potentials (Addison, 2005). The first step includes generating mathematical equations for various cases by developing a programme in Matlab. Mathematical equations are consequently generated for the signals under consideration and are compared with the available database (Rama Raju et al., 2009, 2010a; Rama Raju and Malleswara Rao, 2009b). The second step includes comparing the signal under consideration with all those signals in the database by developing an identification code in Matlab (Rama Raju et al., 2010c, 2010d). The late potentials in the signals under consideration were analysed and identified (Rama Raju et al., 2010b, 2010c, 2010d). Signals under consideration are represented mathematically and graphically and compared to classify the case more straightforwardly. Engineering modelling for alliance of late potentials in ECG signals in the course of wavelets
P.V. Rama Raju, V. Malleswara Rao, Ch.V. Satyanarayana
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 353 - 363
Late potentials in ECG take place in the terminal portion of the QRS complex and are characterised by tiny amplitudes and larger frequencies. The occurrence of late potentials may signify underlying distribution of electrical activity of the cells in the heart and provides a substrate for production of arrhythmias (Rama Raju et al., 2008; Rama Raju and Malleswara Rao, 2009a). The problem of late potentials causes high levels of signal power to be seen at frequencies not representing the original signal (Rama Raju et al., 2008; Rama Raju and Malleswara Rao, 2009a). The present work describes the application of wavelet transform to provide a more accurate picture of the localised time-scale features indicative of the late potentials (Addison, 2005). The first step includes generating mathematical equations for various cases by developing a programme in Matlab. Mathematical equations are consequently generated for the signals under consideration and are compared with the available database (Rama Raju et al., 2009, 2010a; Rama Raju and Malleswara Rao, 2009b). The second step includes comparing the signal under consideration with all those signals in the database by developing an identification code in Matlab (Rama Raju et al., 2010c, 2010d). The late potentials in the signals under consideration were analysed and identified (Rama Raju et al., 2010b, 2010c, 2010d). Signals under consideration are represented mathematically and graphically and compared to classify the case more straightforwardly.

]]> 10.1504/IJHTM.2011.042367 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 353 - 363 P.V. Rama Raju V. Malleswara Rao Ch.V. Satyanarayana Department of Electronics and Communication Engineering, SRKR Engg. College, Bhimavaram 534 204, AP, India; Affiliated to Andhra University, AP, India. ' Department of Electronics and Communication Engineering, SRKR Engg. College, Bhimavaram 534 204, AP, India; Affiliated to Andhra University, AP, India. ' Department of Electronics and Communication Engineering, SRKR Engg. College, Bhimavaram 534 204, AP, India; Affiliated to Andhra University, AP, India Fourier transforms STFT short-time Fourier transform CWT continuous wavelet transform Wigner-Ville distribution ECG electrocardiograms late potentials AANSIAMI-EC13 database St. Petersburg INCART 12-lead arrhythmia database heart disease cardiac arrest electrical signals. 2011-09-06T23:20:50-05:00 12 5/6 353 363 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42368 Feature selection is one of the important pre-processing steps in data mining for selecting informative feature subsets in large noisy data sets. This paper proposes an unsupervised feature selection method known as bidirectional selection based on the contribution entropy of individual features. The proposed feature selection method was tested on benchmark medical data sets, and the quality of the clusters obtained was evaluated using the homogeneity and separation ratio. Results show an improvement in cluster quality when compared with existing feature selection methods. Unsupervised bidirectional feature selection based on contribution entropy for medical databases
D. Devakumari, K. Thangavel, K. Sarojini
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 364 - 378
Feature selection is one of the important pre-processing steps in data mining for selecting informative feature subsets in large noisy data sets. This paper proposes an unsupervised feature selection method known as bidirectional selection based on the contribution entropy of individual features. The proposed feature selection method was tested on benchmark medical data sets, and the quality of the clusters obtained was evaluated using the homogeneity and separation ratio. Results show an improvement in cluster quality when compared with existing feature selection methods.

]]> 10.1504/IJHTM.2011.042368 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 364 - 378 D. Devakumari K. Thangavel K. Sarojini Department of Computer Science, Government Arts College, Dharmapuri 636705, Tamil Nadu, India. ' Department of Computer Science, Periyar University, Salem 636011, Tamil Nadu, India. ' Department of Computer Applications, S.N.R. Sons College, Coimbatore 641006, Tamil Nadu, India singular value decomposition SVD contribution entropy forward selection backward elimination bidirectional feature selection clustering homogeneity separation medical databases data mining cluster quality. 2011-09-06T23:20:50-05:00 12 5/6 364 378 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42369 Electrocardiogram (ECG) signal analysis is a technique to diagnose the cardiac diseases. But, the desired electrocardiogram signals are often corrupted by baseline interference, power line interference and electromyogram. Here, a method is proposed to extract ECG from noisy signals based on Singular Value Decomposition (SVD) and Genetic Algorithm. The advantage of this method compared to conventional methods like adaptive filtering, neural networks is that it does not require any prior knowledge of the signals. It is found that the signal to noise ratio improvement is nearly double when compared to neural network methods. Performance comparison of genetic algorithm and principal component analysis methods for ECG signal extraction
S. Balambigai, R. Asokan
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 379 - 389
Electrocardiogram (ECG) signal analysis is a technique to diagnose the cardiac diseases. But, the desired electrocardiogram signals are often corrupted by baseline interference, power line interference and electromyogram. Here, a method is proposed to extract ECG from noisy signals based on Singular Value Decomposition (SVD) and Genetic Algorithm. The advantage of this method compared to conventional methods like adaptive filtering, neural networks is that it does not require any prior knowledge of the signals. It is found that the signal to noise ratio improvement is nearly double when compared to neural network methods.

]]> 10.1504/IJHTM.2011.042369 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 379 - 389 S. Balambigai R. Asokan Department of ECE, Kongu Engineering College, Perundurai – 638052, Erode Dt., Tamil Nadu, India. ' Department of IT, Kongu Engineering College, Perundurai – 638052, Erode Dt., Tamil Nadu, India genetic algorithms GAs ECG signal extraction electrocardiograms SVD singular value decomposition eigenvalues signal to noise ratio PCA principal component analysis ICA independent component analysis cardiac disease heart disease neural networks. 2011-09-06T23:20:50-05:00 12 5/6 379 389 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42370 The work describes the effect of stress on voice parameters. The human voice is a difficult signal to analyse because it changes much over time and is complex in nature. The fundamental frequency is an important parameter of voice and is considered to be one of the most important features to characterise speech and speaker-specific patterns. Stress analysis and voice disease diagnostics essentially require the measurement and analysis of the fundamental frequency of human voice and after that we can take necessary steps for healthcare management. Stress effects on fundamental frequency of human voice: a review
Rakesh Kumar Garg, R.K. Sharma
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 390 - 404
The work describes the effect of stress on voice parameters. The human voice is a difficult signal to analyse because it changes much over time and is complex in nature. The fundamental frequency is an important parameter of voice and is considered to be one of the most important features to characterise speech and speaker-specific patterns. Stress analysis and voice disease diagnostics essentially require the measurement and analysis of the fundamental frequency of human voice and after that we can take necessary steps for healthcare management.

]]> 10.1504/IJHTM.2011.042370 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 390 - 404 Rakesh Kumar Garg R.K. Sharma Shri Krishan Institute of Engineering and Technology, Faculty of Electronics and Communication Engineering Department, Kurukshetra University, Kurukshetra 136118, India. ' National Institute of Technology, Faculty of Electronics and Communication Engineering Department, Deemed University, Kurukshetra 136118, India human voice stress analysis fundamental frequency vocal profile healthcare management speech speaker-specific patterns voice disease diagnostics. 2011-09-06T23:20:50-05:00 12 5/6 390 404 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42371 Microarray experiments produce enormous amounts of data, leading to new requirements and challenges in bioinformatics. One of the major challenges in the analysis of such data sets is to discover local structures composed by sets of genes that show coherent expression patterns across subsets of experimental conditions. These patterns may provide clues about the main biological processes associated with different physiological states. This proposed algorithm includes gene selection and extraction of biclusters from gene expression data using difference matrix. This improved algorithm extracts biclusters with maximum volume that may be left unidentified. Discovering maximal size coherent biclusters from gene expression data
J. Bagyamani, K. Thangavel
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 405 - 421
Microarray experiments produce enormous amounts of data, leading to new requirements and challenges in bioinformatics. One of the major challenges in the analysis of such data sets is to discover local structures composed by sets of genes that show coherent expression patterns across subsets of experimental conditions. These patterns may provide clues about the main biological processes associated with different physiological states. This proposed algorithm includes gene selection and extraction of biclusters from gene expression data using difference matrix. This improved algorithm extracts biclusters with maximum volume that may be left unidentified.

]]> 10.1504/IJHTM.2011.042371 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 405 - 421 J. Bagyamani K. Thangavel Department of Computer Science, Government Arts College, Dharmapuri 636 705, Tamil Nadu, India. ' Department of Computer Science, Periyar University, Salem 636 011, Tamil Nadu, India biclustering difference matrix gene expression data bioinformatics microarray data gene selection. 2011-09-06T23:20:50-05:00 12 5/6 405 421 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42372 We propose a distributed model of entire human arterial tree to describe the haemodynamic changes due to pressure applied on the brachial artery. The model (without baroreflex) parameters are positively correlated with measured parameters (maximum systolic slope r = 0.54; maximum diastolic slope r = 0.77; pulse height r = 0.89 when P < 0.05). We calculated correlation coefficient of all parameters with baroreflex system (for maximum systolic slope r = 0.97; for maximum diastolic slope r = 0.93; for pulse height r = 0.99 when P < 0.05). With baroreflex loop in the model, the experimental parameters are accurately predicted. Modelling the effects of upper arm cuff pressure on pulse morphology
L. Suganthi, S.V. Viswajith, M. Manivannan
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 422 - 433
We propose a distributed model of entire human arterial tree to describe the haemodynamic changes due to pressure applied on the brachial artery. The model (without baroreflex) parameters are positively correlated with measured parameters (maximum systolic slope r = 0.54; maximum diastolic slope r = 0.77; pulse height r = 0.89 when P < 0.05). We calculated correlation coefficient of all parameters with baroreflex system (for maximum systolic slope r = 0.97; for maximum diastolic slope r = 0.93; for pulse height r = 0.99 when P < 0.05). With baroreflex loop in the model, the experimental parameters are accurately predicted.

]]> 10.1504/IJHTM.2011.042372 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 422 - 433 L. Suganthi S.V. Viswajith M. Manivannan Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai 600 036, India. ' Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai 600 036, India. ' Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai 600 036, India haemodynamics Windkessel model baroreflex photoplethysmograph transmission line model maximum systolic slope peak-to-peak interval modelling upper arm cuff pressure pulse morphology human arterial tree brachial artery. 2011-09-06T23:20:50-05:00 12 5/6 422 433 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42373 Aim of this paper is to study the effect of Gastric Myoelectric Activity (GMA) in finger PPG signal. To this end, Pulse Rate Variability (PRV) analysis in combination with Poincare plots was selected. In PRV, the power of High Frequency (HF) component significantly changes in fasting and postprandial state and positively correlated between Power Ratio (PR) of PRV and electrogastrography (EGG) power (r = 0.46; P < 0.05). The results of this study explored that the combination of Poincare plots and PR value could show a new insight into the assessment of gastrointestinal system between different body conditions of a healthy group. Effect of gastric myoelectric activity on pulse rate variability in fasting and postprandial conditions
S. Mohamed Yacin, M. Manivannan, V. Srinivasa Chakravarthy
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 434 - 446
Aim of this paper is to study the effect of Gastric Myoelectric Activity (GMA) in finger PPG signal. To this end, Pulse Rate Variability (PRV) analysis in combination with Poincare plots was selected. In PRV, the power of High Frequency (HF) component significantly changes in fasting and postprandial state and positively correlated between Power Ratio (PR) of PRV and electrogastrography (EGG) power (r = 0.46; P < 0.05). The results of this study explored that the combination of Poincare plots and PR value could show a new insight into the assessment of gastrointestinal system between different body conditions of a healthy group.

]]> 10.1504/IJHTM.2011.042373 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 434 - 446 S. Mohamed Yacin M. Manivannan V. Srinivasa Chakravarthy Touch Lab, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai 600036, Tamil Nadu, India. ' Touch Lab, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai 600036, Tamil Nadu, India. ' Computational Neuroscience Lab, Department of Biotechnology, Indian Institute of Technology Madras, Chennai 600036, Tamil Nadu, India autonomic nervous system enteric nervous system haemodynamics EGG electrogastrography PSD power spectral density blood volume pulse power ratio gastric myoelectric activity pulse rate variability fasting postprandial conditions finger PPG signals photoplethysmography gastrointestinal system. 2011-09-06T23:20:50-05:00 12 5/6 434 446 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42374 Intravascular stents of various designs are currently in use to restore patency in atherosclerotic coronary arteries and it has been found that different stents have different in-stent restenosis rates. Computational studies are used to investigate the mechanical behaviour of stents by means of strength and temperature analysis. In this paper, we test the hypothesis that two different stent designs (S7 and Cypher). An analysis of the arterial wall stresses in the stented arteries indicates that the S7 (modular) stent design causes lower stress to an atherosclerotic vessel with a localised stenotic lesion compared to the Cypher stent design. Design and analysis of coronary stent
P. Ravikumar, E. Bharathiraja, V. Tharani, R. Yamuna, T. Yamunarani
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 447 - 456
Intravascular stents of various designs are currently in use to restore patency in atherosclerotic coronary arteries and it has been found that different stents have different in-stent restenosis rates. Computational studies are used to investigate the mechanical behaviour of stents by means of strength and temperature analysis. In this paper, we test the hypothesis that two different stent designs (S7 and Cypher). An analysis of the arterial wall stresses in the stented arteries indicates that the S7 (modular) stent design causes lower stress to an atherosclerotic vessel with a localised stenotic lesion compared to the Cypher stent design.

]]> 10.1504/IJHTM.2011.042374 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 447 - 456 P. Ravikumar E. Bharathiraja V. Tharani R. Yamuna T. Yamunarani Department of Biomedical Engineering, Velalar College of Engineering and Technology, Erode-12, Tamil Nadu, India. ' Department of Biomedical Engineering, Velalar College of Engineering and Technology, Erode-12, Tamil Nadu, India. ' Department of Biomedical Engineering, Velalar College of Engineering and Technology, Erode-12, Tamil Nadu, India. ' Department of Biomedical Engineering, Velalar College of Engineering and Technology, Erode-12, Tamil Nadu, India. ' Department of Biomedical Engineering, Velalar College of Engineering and Technology, Erode-12, Tamil Nadu, India coronary stent design coronary stent analysis vascular injury atherosclerosis Cypher stent ANSYS intravascular stents coronary arteries arterial wall stress FEM finite element method modelling. 2011-09-06T23:20:50-05:00 12 5/6 447 456 2011-09-06T23:20:50-05:00 http://www.inderscience.com/link.php?id=42375 Medical image fusion has been used to derive useful information from multi-modality medical image data. In this work, Support Value Transform (SVT) based medical image fusion approach is proposed for fusing multimodality medical images such as MRI and CT &amp; MRI and PET. This new image fusion method with mapped LS-SVM uses the support value to represent the salient features of the image. The results are compared with the Discrete Wavelet Transform (DWT) results of same data set. The resultant fused images are assessed and validated by radiologist. The Support Value Transform approach provides improved results as compared to DWT in terms of both qualitative and quantitative analysis. Support value transform-based multimodality medical image fusion
D. Selvathi, S. Thamarai Selvi
International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 457 - 470
Medical image fusion has been used to derive useful information from multi-modality medical image data. In this work, Support Value Transform (SVT) based medical image fusion approach is proposed for fusing multimodality medical images such as MRI and CT &amp; MRI and PET. This new image fusion method with mapped LS-SVM uses the support value to represent the salient features of the image. The results are compared with the Discrete Wavelet Transform (DWT) results of same data set. The resultant fused images are assessed and validated by radiologist. The Support Value Transform approach provides improved results as compared to DWT in terms of both qualitative and quantitative analysis.

]]> 10.1504/IJHTM.2011.042375 International Journal of Healthcare Technology and Management, Vol. 12, No. 5/6 (2011) pp. 457 - 470 D. Selvathi S. Thamarai Selvi Department of ECE, Mepco Schlenk Engineering College, Sivakasi 626 005, Tamil Nadu, India. ' Department of CSE, Anna University, MIT Campus, Chennai 600 044, Tamil Nadu, India medical imaging support value transform image fusion multimodality medical images. 2011-09-06T23:20:50-05:00 12 5/6 457 470 2011-09-06T23:20:50-05:00