		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
June 2018 | Vol. 96 No.12

Title:	FEATURE SELECTION USING MODIFIED ANT COLONY OPTIMIZATION APPROACH (FS-MACO) BASED FIVE LAYERED ARTIFICIAL NEURAL NETWORK FOR CROSS DOMAIN OPINION MINING
Author:	DR.E.CHANDRA BLESSIE, S.GNANAPRIYA
Abstract:	Web mining and web usage mining are attracting many researchers to propose new ideas, models, deploying machine learning algorithms and more. Internet usage expands its wings to almost all kind of applications which includes e-commerce. E-commerce facilitates the consumers/customers to buy the products online and at the same time, web analytics helps the website administrators to identify which products sell more. Opinion mining is the key to analytics in many decision-making tasks in the e-commerce arena. This research work aims to propose feature election using modified ant colony optimization approach (FS-MACO) based five layered artificial neural networks for cross-domain opinion mining. Dataset is obtained which consists of reviews about products such as books, DVDs, electronics and kitchen appliances. The features are identified by making use of modified ACO and opinion mining is performed by using ANN. Accuracy and F-measure are the metrics chosen for the evaluating the performance of the proposed work. Comparison of domain-specific and domain – dependent words are presented. Results portray that the proposed work outperforms better than that of the existing work in terms of the chosen performance metrics.
Keywords:	Opinion Mining, E-Commerce, Optimization, Neural Network, Accuracy, F-Measure.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	NEURAL NETWORK WITH PSO BASED TRAINING TO DETECT SPOOFING WEBSITES
Author:	SOZAN ABDULLAH MAHMOOD, NOOR GHAZI M. JAMEEL, SHAIDA JUMA SAYDA
Abstract:	With the advent of Internet, various online attacks were increased among them and the most well-known is a spoofing attack. Web spoofing is a type of spoofing in which fake and spoofing websites made by means of fraudsters to duplicate real websites. Spoofing websites represent legitimate websites which attract users into visiting fake websites to steal users sensitive, personal information or install malwares in their devices. The scammers will use the stolen information for illegal purposes. The specific intention of this paper is to build a new intelligent system that detects and recognize between trusted and spoofing websites which try to mimic the trusted sites because it is very difficult to visually recognize whether they are spoofing or legitimate. This paper deals with the detection of spoofing websites using Neural Network (NN) trained with Particle Swarm Optimization (PSO) algorithm. An Information gain algorithm is used for feature selection, which was a useful step to remove the unnecessary features and reduce time. The Information gain seems to improve the classification accuracy via reducing the number of extracted features and used as an input for training the NN using PSO. Training neural network using PSO provides less training time and high accuracy which achieved 99.18% compared to NN trained with back propagation algorithm which takes more time for training and less accuracy which was 98.20%. The proposed technique is evaluated with a dataset of 2500 spoofing sites and 2500 legitimate sites. The results show that the technique can detect over 99.18% spoofing sites with NN trained using PSO.
Keywords:	Web Spoofing, Information Gain, Neural Network, Particle Swarm Optimization
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	FROM THE W3C GOOD SOCIAL ONTOLOGIES TO A UNIFIED SEMANTIC MODEL FOR OSN
Author:	ASMAE EL KASSIRI, FATIMA-ZAHRA BELOUADHA
Abstract:	The Online Social Networks (OSN) are networks resulting from social media users and interactions. Exploiting the semantic web technologies to present the OSN data, in this paper, we propose using the W3C recommended ontologies as good ones named Friend Of A Friend (FOAF) ontology and Semantically-Interconnected Online Communities (SIOC) ontology; to meet the interoperability, aggregation and analysis needs, we propose also a FOAF and SIOC extensions to participate to engineering a Unified Semantic Model (USM) for OSN. The Unified Semantic Model will permit modelling the most popular social media.
Keywords:	FOAF, SIOC, SIOCA, SIOCT, exSIOCInt, exFOAF, exSIOCA, exSIOCT, Unified Semantic Mode USM, OSN
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	EFFECT OF GAMIFICATION ON E-LEARNING TO SUPPORT LEARNING ACHIEVEMENT AND LEARNING MOTIVATION
Author:	TOMMY PRASETYO AJI, TOGAR ALAM NAPITUPULU
Abstract:	Gamification is a use of game elements in contexts other than games to motivate and enhance user activity. With the recent rapid use of gamification for e-learning, an interesting open question for educators is, can it motivate and improve the achievement of students? The purpose of this study is to measure the effect of gamification on e-learning to support learning achievement and learning motivation. This is done by comparing the traditional learning method (class) and the method of e-learning gamification. The researcher will develop a prototype of e-learning gamification to support his research. There are several game mechanics conducted by researchers into e-learning such as, points, levels, challenges, and leaderboards. The data of this research were taken from the questionnaires distribution and the result of study report of 24 students in one of junior high school. Questionnaires were made into two kinds, pre-questionnaire and post-questionnaire respectively for traditional method and e-learning gamification. While the learning reports are obtained from student’s semester report and report during the use of e-learning gamification. The data is processed with the help of software SmartPLS v.3.2.6 and Microsoft Excel 2016 and analyzed using paired t-test. The results obtained are e-learning gamification does not give a positive effect or improvement on student motivation in terms of behavioral, emotional and cognitive. Futhermore, e-learning gamification also does not give a positive effect on improving student's learning achievement. The role of teacher and one time use of e-learning gamification are the causes that e-learning gamification does not give a positive impact. The challenge for further research is, how we substitute the teacher role.
Keywords:	Gamification, E-Learning, Learning Motivation, Learning Achievement, Game Mechanics
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	TEXT CRYPTOGRAPHY USING MULTIPLE ENCRYPTION ALGORITHMS BASED ON CIRCULAR QUEUE VIA CLOUD COMPUTING ENVIRONMENT
Author:	KHALID KADHIM JABBAR, HUSSIN ABD HILAL, RANA SAAD MOHAMMED
Abstract:	The tremendous development of communication technology, it has become necessary to use cloud computing systems that help us to store the data within a virtual structure, with the increasing volume of important data, the need to secure this data has become necessary through the use of diverse and complex techniques and methods to ensure integrity, confidentiality, and security. This paper presented a method to encrypt a message with different sizes in cloud computing environment by using several encryption algorithms such as: Advanced Encryption Standard AES, Advanced Encryption Standard RSA, and Advanced Encryption Standard Proposal AESP to make the method more secure and effective. which controlled by circular queue that is responsible for scheduling the implementation of the algorithm that defined by a secret code generated by Control Key, this a secret code is changed each time and with each message to be decoded later by using the same secret code to infer the algorithm that used in the encryption, in addition to the possibility of generating multiple random keys that are vary according to the encryption algorithm used. The experiment results shows that the proposed method has ability to encrypt and decrypt a text message with different sizes and short time by utilizing the properties of several algorithms that are scheduled on circular queue inside the cloud computing system, the proposed method consume time is less than other methods when it used alone, while the important criteria such as integrity, complexity, usability, and security are take into consideration to make the method more effective and efficient.
Keywords:	Integrity, confidentiality, RSA, AES, AESP.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	ENHANCING THE RETRIEVAL OF SOCIAL WEB-BASED E-LEARNING CONTENT USING SEMANTICS EXTRACTED FROM DBPEDIA AND WORDNET ONTOLOGIES
Author:	AMMAR ALNAHHAS, BASSEL ALKHATIB, AHMAD OMAR
Abstract:	As E-learning Tools and techniques are becoming more common and compelling, many researches have emerged lately that aims at making it more flexible and applicable. Besides, the content is getting very large nowadays, so that it is very important to develop a more accurate and robust search techniques that help users find the best learning materials that exists all along the web specially on social learning websites. In this paper we propose a new method to collect, index and retrieve learning materials, a collection algorithm is presented that can bring together content from various sources. We present a semantic indexing method that aims at weighting words of the document based on both DBpedia and Wordnet Ontologies, which proves more accurate results according to the analysis and comparison that are shown in this paper.
Keywords:	E-learning, DBpedia, WordNet, Search Engine, Social web
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	ENHANCEMENT OF MAXIMAL RATIO COMBINER IN ULTRA-WIDEBAND WIRELESS RAKE RECEIVER
Author:	JAAFAR A. ALDHAIBAINI, MOHANAD S. ALKHAZRAJI, NAEL A. AL-SHAREEFI
Abstract:	For several users' existence, there are much internal or external interference such as inter-symbol interference (ISI) obstacles act during multiple paths reception technique for receiving data at high data rates in "ultra wideband (UWB) technology". For these several reasons, UWB wireless rake receiver technique was designed to combine many received resolvable paths, normally greater than 100 paths. Structures of rake receiver implementation in literature review have been structured, proposed, and designed towards increasing the system complexity. These designs were done to get better performances through outdoor or indoor reception of multi-path propagation to reduce the probability of bit error (Pe) or bit error rate (BER). So, many rake receivers have been designed in the last publications to decrease the number of resolvable paths that must be estimating and combining by combiner. To achieve this main goal, we proposed two structures of combiner in the rake receiver, Signal Separation Maximal Ratio Combiner Partial Rake (SS-MRC-PR) receiver and Signal Separation Maximal Ratio Combiner Selective Rake (SS-MRC-SR) receiver. These proposed combiners are based on separation of received signals depending on their signs to make comparison between the number of negative signs and positive signs. The previous receivers were produced to reduce the system complexity with fewer correlators and to improve the system performance with very low Pe at increased signal-to-noise ratio (S/N). Before the decision circuit, a comparator is used to make comparison between two quantities, negative quantity and positive quantity to decide whether the wireless transmitted bit is 0 or 1. The Pe was simulated by "MATLAB simulation software" for wireless multi-path environments of "impulse radio time-hopping binary phase shift keying (TH-BPSK) modulation" and the simulation results were obtained and compared with those of "Conventional Maximal Ratio Combiner Partial Rake (C-MRC-PR)" receiver and "Maximal Ratio Combiner Selective Rake (C-MRC-SR)" receiver. This comparison show the reducing of Pe against S/N for the proposed receivers compared to that for conventional receivers which supports the proposed designs.
Keywords:	Rake Receiver Structures, SS-MRC-PR and SS-MRC-SR, Sign Separation of Signals, Conventional MRC, Pe and BER
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	NEW MICROSTRIP FILTER FOR MIMO WIRELESS AND COMPUTER SYSTEMS
Author:	Aqeel H.Al-fatlawi, Mohammed A.Taha
Abstract:	This paper proposes new microstrip bandpass filter to prevent the image bands as far as possible for MIMO antenna configurations for IEEE 802.11 b wireless networks. The insertion loss and return loss values of the projected filter are 0.4 dB and 26.4 dB correspondingly that are very applicable to be implemented with MIMO antenna configuration. This enhanced MIMO prototypical structure can significantly develop wireless scheme by using the multipath propagation productively. These enhancements can be utilized to augment the dependability of instantaneously communicated data streams, improve the wireless system capacity (multiplexing gain) and lessen the bit error rate of wireless system. Along with filter frequency response, the augmentations are investigated in terms of phase response, group delay and Bit Error Rate (BER) for various antenna configurations using QPSK digital technique.
Keywords:	MIMO, Microstrip Bandpass Filter, Wireless and Computer Networks, IEEE 802.11 b, Bit Error Rate
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	IMAGE STEGANOGRAPHY BASED THE BEHAVIOR OF PARTICLE SWARM OPTIMIZATION
Author:	INAAM RABAH MOHAMMAD, Dr.ZIYAD TARIQ MUSTAFA AL TAI
Abstract:	The growing possibilities of modern communications and the explosive growth of information technology imposed special means of security. Image steganography is one class of this security. However, in the modern world new techniques are appeared continuously such as swarm intelligence. Therefore, this work presents an enhancement of security in the field of image LSB steganography using the behavior of PSO algorithm. Specifically, SPSO algorithm represents the standard behavior of PSO, QPSO algorithm represents the quantum behavior of PSO and HPSO algorithm represents the human behavior of PSO. In this paper, three image steganography techniques are proposed using (SPSO, QPSO, and HPSO) algorithms. These algorithms are used to determine the best locations in the cover image pixels to embed the secret text message using LSB technique. Therefore, this paper presents a comparison and evaluations between these types of PSO algorithms in the field of image steganography. Experimental results for hiding different size text messages in four BMP cover images with different sizes, prove that the proposed image steganography using QPSO has best performance. However, PSNR of QPSO system stegocovers is (81.709 dB), the PSNR of HPSO system stegocovers is (81.143 dB), and the PSNR of SPSO system stegocovers is (81.012 dB). Hence, the proposed method using quantum behavior of PSO algorithm is the best performance system from steganography point of view.
Keywords:	PSO, SPSO, QPSO, HPSO, LSB.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	SEARCHING OVER ENCRYPTED SHARED DATA VIA CLOUD DATA STORAGE
Author:	SAMEEH ABDULGHAFOUR JASSIM, WALEED KAREEM AWAD
Abstract:	Cloud computing has developed from various technologies such as autonomic computing, virtualization, grid computing, and other technologies, and the secure storage is essential and important for it due to it provides virtualized resources on Internet. Therefore, Data owner must encrypt his documents locally before uploading it in the public cloud storage to prevent unauthorized access to his data. Sometimes, the data owner wants to share some of his encrypted documents that stored in the cloud with other authorized users, so, he must send the secret key for each document for all authorized users, but this way has many limitations due to the difficulty of key management and key distribution. To overcome drawback of this approach we proposed system to generate a single key used for multiple number of documents and users depending on two techniques asymmetric cryptography and symmetric cryptography. Asymmetric cryptography used the IBC of the data owner to generate his private key and split the private key into two parts give one part to all authorized users and the other part send to Semi-Trusted Third Party (STTP). While symmetric cryptography used by combined secret key with the encrypted file properties and decrypted the result by the public key of the data owner by using asymmetric cryptography (RSA algorithm). Finally, many results were obtain from implementing the proposed system, among these results; the data owner could add or revoke any user without change the master secret key, also the data owner not need to share multi keys with authorized users. As well as, the system overcame the problem on difficulty of searching over encrypted data through encryption key in a public cloud.
Keywords:	Cloud Computing, Cryptography, Revocation, Virtualization, Homomorphic.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	THE EFFECT OF ATTRIBUTE DIVERSITY IN THE COVARIANCE MATRIX ON THE MAGNITUDE OF THE RADIUS PARAMETER IN FUZZY SUBTRACTIVE CLUSTERING
Author:	MARJI, SAMINGUN HANDOYO, IMAM N. PURWANTO, M. YUYUD ANIZAR
Abstract:	The Fuzzy Subtractive Clustering (Fsc) method is applied in many fields because it is able to produce optimal clusters without requiring initial information of many groups as well as on the k-mean method. Unfortunately, in the Fsc method, there is a radius parameter that has a vital role in generating optimal clusters. The magnitude of this radius parameter is hypothetical to be influenced by the variability of the covariance matrix of the dataset. This study investigates the magnitude of radius parameter that resulted in optimal clusters on three datasets with high variability (dataset1), moderate variability(dataset2), and low variability(dataset3) on covariance matrices. In the clustering process, the squash factor and accept ratio parameters are made in constant, while the radius parameter is the determined variable that leads to the optimal cluster achievement. Clustering results are said to be optimal based on two criteria: each cluster consists of at least 2 members, and the clustering produces the smallest Ctm value. The results of this study recommend that prior to clustering with Fsc, it should be calculated first covariance matrix based on the standardized dataset. If the covariance matrix has a high variability, the radius value used is close to 1, the moderate variability is a radius value of about 0.5, whereas the low variability is used near the 0 radius value.
Keywords:	Covariance Matrix, Fuzzy Subtractive Clustering, Optimal Cluster, Radius Parameter, Variability
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	AUTOMATIC MACHINE LEARNING TECHNIQUES (AMLT) FOR ARABIC TEXT CLASSIFICATION BASED ON TERM COLLOCATIONS
Author:	FEKRY OLAYAH, WASEEM ALROMIMA
Abstract:	Due to the rapid and increased availability of documents in a digital format, effect for retrieving information with highest accuracy and the lowest error rate is becoming more difficult. Text Classification (TC) has become one of the key techniques for controlling and organizing documents based on the content of documents. Therefore, keyword extraction is one of the most important natural language processing applications, which extracts information from the document such as term collocations, which are two or more words appear together and always seem as associated. In Arabic language, there are many problems in keyword extraction because of the complexity of Arabic orthography. Moreover, the accuracy is affecting by the document content and the classification technique used. The need for automatic text classification came from a large amount of electronic documents on the web. This research aims to propose an Automatic Machine Learning Techniques (AMLT) for classifying Arabic documents by using term collocations. These collocations are mined from Arabic documents, the extracted term collocations will scoring by using association measure and will be used as terms feature selection. To achieve this study, we used Arabic documents divided into four categories (Economy/ business, Politics, Religion and Science). The results of our approach have compared with the full-document approach and summary-document approach using four techniques (SVM, NB, J48, and KNN) for Arabic documents to determine which classifier is more accurate for Arabic text based on term collocation. The evaluation results proved that our proposed approach outperforms the other method in accuracy.
Keywords:	Arabic Language, Text classification, Term collocations, bi-gram, Machine Learning, Category
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	THE EFFECTS OF INFORMATION QUALITY, SERVICE QUALITY, AND COMPATIBILITY ON CONTINUE USE OF M-LEARNING AMONG STUDENTS IN THE PUBLIC UNIVERSITIES OF IRAQI
Author:	SALIH HAJEM GLOOD, RAED MOHAMMED HUSSEIN, WISAM ABDULADHEEM KAMIL
Abstract:	The success of information system could be determined based on continuously using the technology for future benefits. In today’s era of technology, M-Learning (ML) system has become an important component of Information and Communication Technology provided by educational institutions such as universities to facilitate all the transactions between institutions and their students or lecturers. This system has gained the popularity in developed and developing countries alike. Despite the known benefits of ML to the education community, usage of ML services among students in the developing countries, especially in Iraq, is still low. Additionally, there has not been empirical study on the continuous usage of ML services in developing countries such as Iraq. The primary objective of this study is to determine the contributing factors for continuous usage of ML services among students in a higher education of Iraq. Moreover, the study used quantitative approach by distributing 600 questionnaires to respondents in the public universities of Iraq. Besides that, the collected data was analysed using a Structural Equation Model. The findings showed that information quality construct has a large effect on user satisfaction than service quality and compatibility constructs.
Keywords:	Mobile Learning, Continuous Usage, Evaluation IS Success, Higher Education.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	RECOGNITION OF COMPLEX HUMAN ACTIVITY USING MOBILE PHONES: A SYSTEMATIC LITERATURE REVIEW
Author:	MOHAMMED MOBARK, SURIAYATI CHUPRAT, HASLINA SARKAN, MOHD NAZ'RI MAHRIN, 5NURULHUDA FIRDAUS MOHD AZMI, YAZRIWATI YAHYA
Abstract:	Using mobile phones for Human Activities Recognition (HAR) is very helpful in providing a personalized support system for healthcare management and general wellbeing of the user. Many studies have been published which have investigated the HAR with the help of mobile phones. But, in these studies, the researchers briefly mentioned the complex HARs and did not provide any discussion or comparison with the models used. In our study, we have carried out a systematic review of the currently used models in the Complex HAR. We have been carrying out an automatic search in 4 digital libraries since 2012, to address four research questions in our study. We found 11 primary studies after applying the included - excluded criteria. Further studies need to be carried out in this area, especially for solving the issue of a trade-off between the recognition accuracy and the computational load.
Keywords:	Complex Activity Recognition, Mobile Phone Devices, Systematic Literature Review, Composite Activity, Interleave Activity, Concurrent Activity.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	DETERMINING THE DOMINANT ATTRIBUTES OF INFORMATION TECHNOLOGY GRADUATES EMPLOYABILITY PREDICTION USING DATA MINING CLASSIFICATION TECHNIQUES
Author:	KENO C. PIAD
Abstract:	Recent years shows major increase in the study with regards with prediction and model discovery using various types of Educational Data Mining Techniques. Classification is one of the several data mining techniques that has become an interesting topic to the researchers because of its accuracy and efficiency for classifying the data for knowledge discovery. The purpose of this paper is to predict the employability of IT graduates by to determine whether the IT graduates will land into an IT related profession or not related to IT based on the CMO.53 Series of 2006.The study aims to determine the dominant attributes using data mining algorithms under the supervised learning and compare their accuracy. Among the classification techniques used for comparison of accuracy were Naive Bayes, J48, Simple Cart, Logistic Regression and Chaid Algorithms. The researcher collected the historical data from the five year profiles of BSIT graduates from S.Y. 2011 to 2015 from the University Job Placement Office Tracer Study and combine with their academic records. The results show that 3 significant factors that have direct effect on IT employability which includes IT_Core, IT_Professional and Gender.
Keywords:	Data Mining, Decision Tree, Classification Algorithm, Employability, Prediction; Analytics, Accuracy
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	SENDING IMAGE IN NOISY CHANNEL USING ORTHOGONAL FREQUENCY DIVISION MULTIPLEXING SCHEME
Author:	GHASSAN MUSLIM HASSAN, KHAIRUL AZMI ABU BAKAR, MOHD ROSMADI MOKHTAR
Abstract:	Orthogonal frequency division multiplexing (OFDM) is dependable in data transmission with high speed by the benefit of its robustness to multi-path fading, high data rate, and high spectral efficiency. OFDM is a multi-carrier modulation scheme. Synchronization is the major problems of the OFDM system. In this research, the power consumption was considering through a noisy channel when an image was transmitted in the OFDM system. To support the work, many features were tested such as minimizing the complexity with fast Fourier transforms/inverse fast Fourier transform (FFT/IFFT). The size of bandwidth (BW) play the main role and how its effect on the transmission and how its related to the FFT size (Nfft). The modulation type was also tested to see which one is the best for image transmitted. These types are phase shift keying (PSK) and quadrature amplitude modulation (QAM). In addition, signal to noise ratio (SNR) is one of the performances in OFDM system and consider one of the factors which wireless communication depends on related with bit error rate (BER). Another drawback of the OFDM system was Peak-to- average power ratio (PAPR), therefore, the effect of Nfft on the PAPR has been tested with simulation results in which additive white Gaussian noise (AWGN) had been used in the MATLAB simulation.
Keywords:	Bit Error Rate, Fast Fourier Transform, Orthogonal frequency division multiplexing, Peak-to- Average power ratio, Signal-to-Noise Ratio.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	ANALYSIS AND MODIFICATION OF RICE GOLOMB CODING LOSSLESS COMPRESSION ALGORITHM FOR WIRELESS SENSOR NETWORKS
Author:	S.KALAIVANI, Dr.C.THARINI
Abstract:	Wireless sensor networks (WSN) are network that are constructed using number of sensor nodes distributed and connected wirelessly to perform some specific applications. These networks are strictly restricted in the usage of energy as they use batteries with finite amount of power. This necessitates the need for data compression at each sensor node in a WSN so as to overcome the resource constraints of the network and increase its lifetime. Various functions carried out by each node are sensing, processing, communicating and storing the data, among which the communication consumes much energy than the other functions. Data compression is one technique that extends the network lifetime by reducing the energy consumed at each node during communication. The proposed work comprises of 5 different methods that suggests modification of lossless Rice Golomb Coding (RGC) compression algorithm with respect to the decision of tunable parameter based on preprocessing of the input data. Simulation results on various modifications of RGC using different datasets in MATLAB software is analyzed and compared with respect to root mean square error (RMSE) and saving percentage (SP). The modified lossless compression algorithm EMARGC_D with better saving percentage is applied and executed in real time using NI WSN nodes interfaced with LabVIEW.
Keywords:	Data Compression, LabVIEW, MATLAB, NI 3202 Sensing Node, NI 9792 Gateway Node, Rice Golomb Coding, Wireless Sensor Networks
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	ENHANCEMENTS FOR CROWDSOURCED REQUIREMENTS ENGINEERING
Author:	SULTAN ALYAHYA, WEJDAN ALOHALI, SAMEERAH AL-BALHARETH
Abstract:	The use of crowdsourcing in software requirements engineering has become common nowadays. The web-based services offered through Crowdsourced Requirements Engineering (CRE) platforms support customers in finding timely and accurate requirements specification for their proposed tasks and projects. Currently, the literature does not have a critical assessment of the key activities involved in the CRE platforms. In this paper, we review the process used in the CRE platforms including identifying the workflow used in managing the process. Then we made a step further in the direction of improving the current platforms; the review is used to identify a set of limitations in the current process and has led to propose enhancements. These enhancements are evaluated using two techniques: questionnaire and workshop. The questionnaire shows that the enhancements are sound and practical to be added to CRE platforms. In addition, the evaluation through conducting a workshop showed that the participants were satisfied with the enhancements but asked for further modifications.
Keywords:	Crowdsourced Requirements Engineering, Crowdsourcing, Requirements Engineering, Enhancements, Platforms.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	A MEASUREMENT MODEL OF THE FUNCTIONAL SIZE OF SOFTWARE MAINTAINABILITY REQUIREMENTS
Author:	KHALED ALMAKADMEH, KHALID T. AL-SARAYREH, KENZA MERIDJI
Abstract:	The European ECSS-E-40 standard for the aerospace industry includes maintainability as one of sixteen non-functional requirements for the embedded and real time software. The software maintainability requirements measured internally and externally. According to the ECSS European standards, maintainability requirements are apportioned to set maintainability requirements for lower level products to conform to the maintenance concept and maintainability requirements of the system and the maintainability analysis shall identify the maintainability critical items. This paper propose a new measurement model of the functional size of maintainability requirements of software. This functional size of the maintainability requirements measured using the concepts of the ISO19761: COSMIC standard at an early phase of the software development life cycle. It used as one of the primary inputs for the software effort estimation process. Further, this paper presents the design of software standard etalon to help in development of software products more effectively. An experiment is conducted to verify the applicability of the proposed measurement model to measure the functional size of requirements specifications of an online library software.
Keywords:	Maintainability Requirements, ISO19761, ECSS standards, Measurement method
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	DEVELOPING (UTAUT 2) MODEL OF ADOPTION MOBILE HEALTH APPLICATION IN JORDAN E- GOVERNMENT
Author:	MALIK BADER ALAZZAM , YASSER MOHAMMAD AL SHARO , MAJED KAMEL AL AZZAM
Abstract:	Mobile Health Application (MHAs) positively influence the quality of hospital services and lessen health costs. Lack of education and awareness may hinder the use of the MHA system. Through the Unified Theory of Acceptance and Use of Technology (UTAUT) framework, this research scrutinized the elements which influence the MHA acceptance. The UTAUT model is a new tool for evaluating the integration/adoption of MHAs. Through empirical studies and the use of the UTAUT2 model we aim to clarify the behavioral exercise of healthcare specialists and their propensity to using the MHA system. The objective of the research is to test trust information elements which influence integration and adoption of the MHA by healthcare providers. This research focuses on Jordanian hospitals which use the MHA. The study further direct to create a well-defined view of which factors influence the adoption and acceptance of the MHA, by making use of questionnaires as a starting point for in-depth and comprehensive future studies. Methods: The article made use of surveys coursed through Jordan hospitals to gather data from healthcare providers/specialist/professionals, who were familiar with the MHA system. A total of 278 responses were derived from 555 survey-forms for data analysis.
Keywords:	Mhas, Healthcare Professionals, UTAUT1, UTAUT2, Acceptance, Trust In Information, E Government
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	MEAT FRESHNESS IDENTIFICATION SYSTEM USING GAS SENSOR ARRAY AND COLOR SENSOR IN CONJUNCTION WITH NEURAL NETWORK PATTERN RECOGNITION
Author:	MUHAMMAD RIVAI, FAJAR BUDIMAN, DJOKO PURWANTO, JOSHWA SIMAMORA
Abstract:	Meat freshness level is an important factor to determine meat quality for consumption. In this research, a sensor system has been designed to identify the freshness level of meat in fast, precise and non-destructive manners. The system is implemented into a Raspberry Pi equipped by gas and color sensors as the freshness identifier tools to replace the human olfaction and vision in determining a fresh meat. Pattern recognition powered by a neural network is used to identify the meat’s freshness. The neural network inputs are the odors sensed by the gas sensor array of MQ-136, MQ-137, TGS 2620 and Red, Green, Blue values sensed by TCS 3200 color sensor. Three levels of freshness have been tested, such as fresh meat, half-rotten meat, and rotten meat. The usage of the three gas sensors and one color sensor of the system is capable to acquire a distinct pattern for the three categories of freshness. The freshness identification of the meat has a high percentage of success up to 80%. The errors are caused by the small different of the pattern sensed by sensors for half-rotten meat and rotten meat; these two kinds of meat fortunately are not consumable. Thus, it may conclude that the system has 100% success degree to identify fresh meat and non-fresh meat. The implementation of the system is expected to replace the traditional measurement by the human senses (i.e. nose and eyes) to obtain equal measurement as different human examiner acquires different result, and to eliminate the impact of bacteria or virus from meats to examiner. It may also replace measurement system using chemical substances so the tested meat will be still consumable.
Keywords:	Color Sensor, Gas Sensor, Meat Freshness, Neural Network, Raspberry Pi.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	AN EFFECTIVE INTRUSION DETECTION MODEL BASED ON SVM WITH FEATURE SELECTION AND PARAMETERS OPTIMIZATION
Author:	EL MOSTAPHA CHAKIR, MOHAMED MOUGHIT, YOUNESS IDRISSI KHAMLICHI
Abstract:	With the growth of the internet, network attacks have increased severely in a substantial number in the last few years. Therefore, Intrusion Detection Systems (IDSs) have become a necessary addition to the information security of most organizations. An IDS monitors a network or a single host looking for suspicious activity and reports them. Many intrusion detection types of research have focused on the feature selection because some characteristics are irrelevant or redundant which result in a lengthy detection process and degrades the performance of IDS. For this purpose, we have used in this work an algorithm based on Information Gain technique. This algorithm selects an optimal number of features from NSL-KDD Dataset. In addition, we have combined the feature selection with a machine learning technique named Support Vector Machine (SVM) using Radial-basis kernel function (RBF) and a Particle Swarm Optimization algorithm to optimize the parameters of SVM for effective classification of the dataset. We have also compared the proposed method and other methods. Tests on the NSL-KDD Dataset have proved that our proposed method can reduce the number of features and obtain good results in terms of accuracy, attack detection rate and false positives rate, even for unknown attacks.
Keywords:	Intrusion Detection System, NSL-KDD, Feature selection, PSO, SVM, Information Gain.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	A GESTURE RECOGNITION SYSTEM FOR GESTURE CONTROL ON INTERNET OF THINGS SERVICES
Author:	TALAL H. NOOR
Abstract:	Internet of Things (IoT) is a promising computing model, which uses several enabling technologies to provide new type of smart services that allow users to interact with daily objects in a different way. Most of IoT services are invoked using touch screens and connected to Smartphones or tablets to enable a real-time connectivity between users and things. However, only a few IoT systems consider gesture based user interactions for their services which allow users to have a better experience with IoT products. In this work, we present a gesture recognition system for gesture control on IoT services. In particular, the gesture recognition system is based on alphabet characters and number to classify the hand fingertip trajectory using a hidden Markov model. The presented system composed of three key stages. Firstly, color information with 3D depth information that segment the correct position of hands. Then the fingertip is detected based on the curvature of hand contour. Secondly, the dynamic features in polar coordinates are employed using k-mean clustering technique. Finally, Baum-welch procedure is used to carry out the learning gestures and the viterbi algorithm is used to recognize the gesture. The experiments demonstrate that the presented system has a capability to classify the isolated gesture dues to spatio-temporal variability. Precisely, our experiment provides a promising result where the average recognition rates achieved 98.61% and 93.06% for training and testing dataset, respectively. Furthermore, it provides finer presentation and low-slung computational difficulty when functional image sequences samples of multipart circumstances are used.
Keywords:	Internet of things' services, gesture recognition, gesture control, color information, depth map, hidden Markov model.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	AN ANALYSIS OF TEXT MINING FACTORS ENHANCING THE IDENTIFICATION OF RELEVANT STUDIES
Author:	MOUAYAD KHASHFEH, MOAMIN A. MAHMOUD, MOHD SHARIFUDDIN AHMAD
Abstract:	The development of science and the spread of knowledge coincide with growing number of publications, and the volume of online content continue to grow at a rapid rate. For some submitted queries, the search engines may return thousands of documents of questionable relevancy. In this paper, we analyze the literature and identify the text mining factors that influence the identification of relevant studies. Five factors are identified which are Text Typography; Paragraph length; Term Frequency factor; Coordination; and Strict search. Subsequently, we propose an agent based-text mining model that facilitate the identification of relevant studies in big databases. The model consists of four components which are, interface, search process, parsing process, and storage. The interface provides a communication mean between a user and his/her counterpart agent (Personal Agent). In addition, it provides an input tool for user’s search preferences. The second component is the search process that is operated by a pattern matching. The third process is the parsing that is operated by a text mining algorithm. The last part is the storage that is managed by Monitor Agent. The proposed framework would be useful in providing an alternative means of searching highly relevant studies from large databases.
Keywords:	Text Mining, Agent-based Model, Relevant Studies
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	AUTOMATIC QUESTION GENERATION FOR 5W-1H OPEN DOMAIN OF INDONESIAN QUESTIONS BY USING SYNTACTICAL TEMPLATE-BASED FEATURES FROM ACADEMIC TEXTBOOKS
Author:	SETIO BASUKI, SELVIA FERDIANA KUSUMA
Abstract:	The measuring of education quality in school can be conducted by delivering the examination to the students. Composing questions in the examination process to measure students’ achievement in the school teaching and learning process can be difficult and time consuming. To solve this problem, this research proposes Automatic Question Generation (AQG) method to generate Open Domain Indonesian Question by using syntactical approach. Open Domain questions are questions covering many domains of knowledge. The challenge of generating the questions is how to identify the types of declarative sentences that are potential to be transformed into questions and how to develop the method for generating question automatically. In realizing the method, this research incorporates four stages, namely: the identification of declarative sentence for 8 coarse-class and 19 fine-class sentences, the classification of features for coarse-class sentence and the classification rules for fine-class sentence, the identification of question patterns, and the extraction of sentence’s components as well as the rule generation of questions. The coarse-class classification was carried out based on a machine learning with syntactical features of the sentence, namely: Part of Speech (POS) Tag, the presence of punctuation, the availability of specific verbs, sequence of words, etc. The fine-class classification was carried out based on a set of rules. According to the implementation and experiment, the findings show that the accuracy of coarse-class classification reaches 83.26% by using the SMO classifier and the accuracy of proposed fine-class classification reaches 92%. The generated questions are categorized into three types, namely: TRUE, UNDERSTANDABLE, and FALSE. The accuracy of generated TRUE and UNDERSTANDABLE questions reaches 88.66%. Thus, the obtained results show that the proposed method is prospective to implement in the real situation.
Keywords:	Automatic Question Generation (AQG), Coarse-class Classification, Fine-class Classification, Open Domain Question, Syntactical Approach
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	ENHANCING DBPEDIA QUALITY USING MARKOV LOGIC NETWORKS
Author:	MAHMOUD ALI, MOHAMMED ALCHAITA
Abstract:	The linked data in the Web may be incomplete due to be extracted from semi-structured sources such as Wikipedia, or unstructured such as text. There are various approaches aim to complete the missing data in the linked data sets, including the statistical distributions of properties and types for enhancing the quality of incomplete and noisy Linked Data sets, which obtained good results. In this study, we suggest using of Markov logic networks to improve the quality of the unstructured Linked Data sets without using any external knowledge. Markov Logic Networks (MLNs) is considered one of the most known and proposed methods in the field of Statistical Relational Learning (SRL). It is a first order knowledge base with attaching a weight to each formula. Markov Logic Networks generalize the First - order Logic and attach a weight to each equation. Therefore, we rely on RDF(S) and its associating entailment rules which provide a data representation model. We carry out reasoning by transforming the statements and constraints to Markov Logic and compute the most probable consistent state with respect to the defined constraints. Results showed that the proposed algorithm could infer on correct types which the algorithm SDType couldn't. As well, the results were remarkably improved at increasing the number of the steps.
Keywords:	Dbpedia, Type Completion, Markov Logic Network, Knowledge Graph, First Order Logic.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	IMPLICATIONS OF PRIVACY PRESERVING K-MEANS CLUSTERING OVER OUTSOURCED DATA ON CLOUD PLATFORM
Author:	ANURAG, DEEPAK ARORA, UPENDRA KUMAR
Abstract:	Data Mining has gained attention nowadays in the field of sales, marketing, insurance and healthcare applications to name a few. Organizations aspire to perform mining operations on their joint datasets for gaining trade benefits while hiding own sensitive information. Owing to huge resource consumption and less computational power, they often prefer to outsource their data on the cloud platform for entire computation. As there is a risk of exposing the organization's sensitive data from various mistrusted parties involves in it, privacy becomes one of the major challenging issues in cloud computing. Authors have proposed an algorithm were cloud server applies k means clustering on encrypted data sets. A Trusted Party is assumed for key distribution and management. Computations between each party are either performed mutually or via Trusted Authority which involving exchange of sensitive data transfer of each participating parties. Complexity of the algorithm has been analyzed and compared with the existing approach and found that it is linearly depends upon various parameters settings and hence is a better approach while maintaining authenticity and data confidentiality between various participating parties during the mining process.
Keywords:	Privacy Preserving Data Mining, Pailler Homomorphic Encryption, K-Means Clustering, Cloud Platrorm, Use Case Diagram.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	EVALUATION OF EWOM APPLICATION IN MUSEUMS IN JAKARTA
Author:	ARTA MORO SUNDJAJA, SEVENPRI CANDRA, AMALIA RUSADI
Abstract:	This study aims to evaluate and assess the implementation of electronic word of mouth in several museums in Jakarta by using Facebook Fan Page. This study used a qualitative approach to explore the phenomena of public awareness about museum. The population is Facebook Fan Page museum in Jakarta. The sampling technique used in this research is disproportionate stratified random sampling. The data collection used in this research is Facebook observation and the data were analyzed using e-WOM Analytical Framework developed by Andrea Hausmann. The finding is Museum Basoeki Abdullah actively manages its Facebook account and updates it regularly. The content presented is attractive, varied, and interesting with a broad use of media such as images and video content. Museum Basoeki Abdullah also stimulates discussion and interaction through competitions, thus inviting Facebook user engagement and active participation from followers in this social media domain. The goal makes the page look more attractive in general. The conclusions obtained from this study suggest that not all museums utilized the Facebook Fan Page for developing the electronic word of mouth. There is a need for the identification and development of best practice in this domain so that museums management apply electronic word of mouth. The implementation of best practice can attract people to visit the museum based on appropriate benchmark for assessing and comparing their performance.
Keywords:	Electronic Word Of Mouth; Hausmann Analytical Framework; Museum Awareness; Facebook; Social Media Marketing.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	SMS SPAM DETECTION USING ASSOCIATION RULE MINING BASED ON SMS STRUCTURAL FEATURESNOOR GHAZI M. JAMEEL
Author:	NOOR GHAZI M. JAMEEL
Abstract:	The popularity of using mobile phones has led to an increase in sending SMS messages. SMS messages are considered as a rapid way of communication due to its low cost and easy usage. As a result, SMS was target for many types of threats, one of these is spamming. SMS spam is unwanted message sent to many mobile phone users, and cause many problems like annoyance, consuming mobile network bandwidth and other real threats like scam, stealing personal information and installing malware. In this paper, a new system is proposed to detect spam SMSs using Apriori algorithm. This algorithm is used to generate association rules which applied to new SMSs to classify them into spam or legitimate. The system used structural features only instead of textual features or tokens. These features extracted from two publicly available datasets which consists of spam and legitimate SMSs. The rules are generated with different minimum support and minimum confidence values. The generated rules are applied to the test dataset then the rules which achieved higher accuracy are used in the proposed system. The aim of this work is presents a new and fast approach to detect spam SMS using structural features only and to find out if structural features are enough to detect spam SMSs instead of bag of words which depends on preprocessing and consists of many steps like parsing, tokenization, stop word removal and stemming. Good accuracy achieved with 97.65% using rules generated by Apriori association rule mining algorithm with minimum support 0.2 and minimum confidence 0.8 based on SMS structural features only.
Keywords:	SMS, SMS Spam, Association Rule Mining, Apriori Algorithm
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text

Title:	RTDBSTREAM: A REAL-TIME DENSITY-BASED CLUSTERING FOR EVOLVING DATA STREAMS
Author:	K. SHYAM SUNDER REDDY, C. SHOBA BINDU
Abstract:	Density-based clustering method has come into existence as a prominent class for clustering data streams. It has the ability to discover clusters with arbitrary shape, and it can handle noise in data. Recently, several density-based clustering algorithms have been proposed in the literature for clustering data streams. But each algorithm has its own limitation that renders them ineffective and makes a new algorithm necessary for dealing with big data. Existing density-based clustering algorithms require high computation time and more memory for clustering process. In this paper, we present a novel density-based clustering algorithm called Real-time Density-based Clustering (RTDBStream) for evolving data streams. This algorithm is a hybrid density-based clustering algorithm that integrates the pros of density-grid and density micro-clustering algorithms to get better results. The quality of the proposed algorithm is evaluated on various data sets with distinct characteristics using different quality metrics.
Keywords:	Big data, Data stream, Density-based clustering, Grid-based clustering, Micro-clustering
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2018 -- Vol. 96. No. 12 -- 2018
Full Text