		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
October 2016 | Vol. 92 No.1

Title:	ENSEMBLE SELECTION AND OPTIMIZATION BASED ON SOFT SET THEORY FOR CUSTOMER CHURN CLASSIFICATION
Author:	MOHD KHALID AWANG, MOKHAIRI MAKHTAR, M NORDIN A RAHMAN, MUSTAFA MAT DERIS
Abstract:	Ensemble methods or multiple classifiers which combine decisions from many base classifiers have been confirmed to outperform the classification performance of any single classifiers. Despite having the ability of producing the highest classification accuracy, ensemble methods have suffered significantly from their large volume of base classifiers. Thus, in the previous work, we have proposed a novel soft set based method to prune the base classifiers from heterogeneous ensemble committee and have demonstrated the ability of our proposed soft set pruning algorithm in reducing a substantial number of classifiers while at the same time producing the highest prediction accuracy. However, the pruning method only suggests a subset of relevant classifiers, and the search for the optimized and best classifiers is not yet considered. The selection of the best or optimized classifiers is carried out by checking all combinations of pruned classifiers. In this paper, we extended our research by proposing a new soft ensemble selection and optimization method to find the best subset of the pruned classifiers. The results of this work have proven that our proposed method is able to search for the minimum number of classifiers in the ensemble repository while at the same time maintaining or improving the classification performance. The proposed method is systematically evaluated using Customer Churn dataset taken from the UC Irvine Machine Learning Repository data set. This work proved that the proposed soft ensemble selection and optimization method is able to search for the minimum number of classifiers in the ensemble repository while at the same time improving the classification performance.
Keywords:	Ensemble Selection, Customer Churn Prediction, Ensemble Optimization, Soft Set, Ensemble Methods
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	REGION BASED IMAGE RETRIEVAL BASED ON TEXTURE FEATURES
Author:	ABD RASID MAMAT, FATMA SUSILAWATI MOHAMED, NORKHAIRANI ABDUL RAWI, MOHD KHALID AWANG, MOHD.ISA AWANG, MOHD FADZIL ABDUL KADIR
Abstract:	Most of Content Based Image Retrieval (CBIR) system use global texture features for representing and retrieving images. If local texture features are ignored during the initial stage of image processing, the performance will be affected. Meanwhile the features extraction, if it is based on Color co-occurrence Matrix (CCM) will provide the opportunities effective CBIR. Therefore, the main objective of this paper avoids the performance ineffectiveness and the same time opting for much effective CBIR. The problems that were highlighted will be tacked by considering the approach that is based on the local Haralicks texture features, specifically using Average Analysis (AA) and Principal Component Analysis (PCA) methods. The extraction by Haralicks texture feature was based on the predetermined CCM. The experimentation was done on the suggested ten categories of 1000 selected images from the Coral image database. The results portray, it is interesting to note that for certain image categories, only six features of the eleven Haralicks texture features namely homogeneity, sum of squares and sum average, sum variance, difference entropy and information measure correlation I and known as significant’ features provided the best image retrieval. The performance has increased in the range of 8.5% to 26.0%, compared with the previous researches. It is also indicated that the Average Analysis (AA)s combined significant features have achieved better performance than the Principal Component Analysis (PCA) in most categories. This finding has important implication on the use of correct significant features from Haralick texture features for certain image properties as well as leading to less computational processing time due to less.
Keywords:	Color Co-Occurrence Matrix, Haralick Texture Features, Significant Features, Spatial Relationship.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	A FRAMEWORK FOR DESIGNING MOBILE QURANIC MEMORIZATION TOOL USING MULTIMEDIA INTERACTIVE LEARNING METHOD FOR CHILDREN
Author:	SYADIAH NOR WAN SHAMSUDDIN, NURUL FARIHAH ABU BAKAR, MOKHAIRI MAKHTAR, MOKHAIRI MAKHTAR, WAN MALINI WAN ISA, AZILAWATI ROZAIMEE, RHAFIZI YUSOF
Abstract:	Quran is the fundamental holy book of Islam. Among the most important concerns is to learn it by heart. However, current method in Quranic schools is becoming less effective towards young generation. Thus, there is a need to find alternative solutions to memorize Quran for young Muslims. Mobile learning is an alternative to conventional learning that will support the existing method. Mobile devices have made an immediate impact on teaching and learning practices. However, for mobile learning to be effective for children in memorizing Quran, it is necessary to find specific design guidelines and pedagogy to this learning method. This paper aims at providing a unifying framework for developing Quran memorizer application using multimedia interactive method and learning theories for mobile learning.
Keywords:	Quran Memorization, Mobile Learning, Game-Based Learning, Rote Learning, Chunking.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	AGILE TESTING PRACTICES IN SOFTWARE QUALITY: STATE OF THE ART REVIEW
Author:	CESAR GIL, JORGE DIAZ, MARIO OROZCO, ALEXIS DE LA HOZ, EDUARDO DE LA HOZ, ROBERTO MORALES
Abstract:	In this paper you can find a review of articles related to agile testing practices in software quality, looking for theoretical information and real cases applied to testing inside a modern context, comparing them with the standard procedures taking into account their advantages and relevant features. As final result, we determine that agile practices in software quality have wide acceptance and many companies have chosen their use for all their benefits and impact on development software processes in several real applications, not necessarily IT governance ones, since other kind of technical applications have shown excellent results on testing.
Keywords:	Agile testing software, Scrum agile testing software, Kanban agile testing software, Test Driven Development agile test software, Behavior Driven Development test software, automation test software
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	ENABLING SECURE DATA TRANSACTION IN BIO MEDICAL ENGINEERING USING CCART APPROACH
Author:	A. VELMURUGAN , T. RAVI
Abstract:	Biomedical engineering, application is growing day by day. Major work carried by it is to manufacture the medical equipment based on the data of patient produced by professionals. The issue faced is the privacy and confidentiality of patient details that are transferred from professionals. In addition, other important factor is to retrieve the data from the database is other challenging process. This paper considers these issues and proposes a method by transacting the data with security in order to provide privacy. CART approach is implemented to retrieve the required data from the database in an efficient way. It works by searching the content in tree structure which saves the searching time and classification supports effective data (required) from such a huge database. This overcomes the misprocessing of data that are done by manual it leads to loss in time and cost for manufacturing the equipment. The proposed work retrieves the exact data in effective and efficient manner.
Keywords:	Data transaction, privacy, CART, Security and confidentiality.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	PARAMETER ESTIMATION OF GEOGRAPHICALLY WEIGHTED MULTIVARIATE t REGRESSION MODEL
Author:	HARMI SUGIARTI, PURHADI, SUTIKNO, SANTI WULAN PURNAMI
Abstract:	The use of ordinary linear regression model in spatial heterogeneity data often does not suitable within the data points, especially the relationship between response variable and explanatory variables. Therefore, the geographically weighted t regression (GWtR) is used to overcome spatial heterogeneity term. The model is an extension of geographically weighted regression (GWR) which the response variable follows multivariate t distribution. The aim of this study is to obtain the estimator of geographically weighted multivariate t regression (GWMtR) model with known degrees of freedom. The maximum likelihood estimation (MLE) method will be applied to maximize a weighted logarithm likelihood function. Based on the EM algorithm, the estimator of geographically weighted multivariate t regression model can be determined.
Keywords:	Maximum Likelihood Estimation (MLE), EM Algorithm, Geographically Weigted Regression, Multivariate t Model
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	SELECTION SYSTEM OF THE BOARDING HOUSE BASED ON FUZZY MULTI ATTRIBUTE DECISION MAKING METHOD
Author:	DEVIE ROSA ANAMISA, AERI RACHMAD, RULLY WIDIASTUTIK
Abstract:	Boarding house is a residence that is temporary and in the form of blocks of rooms in various sizes which are inhabited by students and employees from outside the area. There is a way of selecting the best boarding house which is influenced by several criteria, such as the rental price, amenities, number of rooms and other criteria such as distance to the destination, the location and the time limit on a visit. The number of criteria can easily select the best boarding based on criteria. However, little information on the boarding house has the shortest distance to the destination, this causes problems in choosing a boarding location so that it takes a decision support system for selecting a boarding locations based on considerations. Some of the solutions to solve the problem of selecting a boarding house have not been done. Hopefully it can provide a satisfactory success which has not been achieved. Therefore, this research makes a decision support system to solve the problem of selecting boarding house based on the criteria that have been determined using the method of Fuzzy Multi Attribute Decision Making (FMADM) to generate the best alternative boarding house and know the criteria which became the characteristics and behavior of those searchers boarding houses which have most domination and influence the decision of the boarding searcher to select a boarding house. The selection process for some alternatives on FMADM needs to determine the criteria early in the process as a reference for decision making, while the method of Weighted Product (WP) is used to normalize weight value that indicates the level of importance of each criteria. This research has five levels such as very low, low, moderate, high, very high. Various experiments were conducted to determine the criteria of FMADM method (such as location, district, village, gender of boarding house, minimum price and maximum price) as well as to obtain the best alternative from the boarding house. Experimental results showed that FMADM methods that have been developed in this study were able to solve the problem selecting the best boarding house from the highest alternative to alternate the lowest characteristics behavioral of home seekers the most superior in the selection of boarding houses, such as the criteria of the water conditions, the price of boarding houses, facilities, and the distance from the boarding house to the destination. Success rate of 100 respondents from 18 types of criteria were tested using the data in Sukolilo area, Surabaya City.
Keywords:	Descision Support System, Boarding House, Method, Fuzzy Multi Attribute Decision Making, Weighted Product.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	VARIATIONAL METHODS OF SYNTHESIS OF SIGNALS BASED ON THE FREQUENCY OF IDEAS
Author:	EVGENIY G. ZHILYAKOV, SERGEY P. BELOV, ANDREI A. CHERNOMORETS, VLADIMIR V. KRASILNIKOV
Abstract:	The article considers the constructing a function of time, which must have a priori given properties. In radio communications and communications main attention is usually given to the frequency distribution of signal energy, wherein the signals are synthesized either on the basis of predetermined reference values at discrete time points (interpolation or estimation of a derivative) or on the requirements to achieve maximum energy concentration of the synthesized signal in a predetermined low frequency band. As part of this work it was developed a new method of synthesis of signals with use of reference values, in which the construction of interpolating function is done based on the integrating of the evaluation of a derivative , calculated using the variational principle to minimization of its energy in a limited frequency range, that is defined by the sampling rate. In addition to that we got relationships describing a discrete signal of finite duration with a guaranteed share of power leakage outside the specified frequency bandwidth.
Keywords:	Variational Principles Synthesis Of The Signal On The Base Of Frequency Representations, Optimal Subband Frequency Synthesis.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	INTEGRATION OF SCIENTIFIC EXPERIMENTAL DATA THROUGH ONTOLOGY APPROACH: A REVIEW
Author:	NUR ADILA AZRAM, RODZIAH ATAN
Abstract:	Data integration in scientific experiments is important to the scientists in many research domains. This is because many experimental data involved multidiscipline areas and run in different machines or instruments which results in data stored in different ends and human intervention is required in forming a chain of data analysis. Ontology is one of the approaches that have been used in data integration in many domain areas. This paper described and reviewed ontology in data integration effort. Furthermore, the state of research for ontology-based integration of scientific experiment data also covered in this paper.
Keywords:	Data Integration, Ontology, Scientific Experiment, Scientific Research Data And Ontology-Based Data Integration
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	VERIFICATION ON THE TRUSTWORTHINESS OF INFORMATION: A STUDY
Author:	MOHAMAD NAZRI KHAIRUDDIN YAP, MASSILA KAMALRUDIN, AHMAD ZAKI A BAKAR, SAFIAH SIDEK
Abstract:	The pervasive use of social media has generated massive information sharing among its users. Given the fluidity and excessive information available online, issues relating to the trustworthiness of information have become a concern among the users and authorities. Sensational and unreliable information shared in the social media may cause and harm the reputation of an individual, product, organisation or government. Therefore, there is a need to develop a mechanism that helps users to verify the trustworthiness of information that feed in the social media so that they can decide whether to trust or to ignore the information. This paper reports a review on the analysis of the existing work related to trustworthiness of information. The analysis were based on three questions that address the definition of trustworthiness of information, factors influencing trustworthiness of information and existing tools to verify trustworthiness of information. Based on thirty nine selected articles reviewed, it was found that the verification on the trustworthiness of information approach is required. It is anticipated that the adoption of this approach will help to educate and make the public users aware of the level of trustworthiness of information, hence developing an informed, safe and ethical users of media content.
Keywords:	Information Trustworthiness, Factors, Social Media, Tools, Approaches
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	INTEGRATION OF MEDICAL SIMULATION EQUIPMENT INTO UNIFIED DATA SYSTEM
Author:	ANDREY ALEKSEEVICH SVISTUNOV, DENIS MIHAYLOVICH GRIBKOV, SERGEY SERGEEVICH SMIRNOV, DMITRII ALEKSANDROVICH SYTNIK, ALEKSANDR LVOVICH KOLYSH
Abstract:	At present there are no unified standards, regulations, protocols of data transfer from medical simulators by various manufacturers. This prevents development and improvement of automation systems of simulation training. This work is aimed at development of software which will provide merging of medical simulators and training devices by various manufacturers into unified data system. This target is based on developed and documented binary data format, where data are presented in the form of coupled key/value pair. On the basis of the developed binary data format the structure of data package has been developed as well as command list for interaction between client and server applications. Using the developed data format and TCP/IP proprietary data exchange protocol has been developed. As an alternative, the data exchange protocol on the basis of JSON format has been developed. The developed client and server applications facilitate data exchange between software of medical simulation equipment and designed data system. The developed software has been tested on the following medical simulators and training devices: Resusci Anne (Laerdal), Lap-X (Epona), and Lap Mentor (Simbionix). In the future it is planned to expand possibilities of the data system and to connect new simulators and training devices to this system. The protocol and software, developed in this work, make it possible to combine data from various medical simulators in the frame of unified data system in real time. The obtained results facilitate automation of training processes on the basis of medical simulators.
Keywords:	Simulator, Simulation Training, Medical Training Device, Data Base, Software, Data System
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	FACTORS AFFECTING GLOBAL VIRTUAL TEAMS’ PERFORMANCE IN SOFTWARE PROJECTS
Author:	ALI YAHYA GHENI, YUSMADI YAH JUSOH, MARZANAH A. JABAR, NORHAYATI MOHD ALI
Abstract:	Today the trend is to perform software development work via distributed geographical area among team, individual or even as an organization. However, due to the global market and international presence of many companies, there is a need to implement a global virtual teams. The global virtual team members are gradually engaged in globalized business environments across space, time and organizational boundaries via information and communication technologies. A global virtual team relies on communication, collaboration, and information exchange are the most important criteria in global virtual teams’ operations. The purpose of this paper is to answer two research questions. The first research question is to identify the factors affecting global virtual teams’ performance. A systematic literature review was conducted to answer the first research question. The second research question is on what the rank of the factor affecting the global virtual teams’ performance according to their level of effect on global virtual teams’ performance. Online survey was conducted within 103 developers and IT managers from eight IT companies to answer the second research question. The Statistical Package for Social Science (SPSS 22) was used to analyze the collected data. In this study, we investigated factors that affect global virtual teams’ performance; factors considered include cultural differences, language problems, time-zone differences, team size, technical problems, lack of trust, lack of sufficient training, and ICT problems. Also the findings indicated that lack of sufficient training is the highest level of effect on global virtual teams’ performance. On the other hand, team size is the lowest level of effect on global virtual teams’ performance.
Keywords:	Global software projects, Global Virtual Teams (GVTs), performance factors
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	CERTIFICATE MECHANISM IMPROVEMENT FOR SECURING OPTIMIZED LINK STATE ROUTING PROTOCOL IN MOBILE AD HOC NETWORKS
Author:	ALAA ABDULLAH MAJHOOL, NOR EFFENDY OTHMAN
Abstract:	Mobile Ad Hoc Network (MANET) comprises a set of wireless mobile nodes which dynamically generate a temporary network devoid of application of any present network infrastructure and centralized administration. Basically, Optimized Link State Routing (OLSR) is a security problem emanating from attacks. When handling packet forwarding, several types of availability as well as integrity attacks exist, including fabrication, modification, misrouting and dropping whether full or partial. This research utilizes the Secure Optimized Link State Routing (OLSR mechanism which includes certificate authorized nodes (CAs) and RSA algorithm to enhance the security and provide secure routing for OLSR routing protocol, through detection of malicious nodes that perform black hole attack. The proposed protocol is called (SOLS) mechanism. The aim of using the RSA algorithm with certificate authorized nodes (CAs) is to find the secure path from the source to the destination and to detect the black hole attack. We have evaluated the performance of SOLS mechanism by designing simulation using MATLAB. We have compared our mechanism with the performance of protocol OLSR and Baadachi’s approach. The comparison was conducted based on the detection ratio, packet delivery ratio, routing overhead, total network load, average delay and source traffic sent & destination traffic received. The SOLS outperformed the Baadachi’s approach under wide network performance metrics and settings. The SOLS improved the detection ratio by 4% compared to Baadachi’s approach; the implication of this finding is that SOLS can be applied to MANET to detect black hole attack.
Keywords:	Mobile Ad Hoc Network, Ranking Strategy, RSA Algorithm, MATLAB, Optimized Link State Routing, Certificate Authorized Nodes
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	EXTRACTING DRUG-DRUG INTERACTIONS FROM BIOMEDICAL TEXT USING A FEATURE-BASED KERNEL APPROACH
Author:	ANASS RAIHANI, NABIL LAACHFOUBI
Abstract:	Discovering unknown drug interactions is of great importance for healthcare professionals since these interactions can become extremely dangerous and can affect patient’s safety. Since newly discovered drug interactions are reported in scientific papers, developing text mining techniques to automatically extract those interactions from unstructured texts is of great importance. All state-of-the-art systems evaluated on the standard DDIExtraction 2013 challenge corpus didn't exceed the threshold of 70%, which means that developing more powerful systems to manage this task still very important. In this paper we present a new feature-based kernel method to extract and classify drug interactions described in biomedical literature. Like many previous works, our method consists of two steps. First we detect interacting drug pairs, and then we classify each extracted pair into one of four interaction categories. To perform the first step, we have enhanced an existing feature-based system by adding new features, correction patterns, and trigger words. To perform the second step, we have built a new feature-based kernel classifier that exploit the lexical field particularity of each interaction type. This classifier is composed of 4 binary classifiers work sequentially. When evaluated on the DDIExtraction 2013 challenge corpus, our system achieved an F1-score of 71.14%, as compared to 69.75% and 68.4% reported by the top two state-of-the-art systems based respectively on Convolutional Neural Networks and graph kernel with context vectors methods.
Keywords:	Drug–drug interaction, Biomedical literature, Feature-based kernel approach , Biomedical Informatics , Natural Language Processing
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	OPTIMAL FEATURE SELECTION FOR CLASSIFICATION OF ELECTRICITY CONSUMPTION
Author:	ZUHAINA ZAKARIA, NOORITAWATI MD TAHIR
Abstract:	Feature selection is the essential process to obtain the best feature vectors in pattern recognition system. These feature vectors contain information describing the original data’s important characteristics. In this research, a framework based on factor analysis technique namely the Principal Component Analysis (PCA) is performed to determine the best features extracted from the daily load curve prior to clustering process. The rules of thumb applied include Bartlett’s test of sphericity, Kaiser-Meyer-Olkin (KMO) measure, Kaiser Criterion, Scree test along with Varimax approach. Accordingly, KMO as well as Bartlett’s test suggested the data factorability is significant. Furthermore, Kaiser Criterion and Scree test together with component matrix approach implied that the first two most significant factor must be retained whilst Varimax approach confirmed that clustering analysis should comprise of the entire load curve values. Upon selection of features, the capability of fuzzy clustering in classifying these features attained from 247 feeders in a particular distribution network is examined. Initial results demonstrated the effectiveness of feature selection process and the potential of fuzzy clustering in particular the fuzzy c- means (FCM) in classifying electrical energy consumption.
Keywords:	Feature Selection, Load profiling, clustering, fuzzy relation, Principal Component Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	IMPROVING SERIOUS GAME DESIGN THROUGH A DESCRIPTIVE CLASSIFICATION : A COMPARATION OF METHODOLOGIES
Author:	SLIMANI ABDELALI, SBERT MATEU, BOADA IMMA, ELOUAAI FATIHA, BOUHORMA MOHAMMED
Abstract:	Serious game provides an instructional tool to make the learning process more enjoyable, easier to memorize and effective. It combines pedagogy goals and game play to increase the participant interest and engagement compared to traditional methods. In this paper, we compare several methodologies of game design relative to our classification proposal; it can assist the analysis and evaluation of serious game design, we illustrate how this classification helps several actors of design to make more informed decisions about the adequate methodology. Finally, we discuss the differences in the use of serious game design methodologies in the follow-up of the statistics of the comparative study.
Keywords:	Serious Game; Learning; Game Design; Comparative Study.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	IMPROVEMENT OF THE METHODOLOGY FOR GRAIN QUALITY ASSESSMENT
Author:	BAKYTKAN DAULETBAKOV, LYAZZAT SULTANGALIYEVA, ARAILYM ABITOVA, PRIMZHAROVA KALYASH
Abstract:	In the article - assessment of the potential properties of the grain; analysis of technological schemes, options, and select the minimum number of parameters to take into account the effect of the complex form of physical and chemical structural, mechanical and biological properties of the processed grain on the basis of factor analysis
Keywords:	Technological Cycle Assessment, Factor Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	A HYBRID GENETIC AND BEE COLONY OPTIMIZATION ALGORITHM FOR TEST SUITE PRIORITIZATION
Author:	R.P. MAHAPATRA, RITVIJ PATHAK, KARAN TIWARI
Abstract:	In the software industry, any software that has been developed needs to go through a maintenance phase. It can typically last from 10 to 15 years. Software maintenance is the most cumbersome yet crucial activity for developers and users alike. Typically, in a Software Development Life Cycle, a software goes from minor to major changes/modifications/updates to provide smooth end user functioning. This entire process of testing the modified software repeatedly, is called as Regression Testing. Exhaustive Regression testing is not possible because of time and budget constraints. Because of this, we have developed several techniques to prioritize test cases in order to reduce time and effort effectively. The two very well researched algorithms in this field are: Bee Colony Optimization and Genetic Algorithm. In this paper, we have formulated a fusion (read hybrid) algorithm based on these two. The Hybrid Algorithm derives a test sequence from the initial population, runs it through a genetic loop and finally applies scout bee path exploration to achieve maximum fault coverage in minimum number of executions. Fault Detection Percentage has been calculated based on the results and a comparison with optimal solution has been presented.
Keywords:	Bee Colony Optimization, Genetic Algorithm, Test Suite Prioritization, Regression Testing, Test Suite Reduction
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	STABILIZATION OF HUMAN HEART USING PID CONTROLLER
Author:	M.AABID, A.ELAKKARY, N.SEFIANI
Abstract:	In the Aim of making an improvement on patient’s quality of life, especially the development of an optimized technique for Hydro-electromechanical (HEM) stimulation and regulation of the Human Heart, This paper simulates the control and the command of the human heart based on three main functions: hydraulic, electrical and mechanical parameters. The based MATLAB mathematical model will primary help to understand the proper functioning of heart attack. In this way we disturb a cardiovascular system with a noise (like Arousal, Anxiety ,disease) coming from human brains and we try to stabilised the whole system by applying a command from PID controller. This research especially focuses on dealing with health care problems to improve quality patients life with heart medical problems. By analysis study of results of the simulation of the whole system by using MATLAB it is found that the overall response of the disturbed system regulated by the adaptive controller is quite like the normal Heart signal.
Keywords:	Proportional Integral Derivative (PID (), Human Heart, Control and command, Pacemaker, Hydro Electromechanical System
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	MULTIMODAL BIOMETRIC AUTHENTICATION SYSTEM USING LDR BASED ON SELECTIVE SMALL RECONSTRUCTION ERROR
Author:	SAVITHA G, DR. VIBHA L., DR. VENUGOPAL K. R.
Abstract:	In Biometrics, physiological or behavioral features are utilized to validate an individual's identity. Though, a substantial amount of research has carried out in this field, unimodal biometric frameworks regularly experience some limits because of non-universal biometrics attributes, vulnerability to biometric spoofing or lack of accurateness. In this paper, the accuracy problem is addressed through multimodal biometric fusion. Our proposed multimodal biometric fusion methodology offers face and fingerprint as biometric traits as an input for sanctuary purpose that are not unique to each other of the human body. Here, we include Wiener filter for preprocessing phase and Discrete Wavelet Transform (DWT) for the fusion process of the two traits. Also, a linear discriminant regression classification (LDRC) algorithm has been proposed. We propose selective small reconstruction error (SSRE) which helps to select the classes, wherein chances to misclassifies the classes are considered when calculating the between-class reconstruction error (BCRE). After maximizing the ratio of BCRE and within-class reconstruction error (WCRE) an optimum projection matrix is obtained through which a high discrimination value can be achieved for classification. Finally, the experimentations are carried out and our proposed LDRC methodology performance is found better than the existing LRC in terms of accuracy, FAR, FER, EER.
Keywords:	Biometric Authentication, Between-Class Reconstruction Error, Discrete Wavelet Transform, Wiener Filter, Within-Class Reconstruction Error.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	ZAHMAH SOCIAL FORCE MODEL FOR PEDESTRIAN MOVEMENT
Author:	AHMAD ZAKWAN AZIZUL FATA, SARUDIN KARI, MOHD SHAFRY MOHD RAHIM, TANZILA SABA, AMJAD REHMAN
Abstract:	The Social Force Model is one of the well-known approaches that could successfully simulate pedestrian’s movement realistically. However, it is not suitable to simulate a complex pedestrian movement. Hence, this research proposed a novel model which improved the Social Force Model for simulating high density crowd such as Tawaf. Tawaf is an Islamic ritual, which requires agents to encircle the Kaabah. This ritual has been complex yet unique, due to its capacity, density, and various demographic backgrounds of the agents. A certain set of rules that must be followed by each agent, which introduces anomalies in the flow around the Kaabah. The agents also will be assigned with unique attributes such as; gender, walking speed and intention outlook to make the simulations more realistic. The findings of this research will contribute to the simulation activities of pedestrians in a highly dense population.
Keywords:	Autonomous Agents, Behaviour, Force, Tawaf, Pedestrians.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text

Title:	IMPLEMENTATION OF PARALLEL ALGORITHM FOR LUC CRYPTOSYSTEMS BASED ON ADDITION CHAIN BY A MESSAGE PASSING INTERFACE
Author:	ZULKARNAIN MD ALI, ARNIYATI AHMAD
Abstract:	The LUC cryptosystem is a modification of RSA cryptosystem. It was based on Lucas Function and has been introduced by Smith and Lennon. The computation of the LUC Cryptosystem is totally based on the computation of Lucas Function. Fast computation algorithm is required since the public key, message, primes are all big enough in order to have very secure cryptosystems. In this paper, the Addition Chain technique will be implemented for a parallel computation algorithm. In this case, the public key will be turn into the suitable array where this array will be used for computation of LUC cryptosystem based on Addition Chain. This Addition Chain will be use in manipulating the Lucas Functions properties such as V2n, V2n+1 and V2n-1 to find the fast computation techniques for Lucas Functions. The capability of the standard Message Passing Interface (MPI) is implemented. The process run on special distributed memory multiprocessors machine known as Sun Fire V1280. The proposed techniques can reduce a computation time for LUC Cryptosystem computation compare to the computation algorithm for one processor. As a comparison, the computation time for one processor and several numbers of processors are also included.
Keywords:	Parallel Algorithm, Addition Chain, MPI, Public Key Cryptosystem.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2016 -- Vol. 92. No. 1 -- 2016
Full Text