International Journal of Reasoning-based Intelligent Systems (34 papers in press)
Multimedia-Aided English Online Translation Platform based on Bayesian Theorem
by Xinfei Wang
Abstract: In order to overcome the problems of the traditional online English translation platform, such as low translation efficiency, poor translation accuracy and small translation database capacity, a multimedia aided online English translation platform based on bayesian theorem is designed. The translation platform consists of display layer, permission control layer, logic control layer and data processing layer. This paper introduces bayes' theorem and calculates the probability of translation from English to Chinese. In the design of query module, the translation of search words and thesaurus is selected based on bayes' theorem, and the retrieval method is optimized. Sqlite management system is used to manage the vocabulary data in the vocabulary, so as to complete the design of multimedia assisted English online translation platform. Experimental results show that the translation accuracy of the platform designed in this paper fluctuates in the range of 86-95, and the translation time is always lower than 0.4s, indicating that the platform not only has high translation efficiency and accuracy, but also can complete the translation of large volume data.
Keywords: machine vision technology; multimedia; English; translation platform; platform construction;.
A Neuron based Active Queue Management Scheme for Internet Congestion Control
by Sukant Bisoy
Abstract: To deal with nonlinear and complex problems of Internet congestion control, an intelligent scheme is required, which can learn the traffic pattern of the network. In order to achieve quality of service (QoS) provisioning of real time service, active queue management (AQM) scheme in Internet router needs to stabilize the queue length. In this paper, we design a robust AQM scheme called neuron based AQM (N-AQM) to efficiently control the complex network congestion problem and achieve QoS. In N-AQM, a neural network is used to predict the future value of current queue length and estimate the differential queue length error and use it to define the packet drop probability. The parameters of neurons can be adjusted dynamically depending on the time-varying environment to stabilize the queue length and achieve robustness against different network parameters. Our simulation result demonstrates that N-AQM is stable, robust and outperforms other AQM schemes.
Keywords: AQM; Neuron; QoS; Stability; Robustness.
Special Issue on: CIM-19 Advances in Machine Learning and Intelligent Systems - Challenges and Solutions
Demographical Gender Prediction of Twitter Users using Big Data Analytics: An Application of Decision Marketing
by Sudipta Roy, Bhavya Patel, Debnath Bhattacharyya, Kushal Dhayal, Tai-Hoon Kim, Mamta Mittal
Abstract: The use and influence of digital media, particularly social media, have grown in every sphere of life. One of the trendiest social sites is Twitter. Twitter often contains conversation in non-standard language, and thus, it is difficult to analyze in real-time using conventional language processing. Twitter does not accumulate user gender information as do other popular social media platforms. Thus, demographic feature prediction and additional informative content are important for advertising, custom-made marketing and authorized investigation from the social medium. In this study, proposed statistical representation with real-time analysis using big-data technologies is able to predict the gender of Twitter users. Data cleaning, processing, and storage are performed by the big-data technology Apache Hive. Gender prediction is performed using the naive Bayes classifier to address systemic issues, and Apache Hive is used to solve data storage and big-data processing issues. Authors have considered the tweets-only scenario, the other scenario that was used predicts gender by combining the user tweets and the user profile description. To maintain the stability of the amount of training instances used per estimation, we initiate a balanced class formulation using the polynomial Naive Bayes. Another systemic and previously existing problem of features that was assumed to be independent is solved by the proposed method. The proposed customized method is a speedy, easy-to-implement with pre-processing, close to state-of-the-art document text categorization method using big-data technologies. The proposed statistical method produces higher accuracy in gender classification using tweets only and tweets with description compared with other gold-standard methods.
Keywords: Twitter; Naïve Bayes; Gender Classification; Apache Hive; Perceptron; Logistic Regression;.
Energy Efficient Task Scheduling using Adaptive PSO for Cloud Computing
by Rama Rani, Ritu Garg
Abstract: Cloud computing is an important research domain where all computational resources are networked globally and shared to users easily. The cloud service provider (CSP) wants an eco-friendly solution to resolve these issues. To enhance the performance of cloud computing resources, task scheduling is of prime concern. Further, the growth of cloud computing resources leads to a large amount of energy consumption and carbon footprints. Thus, this paper aims to reduce the makespan along with energy consumption for independent tasks. For this purpose, we proposed energy-efficient adaptive particle swarm optimization (EE-APSO) algorithm for independent tasks scheduling decision. Each particle represents a potential solution, and small position value (SPV) rule is used to change the continuous particle position vector to a discrete particle position vector. PSO is made adaptive by varying acceleration coefficients and inertia weight. We also introduced mutation operation to avoid the PSO algorithm getting stuck in local minima and explore the whole search space efficiently. Result analysis demonstrated that our proposed algorithm EE-APSO using SPV rule gives better results than min-min, max-min and genetic algorithm (GA) in terms of makespan and energy consumption.
Keywords: Cloud Computing; Independent task scheduling; Particle Swarm Optimization; Energy Consumption; Makespan.
NITCO: An Intelligent Agent Technique for Optimizing of Resource Utilization in Cloud
by HARVINDER SINGH CHAHAL, ANSHU BHASIN, PARAG RAVIKANT KAVERI
Abstract: Efficient task scheduling is significant to meet the quality of service (QoS) requirements in cloud computing. Cloud is a large pool of virtual access resources to perform thousands of computational and storage operations. Task Scheduling is an NP-hard problem, unsuitable matching leads to performance degradation and violation of service level agreement (SLA). The growing complexity of cloud services needs an extension of existing scheduling algorithms. In this paper, the scheduling problem has been explored based on growing application trends. Cloud dynamic resource provisioning can satisfy users requirements if execution of tasks performed: identifying of task requirements, workflow of application scheduling using a sufficient amount of resources. In this research work, we present an intelligent agent technique for optimizing resource utilization named NITCO. NITCO considers the above mentioned challenge, identification of task requirements and configuration of resource. The performance of proposed NITCO has been evaluated on simulated cloud environmen2016t, and comparison of results show that NITCO performed better in terms of execution cost, execution time, VM utilization and SLA violation while it delivers quality of service.
Keywords: Cloud Computing; Scheduling; Utilization; Energy-consumption; SLA.
Computing Semantic Relatedness by Latent Semantic Analysis and Fuzzy Formal Concept Analysis
by Shivani Jain, Seeja K.R, Rajni Jindal
Abstract: Measuring semantic similarity/semantic relatedness is an important task in Computational linguistic, Natural language processing and Ontology Creation. In this paper, a new hybrid method using LSA and FFCA is proposed for computing the semantic-relatedness. Latent semantic analysis (LSA) is used to extract the attributes of the concepts and these attributes are further mapped to FFCA to compute semantic relatedness. The latent semantic analysis is used for finding the neighboring words or attributes and their correlation value. The concepts and their attributes are mapped to FCA table and then to FFCA table by using the correlation value as membership. A Fuzzy similarity measure is then used to compute the semantic relatedness between these concepts/words. The proposed method is evaluated on word similarity bench mark datasetWS-353 and found an accuracy of 0.85.
Keywords: Semantic Relatedness; Semantic Similarity; LSA; Fuzzy formal concept analysis; fuzzy set similarity measure; Semantic Association;.
ADAPTIVE EDGE-BASED BI-CUBIC IMAGE INTERPOLATION
by C. John Moses, Selvathi D
Abstract: Image interpolation is a technique of creating new pixels by using old pixels. Nowadays image interpolation systems are widely used in many digital signal processing applications like reconstructing medical images and increasing the resolution of satellite and multimedia images. Bi-cubic interpolation is one of traditional and high-performance scheme as compared with other conventional interpolations like nearest neighbour and bilinear. However, the traditional interpolation produces image artifacts like jagging and blurring. To avoid these kinds of drawbacks, several adaptive bi-cubic schemes are introduced in the past decade. This work presents an edge-based adaptive bi-cubic image interpolation using clamp filter and sigmoidal edge detection technique. The clamp filter avoids aliasing artifacts and it smooths edge information by performing low-pass filtering. The experimental result shows that the proposed edge-based bi-cubic outperforms other related bi-cubic image interpolation schemes.
Keywords: Up-scaling; resolution; PSNR; clamp filter; convolution; SSIM; multimedia; bilinear; polynomial; convolution.
Deep Learning based Detection and Prediction of Trending Topics from Streaming Data
by AJEET R.A.M. PATHAK, Manjusha Pandey, Siddharth Rautaray
Abstract: Detecting and predicting trending topics from steaming social data has always been the point of active research area in business and research firms to take quick decisions, change marketing strategies and set new goals. Topic modeling is one of the excellent methods to analyse the contents from large collection of documents in an unsupervised manner and it is a popular method used in natural language processing, information retrieval, text processing and many other research domains. In this paper, deep learning based topic modeling technique has been proposed to detect and predict the trending topics from streaming data. The online version of latent semantic analysis with regularization constraints has been designed using long short-term memory network. Specifically, a problem of detecting the topics from streaming media is handled as the minimization of quadratic loss function constrained by ?1 and ?2 regularization. The online learning mechanism supports scalable topic modeling. For topic prediction, sequence-to-sequence long short-term memory network has been designed. Experimentally, significant results have been achieved in terms of query retrieval performance and topic relevance metrics for topic detection on our published dataset. For topic prediction, the results obtained in terms of root mean squared error are also significant.
Keywords: Deep learning; topic detection; topic prediction; social media data.
Special Issue on: ICCD-2018 Human-Computer Interaction
Generalized Linear Orthomorphisms
by Haiqing HAN, Siru Zhu, Yanqing Dai, Qili MAO, Qin Li, Kang SHI
Abstract: In this scientific research paper, the authors have generalized the concept with regard to orthomorphic permutations(called orthomorphisms) over the Galois field. Meanwhile we have gain the enumeration formula of the total generalised linear orthomorphic permutations over the Galois field, which possesses an arbitrary prime number as the characteristic of the prime subfield. So, the local creating algorithm with regard to partial generalised linear orthomorphic permutations over the Galois general fieldis realized. Comparatively speaking, the innovativeness and originality enumeration formula with regard to linear orthomorphisms over a Galois field with characteristic 2 is a special case to contain in our novel fruits over the general field. What is more, the generalised linear orthomorphic permutations have been thoroughly discussed and generated far
Keywords: P-permutation; Block Cipher; the Branch Number; Generalized Linear Orthomorphism.
Multi-Agent-Based Distributed Text Information Filtering Method
by Wuxue Jiang
Abstract: In order to improve the filtration efficiency and precision, and reduce the occupation of network resources in distributed text information filtering system, a kind of Multi-Agent-based text filtering method was designed. Directed by multi-Agent theory and technology, the system structure and working mechanism of distributed text information filtering are presented, which makes detailed design for scheduling responding agent and learning agent. The load balance was implemented by dynamic range adaptive load migration (DRALM). The experiment shows that this filtering method, boasting higher filtering performance, not only has higher filter precision, but processes tasks in many machines effectively balancing computing load.
Keywords: Multi-Agent System; Text Information Filtering; Distributed System; Open Computing Model; Dynamic Range Adaptive Strategy; Daemon.
Modified Jaya algorithm with chaos
by Mingjing Pei, Shuhao Yu, Maosheng Fu, Xukun Zuo
Abstract: Jaya algorithm is a recently developed optimization algorithm, which is a new optimization algorithm designed to solve optimization related problems, it has two random parameters in equations. In the study of this paper, we will introduce chaos into Jaya so as to increase non-repeatability and ergodicity for global optimization. Here, four different chaotic maps are utilized to control random parameters in Jaya. The results show that some chaotic maps can outperform the random parameters in the high dimensional function and the result of the two-dimensional function is almost the same.
Keywords: Jaya algorithm; Chaos; Global optimization.
Hedging Strategy for Commodity Futures Based on SVM-KNN
by Mei Sun, Rongpu Chen, Yulian Wen, Peiyao Nie
Abstract: In view of the problem of excessive exposure in the field of quantitative investment in commodity futures and policy failure in the low volatility market environment, a new quantitative investment strategy using SVM-KNN combined classifier to hedge multi-factor futures is proposed and applied to the management of quantitative fund. The quantitative investment strategy can not only reduce the overall systemic risk of the investment portfolio, but also adapt to the long-term environment of the commodity futures market. The retest data and the results of real trading show that the SVM-KNN based hedging strategy of commodity futures is significantly higher than the traditional CTA trend tracking strategy in the annual rate of return and the SHARP ratio, and the retracting of the cross period is greatly reduced.
Keywords: Quantitative Investment; Commodity Futures; Multifactor Hedging; Support Vector rn Machine; K-nearest Neighbors.
Special Issue on: ICICT2019 Emerging Technologies for the Internet of Things
Estimating Equations under IPW Imputation of Missing Data
by Hao WU, CuiCui LI, Chen Cheng
Abstract: The IPW imputation method is first applied t to compensate for nonresponse. And then, the empirical likelihood (EL) inference is made for estimation equation parameters. It is a nice result obtained in this paper that the limiting distributions of the EL statistics are 2-type distributions under the IPW imputation. Compared with the usual methods, the proposed method is easier to complement and more efficient.
Keywords: Empirical likelihood; equation estimation; missing data imputation; IPW (inverse probability weighted).
Design and Realization of Vehicle Security and Protection System Based on Multi-task Polling Processing
by Hai-ye Qiao
Abstract: As the increasing number of vehicles and more important role of the car in the daily life, the issue of security and protection of the vehicle has attracted more attention. Nowadays, the functions like location, monitor, anti-theft or the medium, low level vehicles are not popularized. Current existed systems have the problems of incomplete functions, unfriendly- user interface which cannot well fulfill the needs from users. This essay introduces the design of vehicle security and protection system based on C/S architecture. This system could realize the functions of remote monitoring, in-car phone call, fatigue driving monitoring, remote security, alarm call, ensuring the vehicle is under surveillance 24 hours a day, so to enhance the safety factor. This system is proved by the test for its stable running, uninterrupted transmission, user-friend interface and strong operability.
Keywords: Multi-task,Multithreading ,In-car Terminal; GPS; GPRS; C/S.
Research on key indicators and regional comparison of green data center
by Mei Zhang, Fei Feng, Zhi-long Zhang, Jing-hua Wen
Abstract: With the rapid development of information technology and the increasing number of information, green data centers are growing in size, and it is used more and more widely, so green index system of the green data center is the key problem to be solved urgently. This paper studied on the basic index system of green data center, with the help of PUE, CEI and TCO index analysis, it is made in depth analysis of the factors affecting the green index of the green data center, then using factor analysis method from the annual average temperature, annual precipitation, air quality index, seismic belt, information transmission enterprise fixed assets, the number of Internet users, power generation, the whole society and the Internet penetration rate of nine aspects, it is built the mathematical model for evaluating the operational advantages of green data center, finally it is finished that quantitative analysis and evaluation, and according to the calculation of the green data center development area comparison results.
Keywords: Green Data Center; Basic Index System; Green Index System; Regional Comparison; Advantage Evaluation Coefficient.
Special Issue on: Intelligent Information Technologies and Agriculture
Wireless sensor networks for smart agriculture
by Volodymyr Romanov, Igor Galelyuka, Oleksandr Voronenko
Abstract: Digital agriculture requires development and implementation of new information and communication technologies, including wireless ones for increasing efficiency. The authors developed wireless sensor networks, and wireless technology for express-diagnostics of plant state in agriculture, created the appropriate hardware, software and methodological support. The developed networks now are implemented and under field tests both in open agricultural lands and in smart greenhouses. In this paper the design and application of developed wireless sensor network and some results of calculations and modelling are given
Keywords: wireless sensor network; smart agriculture; Internet of Things.
Special Issue on: ICCD-2017 Internet of Things, Big Data and Machine Learning
Evaluation Research on Green Degree of Equipment Manufacturing Industry Based on Improved Particle Swarm Optimization Algorithm
by Zhang Li
Abstract: In order to improve the sustainable development of equipment manufacturing industry, the improved particle swarm algorithm is applied in evaluating green degree of equipment manufacturing industry. Firstly, the green degree evaluation system of equipment manufacturing industry is constructed, and evaluation index system is established. Secondly, the basic theory of particle swarm algorithm and the improved particle swarm algorithm are studied basing on analysis of disadvantages of traditional particle swarm algorithm. Thirdly, the analysis procedure of improved particle swarm algorithm is designed. Finally, equipment manufacturing industry in a province is used as a researching object, the green degree evaluation of equipment manufacturing industry in this province is carried out, and results show that this algorithm can improve evaluation level of green degree of equipment manufacturing industry.
Keywords: green degree; equipment manufacturing industry; improved particle swarm algorithm.
Network Security Situation Detection of Internet of Things for Smart City Based on Fuzzy Neural Network
by Qing Liu, Ming ZENG
Abstract: in order to ensure the safety of Internet of things for smart city and ensure normal operation of smart city, the network security situation of Internet of things should be monitored correctly for a long time, therefore the fuzzy neutral network with wavelet package and chaos particle swarm algorithm is applied it. Firstly, the basic theory of network security situation of Internet of things for smart city is analyzed, the corresponding mathematical is constructed, and the security situation awareness framework of Internet of things is designed. Secondly, the basic theory of fuzzy neutral network is studied, and the structure of the fuzzy neutral network is designed. Thirdly, the processing method of network security situation data based on wavelet package is constructed. And then training procedure of fuzzy neutral network based on chaos particle swarm algorithm is established, the algorithm procedure is designed. Finally, the simulation analysis is carried out using a smart city as example, and the network security situation of Internet of things for it is monitored correctly, then the network safety can be ensured.
Keywords: fuzzy neutral network; smart city; Internet of things; network security.
Special Issue on: ICEST'18 Intelligent Sensor Data Processing, Mobile Telecommunications and Air Traffic Control
Application Level Extension of Bandwidth Management in Radio Access Network
by Evelina Pencheva, Ivaylo Atanasov
Abstract: Multi-access Edge Computing (MEC) provides processing and storage capabilities of the cloud into the radio access network. In this paper, we study the deployment of bandwidth management service in MEC environment. The bandwidth management service procedures are mapped onto functionality of the control protocol between radio access network and core network. An extension of the bandwidth management service is proposed that enables detecting of packets generated of specific applications and applying the appropriate enforcement actions. The proposed extension is described by typical use cases, information flows, required information, data model, as well as respective application programming interfaces. Models representing the status of bandwidth allocation as seen by the mobile edge application and network are proposed, formally described and verified. Formal model verification enables mathematical demonstration that the proposed extension is consistently implementable.
Keywords: Quality of service control; Bandwidth management; Application detection and control; Radio access network; Multi-access Edge Computing; Application Programming Interfaces; Data model; Finite state machines.
Flight Safety Sensor and Auto-Landing System of Unmanned Aerial System
by Krume Andreev, Georgi Stanchev
Abstract: Over the past decade, there has been a rapid development of Unmanned Aerial Systems (UAS). The trend and current developments lead to an increase in the use of UAS. The operations of UAS and their use significantly increase every day. This article provides solutions and options for introducing a flight safety sensor system and auto-landing system for UAS. The reason is to ensure effective completion of their mission without the involvement of a qualified operator (pilot) in the control station. The problems and characteristics of these systems and the algorithms through which they successfully perform their tasks are analyzed in the article. In the article has been proposed an architectural realization of a flight safety sensor system and an auto- landing system for UAS.
Keywords: Flight Safety; Sensor System; Technical Condition; Auto-Landing System; Unmanned Aerial System; Conical Scanning; Pseudo-Conical Scanning.
Performance of VWM algorithm in the presence of impulse noise and resizing
by Bojan Prlincevic, Zoran Milivojevic, Stefan Panic
Abstract: The first part of this paper describes VWM (Visible Watermarking) algorithm for inserting and removing visible watermark in the image. The second part of this paper describes an experiment in which the image is watermarked with the VWM algorithm,impulse noise is added, and the image quality is improved with the MDB algorithm for filtering. Watermark is removed from noised andfiltered image. Afterwards, an experiment is described in which resizing of the noised watermarked image is performed. Watermark is removed from this image. Finally, a comparative analysis of the results is performed in order to evaluate the efficiency of the applied algorithms. The comparison was performed on the basis of MSE and Similarity. The obtained results are analysed in detail and presented in a tabular and graphical manner.
Keywords: Visible watermark; Impulsive noise; Filtering; Resizing;.
Design and optimization of bio-inspired robotic stochastic search strategy
by Farhad Maroofkhani
Abstract: An autonomous robots search strategy is the set of rules that it employs while looking for targets in its environment. Biological systems (e.g., foraging animals) provide useful inspirations for designing optimal stochastic search algorithms for autonomous robots. Due to the complexity of interaction between the robot and its environment, optimization must performed in high-dimensional parameter space. We analyze the dependence of search efficiency on environmental parameters and robot characteristics using Response Surface Methodology (RSM), a technique originally developed for experimental design. In this study, the efficiency of a strategy focuses on L
Keywords: Levy walk; Autonomous robots; Swarm robot; Biomimetic; Individual motion; Design of experiments.
Influence of optimal pair-wise SUS algorithm on MU-MIMO-OFDM system performance
by Aleksandra Panajotovic, Nikola Sekulovic, Daniela Milovic
Abstract: In this paper we proposed a new user scheduling algorithm, named as optimal pair-wise semi-orthogonal user selection (SUS), for multiuser multiple-input multiple-output orthogonal frequency division multiplexing (MU-MIMO-OFDM) system. Multiuser interferences are canceled applying zero-forcing beamforming (ZFBF) technique with presumption that channel state is perfectly known at transmit side. Simulated throughput and error results demonstrate advantage gain achieved in system performance realized through applying the proposed scheduling algorithm.
Keywords: FLA; IEEE 802.11ac; MU-MIMO-OFDM; User Scheduling Algorithm; ZFBF.
The effect of background and outlier subtraction on the structural entropy of two-dimensional measured data
by Szilvia Nagy, Brigitta Sziova, Levente Solecki
Abstract: For colonoscopy images the main information is in the fine structure of the surface of the bowel or colorectal polyps, similarly to the case of combustion engine cylinder surface scans, where the grooving and wear can be detected from the fine pattern superposed to a cylinder curvature.
In both cases appear outliers, colonoscopy images have many reflections, whereas the roughness scanners detect small dust particles as well as the micron scale vibrations from the environment.
The method presented in this paper takes care of both the problems using histogram stretching together with a special type of filtering. Also, masks are introduced in order to control the effect of the operators.
The effects of the processing steps on the structural entropy of the image is also studied, as structural entropies are used in characterization of the images. By removing the background makes the structural entropies much smaller, and by suppressing the outliers the structural entropies increase.
Keywords: Image preprocessing; Rényi entropy; structural entropy; colonoscopy; microgeometrical surface.
A Fuzzy Decision Maker to Determine Optimal Starting Time of Shiftable Loads in the Smart Grids
by İsmail Hakkı Altaş, Recep Çakmak
Abstract: Smart grid studies have been increased tremendously for past ten years in order to modernize and solve problems of current electrical grids. One of the aim of the smart grids is to react autonomously to the problems in electrical networks by means of artificial intelligence and decision maker. Fuzzy logic based embedded control systems simulate human thoughts and decision making processes. So, fuzzy logic and fuzzy decision makers can be utilized in smart grids for automated system management. In this paper, a fuzzy decision maker has been proposed to manage time-shiftable loads in residences. The proposed fuzzy decision maker determines optimal starting time of time-shiftable loads in residential areas in order to provide balanced power curve and decrease peak load consumptions by scheduling the loads. Design stage of the proposed fuzzy decision maker have been introduced and presented clearly. Finally, a design example has been given to show the decision results.
Keywords: Fuzzy Logic; Fuzzy Decision Maker; Demand Side Management; Load Scheduling; Smart Grids.
Special Issue on: ICICT2018 Advances in Intelligent Information Communication Technologies
Onboard Reasoning and Other Applications of the Logic-Based Approach to the Moving Objects Intelligent Control
by Andrey Tyugashev
Abstract: This article provides the theoretical background and practical case studies of the application of reasoning and other logic-based approaches to the moving objects control. Modern moving objects, both manned and unmanned, utilize computers as their onboard brain. Since planes, spacecraft, cars, trucks and trains must demonstrate flexible and safe behavior in various situations, it seems prospective to use intelligent control means instead of rigid control logic dispersed in a program source code. This article is concerned with the possible implementation of onboard intelligence. In contrast to the popular use of neural networks, the logic-based approach is based on clear and exact control rules with strict responsibility. Thus, formal specification and verification methods can be utilized. The article describes the Real-Time Control Algorithm Logic (RTCAL) for the above-mentioned purposes. We also present case studies of reasoning at the design and operation stages for providing the fault tolerant control of a spacecraft.
Keywords: Moving objects control; logic; intelligent control; reasoning; Real-Time Control Algorithm; flight control software.
Multi-Criteria Clustering-based Recommendation using Mahalanobis distance
by Mohammed Wasid, Rashid Ali
Abstract: There have been significant advances made in the research of recommender systems over the past decades and have been implemented in both industry and academia. Recently, multi-criteria ratings are being incorporated into traditional recommender systems to further improve their quality, especially to handle the data sparsity and cold start issues. However, incorporation of multi-criteria ratings have improved the performance of the recommendation, but at the same time, multidimensionality issue is also arises. This paper presents a clustering based recommendation approach which is used for dealing with the multi-dimensionality issue in multi-criteria recommender systems. Here, we cluster the users based on their individual criteria ratings using K-means cluster-ing and the intra-cluster similarity is computed using Mahalanobis distance measure for neighborhood set gen-eration. This improves the recommendations quality and predictive accuracy of both traditional and clustering-based collaborative recommendations. The Yahoo! Movies dataset was used for testing the approach and the experiment conducted shows promising results.
Keywords: Recommender systems; RS; Collaborative filtering; CF; Mahalanobis distance; MD; K-Means clustering; Multi-criteria.
Fast Algorithm of Image Enhancement based on Multi-Scale Retinex
by Alexander Zotin
Abstract: In this paper, a fast image enhancement algorithm based on Multi-Scale Retinex in HSV color model is presented. The proposed algorithm produces the result similar to the one which uses a nonlinear processing in the HSV color model, but with less computational cost. It uses linear dependencies of RGB colors from the V-component of HSV model. Additionally, to speed up the images processing and enhance the local contrast is suggested to perform Multi-Scale Retinex (MSR) computation only in the low-frequency area obtained by the wavelet transform. Experimental research was performed on more than 100 color images having non-uniform brightness. Different algorithms based on Retinex technology were implemented and their performance was compared. The proposed way of output image color formation allows to reduce processing time by 30-75%, depending on the image size. The experimental data show that the usage of the wavelet transform in proposed MSR algorithm additionally leads to 2-2.8 times increase in processing speed.
Keywords: Color image enhancement; Retinex; MSR; Multi-Scale Retinex; Color space; HSV; Wavelet transform;.
Exchanging Deep knowledge for fault diagnosis using ontologies
by Xilang Tang, Mingqing Xiao, Bin Hu, Dongqing Pan
Abstract: To improve the development efficiency of automated diagnosis equipment (ADE) and ensure the generality of ADE software, this paper proposes a novel method to exchange deep knowledge of systems under diagnosis (SUD) using ontologies. A general framework of knowledge base combining test information model and diagnosis information model is proposed. The diagnosis information model is decomposed into structure model and function model. The structure model describes the connectivity of adjacent components as well as the structural hierarchy, and the function model describes behavior of modules by mapping input signals into output signals. Moreover, the method to locate the fault based on the proposed knowledge base is introduced. Finally, a case study for guiding system of passive-radar guidance missile is carried out to illustrate our proposed method. The practice shows that our method can achieve the object well
Keywords: fault diagnosis; test; knowledge; ontology; reasoning.
Multistage approach for automatic spleen segmentation in MRI sequences
by Antonia Mihaylova, Veska Georgieva, Plamen Petrov
Abstract: Most of the known methods of segmentation of the abdominal organs are not automated for the whole series of images or are semi-automatic and require additional intervention by the user. This is typical for cases where the difference in intensity of the gray level between the subject and the background is small. A typical example of this is the spleen and adjacent tissue in unconstrained MR images. This paper presents a multistage approach for spleen segmentation from MRI-sequences. It is based on segmentation methods such as active contours without edges and k-mean clustering. The proposed approach consists of some basic stages. The first stage is pre-processing, based on image enhancement and morphological operation. Two atlas models are created, which are used in the initial image to define the initial contour at which the segmentation begins. The initial image is semi-automatic segmented using the created atlas models. The sequence is then automatic segmented, dividing it in two parts (before and after the initial middle image) and using the segmentation of the previous image. The proposed approach allows extracting the spleen in the different depth images, which has a variable form and unstable position. The conducted experiments are showing the robustness of the proposed approach. The obtained results demonstrate the effectiveness of the approach for application in screening diagnostics.
Keywords: Segmentation of Spleen; Segmentation of MRI sequences; Automatic Segmentation.
Classification of Radar Non-Homogenous Clutter Based on Statistical Features Using Neural Network
by Thamir Saeed, Ghufran Hatem, Jafar Abdul Sadah
Abstract: This paper presents a robust clutter classifier based on the neural network to assist the radar receiver by choosing optimal constant false alarm rate. Where this classifier has been trained for sixteen class, four radar return distribution with different situations. The return radar signal distributions are Rayleigh, Weibull, lognormal and K- distribution, while the situations are, Signal, Multi-, Closed Multi-target, and clutter edge. Multi-layer perceptron with back-propagation as a neural network with seven features, Mean, Variance, Mode, Kurtosis, Skewness, Median, and Entropy, have been used to classify the return signal. A Least mean square error is used to evaluate the classifier performance. The simulation is evaluated for the Signal to clutter ration from +35dB to -35 dB, with 5-20 neurons of the hidden layer, and 60-360 samples. By performing, the Optimization has been gained by using 240 samples and 20 neurons then lead to 98.1 % return signal classification
Keywords: Clutter Classifier; CFAR; Radar; and Non-homogenous clutter; statistical Features.
Development of a sit-to-stand assistance chair for elderly people
by Ari Aharari, Won-Seok Yang
Abstract: According to the survey on the actual situation of elderly persons at home or nursing home care, the first item after concerning about disease under treatment is Weak legs and difficulties to stand from the chair. Muscle strength further decreases with aging and make feeling burden when standing from chair. Also, people who are suffering from secondary symptoms such as bedsores and keep sitting in a chair for a long time are on the rise. The most burdensome for elderly persons when trying to stand up from the chair is to bear the weight themselves. In this paper, we introduce Rakutateru which is specially designed to support elderly persons to easily stand up from the chair and keep people to more active and independent. We also evaluate the validity of an assist unit which is contained inside the lower part of the Rakutateru surface.
Keywords: Assist chair; Elderly support chair; Lifting unit.
Special Issue on: CIM-19 Advances in Machine Learning and Intelligent Systems - Challenges and Solutions
A NOVEL APPROACH FOR DYNAMIC INFORMATION INTEGRATION
by Vikash Kumar Garg, Ashish Oberoi, Manish Arora
Abstract: With tremendous growth of data, in recent past, NoSQL databases have emerged and become the popular choices amongst top companies. Scalability can be easily achieved with these databases which is suitable for big companies working with streaming or social data. But the consistency offered by these databases have always remained a concern for companies working with crucial and specially financial transactional data. Moreover the entirely new architecture and new set of query language makes it more expensive and tedious to migrate the existing architecture on this new platform. The proposed architecture in this paper tries to eliminate these business issues by implementing the powers of NoSQL databases using the traditional RDBMS model. With this proposed architecture, the query language remains the same, the ACID properties can be maintained where required and more scalability and reliability can be achieved.
Utilizing Predictive Analytics for Decision Making and improving healthcare services in Public Maternal Healthcare Database
by Shelly Gupta, Shailendra Singh, Parsid Jain
Abstract: Abstract: Background: Predictive analytics is the advanced analytics which is used to make predictions about the unknown future events. In public healthcare datasets, predictive analytics helps to improve the healthcare quality by supporting the healthcare planners in decision making. Hence it is an ongoing research in the field of public healthcare data, especially with the increase in the electronic public healthcare datasets. In this paper the predictive analytics enabled results on public maternal health data (2015-16) of Uttar Pradesh state of India are discussed for enhancing the quality in public maternal healthcare to sustain nation women health. Methodology: In this study a process model based on KDD (Knowledge Discovery in Data) process is presented for predictive analysis in public maternal healthcare data of Uttar Pradesh, state of India. The supervised learning based predictive methods i.e. C4.5, MLP and kNN are used for predictive model building. The dataset is divided in the three major categories i.e. Pregnancy registration and ANC receipt, Deliveries at Home and Medical Facility Availability to achieve the mentioned objectives. Results: The classifier results are compared using the accuracy and error rate matrices of classification. It is found that C4.5 has outperformed over the other two benchmark classifiers. Discussion: In the first category of ANC (Antenatal Care) registration and receipt attributes it is found that the districts with higher percentage of live births rate having weight less than 2.5 kg is an important parameter to be included during NPDs (Non-priority Districts) and PDs (Priority Districts) distribution. Our predictive analysis on deliveries at home category of attributes leads us to know that the PNC (Post Natal Care) checkups within 48 hours percentage are high when deliveries at home are taken under trained SBA (Skilled Birth Attendant). So, this indicates that more effort is needed towards the awareness of the deliveries to be done under trained SBA. In the third category of medical facility availability, it is analyzed that the impact of SCs (Sub-Centres) availability is less to identify priority and non priority districts. Ideally SCs are those care units which have great role in providing the awareness towards health.
Keywords: Predictive Analytics; Public Maternal Health; Machine Learning; ROC (Receiver Operating Characteristic) curve.