		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
September 2018 | Vol. 96 No.18

Title:	ENHANCE INTRUSION DETECTION CAPABILITIES VIA WEIGHTED CHI-SQUARE, DISCRETIZATION AND SVM
Author:	WARUSIA YASSIN, MOHD FAIZAL ABDOLLAH, MOHD ZAKI MASUD, 1ROBIAH YUSOF, RAIHANA ABDULLAH, ZAITON MUDA
Abstract:	Anomaly Intrusion Detection Systems (ADSs) identify patterns of network data behaviour to determine whether they are normal or represent an attack using the learning detection model. Much research has been conducted on enhancing ADSs particularly in the area of data mining that focuses on intrusive behaviour detection. Unfortunately, the current detection models such as the support vector machine (SVM) is affected by high dimensional data which limits its ability to accurately classify data. Moreover, the data points which appear similar between intrusive and regular behaviours could be problematic as some innovated attack behaviours may not be detected. To overcome this SVM drawback, we propose a combination of weighted chi-square (WCS) as a feature selection (FS) and a Discretization process (D). The WCS method is used firstly to reduce the dimensionality of data following which the assembled records are transformed into interval values via the D process before the SVM is used to identify groups of samples that behave similarly and dissimilarly such as malicious and non-malicious activities. Experiments were performed with well-known NSL-KDD data sets and the results show that the proposed method namely WCS-D-SVM (weighted chi-square, discretization and support vector machine) significantly improved and enhanced accuracy and detection rates while decreasing the false positives which the single SVM classifier produces.
Keywords:	Intrusion Detection, Data Mining, Feature Selection, Weighted Chi-square, Discretization, Support Vector Machine
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	QUALITATIVE ASSESSMENT OF SYSTEMATIC LITERATURES IN SOFTWARE ENGINEERING
Author:	J.O. OKESOLA , K.O. OKOKPUJIE , A.A. ADEBIYI , C.K. AYO
Abstract:	Several systematic literature reviews (SLRs) have been published on many aspects of Software engineering (SE) in the last two decades. However, researchers are yet to evaluate the quality of those studies in order to determine the reliability of their findings. This work employed SLR method and performed automated search of studies published between 2012 and 2017 aiming at evaluating the quality of the recent SLRs published in SE. This paper adapted Dybå and Dingsøyr quality criteria using dichotomous scale of grad-ing to assess the quality of the primary studies in SLRs. A total of 15 of 53 primary studies have suitable recruitment strategy for their research aims, and 19 mentioned the control group (s) with wish their meth-ods were compared. All the 53 papers passed all the standard quality conditions. The quality of the SLRs are high with only very small percentage failing in three out of 11 quality criteria. The research methodol-ogies applied in their primary studies are comprehensive and were based on clear description of the con-text, thereby making their findings valid and reliable. The current SLRs in SE are of good quality but ad-equate consideration should be given to the relationship between the researchers and the participants.
Keywords:	Quality assessment, Requirement Engineering, Software Engineering, Structured Review, Systematic Literature Review.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	DIAGNOSIS RETINOPATHY DISEASE USING GLCM AND ANN
Author:	NOOR.A.RASHED, SHAKER K. ALI, ALI J. DAWOOD
Abstract:	The diabetes mellitus is a chronic disease. It has high incidence all over the world. It has many complications such as peripheral neuropathy, cardiac and renal problems and retinopathy, but the diabetic retinopathy considers one of the major problems, which causes retinal damage and leading blindness. Unless we avoid the danger of rapid diagnosis and accurate continuity to monitor any developments that may occur. In addition, distinguish them from other diseases that may affect the eye and which occur for other reasons. Therefore, it is necessary for ophthalmologists to accurately diagnose this disease in order to avoid any error may occur. In this paper, we suggest an algorithm for retinopathy diseases diagnosis to help doctors diagnose diabetes mellitus and distinguish between the health s conditions from the infected condition. The algorithm based on two stages; the first Stage, depends on converting the image to grayscale and improving the contrast of the image using the Contrast Limited Adaptive Histogram Equalization (CLAHE). Then analysis the image by using the Grey Level Co-occurrence Matrix (GLCM) to extraction the image features. The second stage extracting the qualities from the color image by converting (RGB) color space in to (HSV) color space and using color moment algorithm and extract the feature based on color. The features extracted from Qualities gave strong results. The features will be to Neural Network, which enables us to diagnose the cases of, normal and abnormal with high accuracy; our algorithm accuracy is 97%. Our dataset collected from various sources, including local and international, in this paper used (283) images.
Keywords:	GLCM, Retina, Diagnosis, Feature Extraction, Diabetic, ANN.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	TEST CASE PRIORITIZATION TECHNIQUE FOR EVENT SEQUENCE TEST CASES BASED ON REDUNDANCY FACTOR
Author:	JOHANNA AHMAD, SALMI BAHAROM, MYZATUL AKMAM SAPAAT
Abstract:	Software testing is often used to verify and validate the output of the system to confirm that no discrepancy has taken place throughout the development phase. Test case prioritization (TCP) is one of the techniques applied to modify the order of test cases based on best test scenarios and to prioritize them. The main objectives of the TCP are to increase the effectiveness of the testing process, while reducing time and cost, which would increase when the system reaches a certain level of complexity. Numerous TCP techniques have been proposed in the past; however, only a handful of researches were truly focused on TCP techniques for test cases involving the sequence of events. TCP technique for sequence of events is more complex compared to the conventional code-based application due to the properties of the sequence of events. The size of the sequence of events’ test cases can be infinite and large sized test cases have considerable degrees of redundancy. This means that there is a possibility for these test cases to have combinations of events with a large input parameter. Redundancy is one of the major issues that have been discussed by previous researchers. This paper proposes a technique that can detect the redundancy within the test suites and produce a unique weight value. This paper will also present how test cases were prioritized based on the obtained unique weight value. The experiment results obtained indicates that the prioritized test suite is effective compared with the original test suite. The effectiveness of the proposed approach is evaluated using Average Percentage of Faults Detected (APFD).
Keywords:	Test case prioritization, software testing, unique weight, event sequences
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	HYBRID FEATURE SELECTION BASED ON MUTUAL INFORMATION AND AUC FOR PARKINSON’ DISEASE CLASSIFICATION
Author:	ZAINAB N. SULTANI, SUHAD A. YOUSIF
Abstract:	Machine learning classifiers are used to distinguish healthy individuals from patients with Parkinson’s disease through the use of a dataset of voice measurements based on patient speech recordings. Feature selection based on information theory is used in many data mining and machine learning applications. Mutual information is used on the Parkinson disease dataset to select a subset of relevant features that contribute the most in the decision making process. In conjunction with Mutual Information, the area under curve (AUC) is applied for feature selection, and features are eliminated by majority voting. In this paper, five classifiers are used to classify Parkinson’s disease: Multilayer Feedforward Artificial Neural Network, k-Nearest Neighbor (kNN), Support Vector Machines, Naïve Bayes, and k-Means. The dataset is preprocessed prior to the classification, and the classifiers are trained using the k-fold cross validation evaluation model. The performance of the classifiers is evaluated based on the accuracy and the area under curve before and after the feature selection. The results are promising, particularly for the kNN classifier; k-Means presents the worst performance.
Keywords:	Machine Learning, Feature Selection, Mutual Information, Area Under Curve, Parkinsons Disease
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	REAL-TIME ABNORMAL EVENT DETECTION IN CROWDED SCENES
Author:	AHMED NADY, AYMAN ATIA, AMAL ELSAYED ABUTABL
Abstract:	Detecting unusual events in crowded scenes has drawn considerable research interest lately. In this paper, an unsupervised method that relies on a spatio-temporal descriptor and a clustering technique is presented to tackle this problem. We employ space-time auto-correlation of gradients (STACOG) descriptor to extract spatio-temporal motion features from video sequence. Following that, the K-medoids clustering algorithm is used to partition the STACOG descriptors of training frames into a set of clusters. The frame abnormality is defined by distances between the center of the clusters and the motion feature extracted by STACOG. We have conducted experiments on various benchmark datasets and the results show that the proposed method obtains comparable results: 98.48% AUC for UMN, and 92.13% accuracy for PETS 2009, at the frame level. In addition, fast computation time of our method that satisfies the demand of real-time processing.
Keywords:	STACOG, K-medoids, 3D gradient, Abnormal event detection, Visual surveillance
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	FUNCTIONAL REQUIREMENTS ANALYSIS OF E-COUNSELING
Author:	ULFIAH ULFIAH
Abstract:	This article aims to analyze the functional requirements of counseling activities that utilize information technology, called e-Counseling. This article used information resources of literature review, observation, interview, and researchers’ experience as a methodology. The author conducted the analysis of functional requirement based on knowledge management system. Design of e-Counseling uses prototype software development methodology. The result of this study showed that all the functional requirements of e-Counseling could be traced well and completely based on knowledge management activities, among others knowledge acquisition/ creation, knowledge sharing, knowledge storage, and knowledge utilization. It could be concluded that the traceability quality of functional requirement analysis of e-Counseling had been met completely, effectively and efficiently.
Keywords:	E-counseling, Knowledge Management; Knowledge Management System
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	COMPARISON OF SKIN LESION IMAGE BETWEEN SEGMENTATION ALGORITHMS
Author:	SHAKAR H. SALIH, SHEREEN AL-RAHEYM
Abstract:	Melanoma is the most common dangerous type of skin cancer. Furthermore, if found in an early stage, there is a high likelihood of cure. For that reason, various types of imaging techniques have been investigated. Dermoscopy is one non-invasive imaging technique for diagnosis. The accuracy of diagnosis using dermoscopy is very important and depends on the experience of dermatologists. Visual examination is a waste of time, so there is currently wide attention paid to the development of computer-aided diagnostic systems to aid the clinical evaluation of dermatologists. Image Segmentation is very important in digital-image processing and self-discovery, with an important role to play in solving many difficult problems, particularly those related to chronic diseases, such as skin cancer. Analysis of automatic dermoscopy images usually has three stages: a) feature selection and extraction, b) image segmentation, and c) feature classification. In this work, we suggest and test two methods that are applied to 22 dermoscopy images: a) active contour modeling, and b) a proposed method of fuzzy clustering based on region growing. We evaluated our methods using three metrics: accuracy, sensitivity, and specificity as a result, our proposed method of fuzzy clustering based on region growing achieved the best ratio. Our research limitation can be addressed through applying a large amount of dermoscopy images and use different processing algorithms to reach a better classification will enrich our result that are left for future work.
Keywords:	Image Segmentation, Dermoscopy, Skin Cancer, Melanoma, Skin Lesion.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	ENHANCING CLUSTERING-BASED CLASSIFICATION ALGORITHMS IN E-COMMERCE APPLICATIONS
Author:	AYMAN MOHAMED MOSTAFA, MOHAMED MAHER, M.M. HASSAN
Abstract:	Data mining algorithms are used for analyzing data from different sources and extracting useful information from a large volume of data. Algorithms of data mining are used in E-commerce companies to help them identifying online customer behavior to recommend appropriate products based on customers’ needs. In this paper, our aim is enhancing the result of the classification techniques that applied to an online shopping agency dataset by using clustering techniques which applied to this dataset before entering it to classification techniques, so farthest first, expectation maximization (EM), and K-mean clustering algorithms are applied to an online shopping agency dataset to allocate related objects into the same cluster. After applying clustering algorithms, a group of data mining classification algorithms such as Bayes net, Naïve Bayes, K star, filtered classifier, decision table, J48, and JRIP are applied to the three clustering algorithms. A logistic model tree (LMT) classification algorithm is applied also to measure the performance parameters for each classifier. The experimental results achieved high rates in accuracy, precision, recall, F-measure, and ROC when compared to recent research paper.
Keywords:	Data mining, Classification, Clustering, Logistic Model Tree, and E-commerce
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	PROPOSED METHOD FOR ROAD DETECTION AND FOLLOWING BOUNDARIES
Author:	DR.HAZEEM B. TAHER, DR.KADHIM M. HASHEM, FATIMA A. SAJET
Abstract:	Lane detection and following is a significant component of vision-based driver assistance systems (DAS), lane detection and tracking methods are the state of the art in present intelligent transportation systems and intelligent vehicle applications. It is however very challenging since the road is in an outdoor scenario imaged from a moving platform. in this paper, we suggest and implement an effective algorithm of real-time line detection and following lane signals to detect the left and right lane boundaries of the line .The proposed algorithm consist of two phases, In the first phases the road is isolation from the image, so, the proposed algorithm in this phase will detect the edges and marks on the road using image processing techniques, also, apply this phase in image taken or video in real time. The second phase in this research, is for how to follow the lines that represent the road signs for a way to take the angles of the neighborhood of each pixel on the line, to be able to know the road is straight or rotate. Lane detection algorithm which is simple, robust, and efficient. Thus, suitable for real-time processing. The main objective of this paper is to implement an effective lane detection and following system, the approach presented here was tested on image and video sequences downloaded from https://www.shutterstock.com/search. All the detection and tracking programs developed using the MATLAB R 2015 b platform.
Keywords:	Driver Assistance Systems, Lane Detection, Lane Following, Intelligent Vehicle, Neighborhood
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	EMOTION RECOGNITION USING FACIAL EXPRESSION ANALYSIS
Author:	ALI GHALI Dr. MHD BASSAM KURDY
Abstract:	Emotion recognition is a natural capability in human beings. However, if we are to ever create a humanoid “robot” that can interact and emote with its human companions, the difficult task of emotion recognition will have to be solved. The ability for a computer to recognize human emotion has many highly valuable real world applications. Consider the domain of therapy robots which are designed to provide care and comfort for infirm and disabled individuals. These machines could lever information on a patient’s current and evolving state of mind, in order to tailor personalized strategies for patient care and interaction. For example, when a patient is upset or unhappy, a more effective strategy may be take a moment to recognize the emotion and offer sympathy. Even outside of the realm of robotics, working with computers that have the ability to sense and respond to emotional state can go a long way to improve the quality of human-computer interaction (HCI). By designing HCI to be more like human-human interaction, we have the ability to create more natural, fulfilled, and productive working relationships with our machines. In this research we explain how to recognize emotions through digital images using Android application, and we will identify seven types of emotions (neutral- happy- sad- surprised- afraid- angry- disgusted). We designed this work based on a popular library called OpenCv, and the Fisherfaces algorithm that consists of (PCA) principle component analysis algorithm and (LDA) the linear discriminate analysis algorithm, in addition, we built the server using Java language to implement the android application, also we compare the coordinates of eyes and mouth in test image with the coordinates in the database to take the highest similarity and show the result. The language used to build this work is the Java language using NetBeans IDE 8.0.2, and the use of android studio to design android application.
Keywords:	OpenCv Library, Fisherfaces Algorithm, (PCA) Principle Components Analysis Algorithm,(LDA) Linear Discriminate Analysis, Server Architecture, Android Application.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	TRIO-SECURITY MODEL FOR SECURING DATA OF FILE SHARING IN MOBILE ENVIRONMENT
Author:	SITI RAHAYU SELAMAT, S.L. MUHAMMAD HAFIZUDDIN, ZAKIAH AYOP, ROBIAH YUSOF
Abstract:	Nowadays, mobile phone is a sharing medium to connect to one s own social network and larger society for its convenience and high-speed. Consequently, data breach incidents by unauthorized parties might often occur. Therefore, the aim of this study was to secure sensitive information in the CIA (Confidentiality, Integrity, Availability) triad. Data Security model, Trio-Security, was integrated within file sharing application as a solution to the problem as this model used three different integrated technologies namely Message Digest, Cryptography and Steganography to provide security for the CIA data. The most suitable and compatible algorithm for each technology was used for mobile environment specifications. The results of this project determined the quality of the output for each algorithm. Based on the results, the integration of Trio-Security model with the file sharing application was able to increase the security level when transferring sensitive data.
Keywords:	Trio-Security, File Sharing, Mobile, Cryptography, Steganography, Message Digest
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	THE IMPACT OF E-COMMERCE ADOPTION FOR SMALL AND MEDIUM ENTERPRISE IN DEVELOPING COUNTRY: A CASE STUDY UGANDA
Author:	ABUKAR MOHAMED, RUZZAKIAH JENAL, SITI AISHAH HANAWI
Abstract:	In order to attain achievement in this 21st century and capability facing more complex challenges, the small-medium enterprise (SMEs) in developing country needs to progress ideas based on economic and community. E-commerce has many benefits for SMEs in terms of faster communication within the firm and more efficient for managing resources of the firm. SME in developing countries has more challenges than from those developed countries in adopting e-commerce. E-commerce initiation by SMEs is still lesser in a figure, insufficient and only at the initial stages such as having email or website. The aim of this study is to focus on the ability to understand the knowledge regarding the SMEs’ adoption of e-commerce in developing countries such as Uganda, and at the same time developing an e-commerce adoption model for SMEs and then validating the model. This study runs into two phases by doing the preliminary study and the survey. During the preliminary study phase, the e-commerce adoption model is developed based on TAM model of perceived ease of use, perceived usefulness, perceived trust and intention to use. While in the survey phase as a quantitative method, the questionnaire is developed and then the sample is identified. After conducting the survey, the questionnaire is analyzed using the multiple linear regression analysis. Multiple linear regression analysis found that the factors of perceived ease of use and perceived usefulness are significantly and positively contributed to the factor of perceived trust. While perceived trust significantly and positively contributed to the factor of intention to use. This shows that perceived trust has great contribution in clarifying intention to use e-commerce in Uganda SMEs. The developed e-commerce adoption model is expected to help the Uganda SMEs towards the developing and accelerating of the e-commerce implementation. Thus, the developing country especially Uganda will be improving in terms of the e-commerce sectors.
Keywords:	E-Commerce; Small And Medium Enterprise; Adoption Model; Uganda.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	THE INFLUENCE OF KNOWLEDGE MANAGEMENT CAPABILITIES ON ORGANIZATIONAL EFFECTIVENESS
Author:	YOHANNES KURNIAWAN, ARVIN HARDIANTO, FENTY MEYLANI, WANDY
Abstract:	This research aims to evaluate the knowledge management that runs on startup companies and to find out the factors that can improve organizational effectiveness through the implementation of knowledge management. Articles related to "Knowledge Management" are collected through online journal databases. These articles are then reviewed and analyzed and then described in relation to the organizational effectiveness in "Knowledge Management". Then, data collection methods using questionnaires and data analysis using a single regression model with SPSS software are conducted. From the test results, it can be concluded that Knowledge Infrastructure Capability and Knowledge Process Capability influence the effectiveness or productivity of the company. Moreover, the results of this research are expected to provide an evaluation for the company through the analysis of knowledge management, and to find out what variables influence the organizational effectiveness through the implementation of knowledge management, as well as to provide suggestions and recommendations that can improve the organization effectiveness to achieve strategy using knowledge management.
Keywords:	Knowledge Management, Capabilities, Organizational Performance, Case Study, System
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	RATE ADAPTIVE MULTICAST VIDEO STREAMING OVER SOFTWARE DEFINED NETWORK
Author:	RAMAKRISHNA M, KARUNAKAR A K
Abstract:	Multicasting has always been a topic of importance when it comes to multiple receiving users. The participants are heterogeneous in terms of their capacity to process the video data and network technology. This capability difference affects the QoS and QoE of multicast video communication. In this work, we have developed a rate adaptive streaming mechanism to stream the video to meet the device and network constraints. The method uses SIP and SDP protocols to learn device constraints and link statistics to estimate the network resources. Later, this information is made available to the adaptation module to decide the video rate for streaming. We have implemented the method in the floodlight controller and streamed multiple rates of video over an SDN enabled network. The objective quality of the video is used for analysing the performance of the proposed adaptation technique.
Keywords:	Video Adaptation, Multi-Rate Video, Scalable Video Communication.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	THE METHODS AND TECHNOLOGIES OF RELIABILITY AND SECURITY OF INFORMATION SYSTEMS AND INFORMATION AND COMMUNICATION INFRASTRUCTURES
Author:	SEILKHAN BORANBAYEV, NIKOLAJ GORANIN, ASSEL NURUSHEVA
Abstract:	The article is devoted to the investigation of the problem of the reliability and security of information systems and information and communication infrastructure functioning. Some models and methods for calculating reliability and assessing of the information risks, and the tools for managing information security risks are considered. A review of the best experiences of countries with a high global cybersecurity index is made. The directions recommended to achieve the global cybersecurity index of Kazakhstan, established by the Cybersecurity Concept of the country ("Cybershield of Kazakhstan") are defined.
Keywords:	Information system, Reliability, Security, Risk, Method, Cybersecurity, Global Cybersecurity Index.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	REVIEW ON MATRIX PSEUDO-INVERSE USING SINGULAR VALUE DECOMPOSITION-SVD AND APPLICATION TO REGRESSION
Author:	BASHAR SAMI NAYYEF AL-DABBAGH, ZINAH MOHSIN ARKAH, RAJA DAAMI RESAN, LAITH ALZUBAIDI
Abstract:	Singular Value Decomposition (SVD) is one of the most factorization of the real or complex mathematical matrix problems. In this paper, one of the most significant applications of the Signa gular Value Decomposition (SVD) which is the Matrix decomposition is being selected to be described and explained as a regression model. The experimental results show that the SVD regression using Matrix-Pseudo Inverse results are more realistic and nearly as expected that the simple regression model when the results have been compared between the simple regression model and the SVD regression model based on the Matrix-Pseudo Inverse model based on implement them on the same dataset (data points). In this paper, two main cases are discussed. The first one is the insertable matrix pseudo-inverse, and the non-invertible matrix pseudo-inverse. Both cases are mainly discussed with a relative example given which shows that main approach that is used to compute based on the Singular Value Decomposition.
Keywords:	Singular Value Decomposition, SVD, Matrix Decomposition, Matrix-Pseudo Inverse, Regression.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	DIRECT CONTROL OF THE STATOR FLUX AND TORQUE OF THE THREE-PHASE ASYNCHRONOUS MOTOR USING A 2-LEVEL INVERTER WITH SINUSOIDAL PULSE WIDTH MODULATION
Author:	LOUBNA LAZRAK, SOUKAINA EL DAOUDI, CHIRINE BENZAZAH, MUSTAPHA AIT LAFKIH
Abstract:	This paper presents a direct control of the stator flux and torque of a three-phase asynchronous motor fed via a conventional voltage inverter to PWM pulse width modulation (sinus-triangle). This command uses PI type controllers, their parameters are determined from two control methods: The identification and the optimal symmetry criterion. The two-phase voltages obtained at the output of the PI regulators are compared with high frequency triangular signals to develop the control of the IGBTs of the inverter. The performance of the asynchronous motor control is verified by simulations under MATLAB / SIMULINK.
Keywords:	Direct Torque Control, Direct Flux Control, Induction Motor, PI Controller, Pulse Width Modulation, 2-Level Inverter, Optimal Symmetry Criterion
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	FOGGY DEGRADED IMAGES: A RESTORATION APPROACH UTILIZING NEURAL NETWORK
Author:	KHADER S. AL-AIDMAT, VENUS W. SAMAWI
Abstract:	Atmospheric problems such as fog or dust reduce visibility on roads. Car cameras with a suitable image restoration technique can be used to enhance automotive vision in a misty (foggy) weather. Foggy images can be restored by using a suitable filter (de-noise filter) to reconstruct a clear image from its degraded version. Accordingly, this paper aims to find a fog filter to restore foggy images in real time (as a step toward the development of automotive vision in foggy weather). Supervised neural network (SNN) is used as a technique to restore a foggy image to its original version. Although training SNN is time consuming (during training phase), the process of applying the generated fog filter on a foggy image (for restoration) is a rapid operation. For generating a fog filter, SNN is trained offline through mapping between a foggy scene and its corresponding original scene. The weight matrix, which is obtained from training the SNN, represents a fog filter. In this paper, seven approaches utilizing different feature sets are proposed. Each approach presents different neural network (NN) architecture. Image features are extracted from spatial and transformed domains using discrete cosine transform (DCT). DCT is applied locally to suppress noise components while ‎preserving the useful image ‎content. The seven fog filters (resulting from training the seven NNs) are evaluated empirically, using Peak signal-to-noise ratio (PSNR), and perceptually (based on judgment of expert persons). Their performances are compared to specify the effective fog filter and to determine the feature set that best suits the NN technique for restoring foggy images. The recommended approach has demonstrated its efficiency and usefulness in restoring moderately foggy images in real time.
Keywords:	Image restoration, Artificial Neural Network, Discrete Cosine Transform, Foggy Image Filter
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	RESEARCH ON KEY SECURITY STRATEGIES OF CLOUD COMPUTING
Author:	Saif Al-din M. Najim, Shokhan M. Al-Barzinji
Abstract:	The platform of Cloud computing is model based on Internet environment which enables an easy on-demand access and usage payment of each access and utilization of pool of networks that is shared among multiple users. This type of computing is considered as another innovation that fulfils users’ needs and requirements for resources of computing like stockpiling, systems, administrations and applications as well as servers. Securing the cloud’s stored Data is seen as one of the significant principles with many challenges and concerns in the research of cloud computing. This study has reviewed the research in a critical manner which focused on the types of cloud computing, industries, deployments and models of delivery. This constant issue is becoming more impactful because of the emerging challenges in cloud computing technology management. From the client’s point of view, the security in cloud computing is hazardous, typically in the matter of assurance affirmation problems and securing the data. These problems create shortcomings that hinder the adoption of cloud computing administrations. This paper inspects and illustrates the critical issues of cloud computing in relation to the privacy and protection on the Cloud. Lastly, this paper is concluded with a review to the literature stated as well suggesting on-going future studies.
Keywords:	Cloud computing, Data security, Data privacy, Cloud Cryptography, Security threats.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	AUCTION BASED DISPATCH MODEL IN ONLINE MOTORCYCLE TAXI SYSTEM
Author:	PURBA DARU KUSUMA
Abstract:	One problem in the existing online motorcycle taxi system is generalization among drivers. The generalization includes price, travel distance, and pickup distance. Meanwhile, both drivers and passengers cannot be generalized. For example, some drivers want to get higher price while other drivers want to take shorter travel distance. In the other side, some passengers want to get lower price while other passengers want to get lower waiting time. Based on these needs, in this research, we propose new online motorcycle taxi dispatch system that accommodates this various requirements. The proposed model is developed based on auction model. The auction is done automatically, sealed, and it is single round auction. In this research, the driver’s requirements are: maximum travel distance, maximum pickup distance, and price range. Meanwhile, the passenger’s requirements are: maximum waiting time and price range. There are three proposed models in this research. In the first model, pickup distance limitation is implemented. In the second model, travel distance limitation is implemented. In the third model, both pickup distance and travel distance limitations are implemented. In the test, besides comparing to each other, these proposed models are also compared with the previous nearest driver model. The test result is as follows. The previous nearest driver model performs the highest success ratio. The first model performs the highest average driver revenue. The third model performs the lowest average waiting time and average pickup distance.
Keywords:	Dispatch System, Online Motorcycle Taxi, Auction, Nearest Driver, Multi Agent.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	PRIVACY PRESERVING MINING OF WEB REVIEWS BASED ON SENTIMENT ANALYSIS AND FUZZY SETS
Author:	MOSTAFA A. NOFAL, SAHAR F. SABBEH, KHALED M. FOUAD
Abstract:	In the traditional Web, users are considered as information consumers. In social Web, users play a much more active role since they are now not only information consumers but also data providers. Users like online posting reviews which has become an increasingly popular way to express opinions and sentiments toward the products bought or services received. Analyzing these reviews can be helpful for collecting opinions of people about products, social events and problems and would produce useful actionable knowledge that could be of economic values to vendors and other interested parties. Thus, due to the huge number of reviews and their unstructured nature, efficient computational methods are needed for mining and summarizing these reviews, because regular analysis of reviews does not indicate user likes and dislikes. In a review, user typically writes about both the positive and negative aspects of the object, although the general sentiment toward that object may be positive or negative. That’s why sentiment analysis together with opinion mining try to extract and study of user’s opinions, sentiments and subjectivity of text. However, this analysis must come with careful consideration of user’s anonymity and the privacy of their sensitive data as privacy is today an important concern for both users and enterprises. In this research, automatic analysis of opinions (opinion mining) is performed to obtain such detailed aspects based on ontology. Opinion mining identify the features in the opinion and classify the sentiments of the opinion for each of these features. Opinion mining is a difficult task, owing to both the high semantic variability of the opinions expressed, and the diversity of the characteristics and sub-characteristics that describe the products and the multitude of opinion words used to depict them. In the proposed approach, the opinion polarity and polarity strength are measured using fuzzy set. As the fuzzy set theory is quite effective in processing natural languages, to measure the vagueness, it will also be effective in analyzing review articles, which are generally in natural languages. Additionally, the proposed system takes privacy into consideration by anonymizing data before final publishing. Methods of generalization and micro-aggregation are utilized for anonymizing quasi-identifiers to maintain the balance between data utility and user privacy.
Keywords:	Sentiment Analysis, Sentiments Classification, Privacy Preserving, Sentiment Feature Extraction, Fuzzy Sets.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	IMPACT OF MIMO SCHEMES OVER QOS BASED INDEPENDENT CARRIER SCHEDULING ALGORITHM FOR DOWNLINK 5G LTE-ADVANCED NETWORKS
Author:	HAITHAM S BEN ABDELMULA, M. N.MOHD WARIP, ONG BI LYNN, NAIMAH YAAKOB
Abstract:	Carrier Aggregation (CA) and Multi-Input Multi-Output are a promising techniques which invented by 3GPP to support next generation of all IP mobile networks “5G Long Term Evolution-Advanced (LTE-A) network” with extreme virtual bandwidths, for providing unprecedented speed of transmission rate and minimal latency. To the best of our knowledge, an efficient user-level QoS provisioning for multi-services multi-users deployment scenario is of vital importance in 5G LTE-A systems. One of the main challenges to meet the user level Quality-of-Services (QoS) demands for diversified services “Real-Time (RT) and Non-Real-Time (NRT) traffic” is to offer robust and suitable resource scheduling algorithm. However, different MIMO system schemes have various delays in the feedback reporting, resulting lead degradation in QoS performance where accurate feedback is difficult to achieve. In this paper, authors investigate the impact of divers MIMO schemes on the proposed QoS based Independent Carrier Scheduling (QoS-ICS) algorithm in order to find the optimum transmission mode which is exploited for guaranteeing the user QoS performance among different users. Firstly, the QoS-ICS exploits the round robin with service concept which assigns the CCs among users equally based on the user’s service. Secondly, for PRBs-Scheduler, the adopted user-level QoS aware packet scheduling relies on different service utility factor was computed in order to achieve QoS performance. Furthermore in this paper, two different MIMO system schemes are considered, Open Loop Spatial Multiplexing (OLSM) and Closed Loop Spatial Multiplexing (CLSM). Simulation results reveal that the proposed QoS-ICS scheme has achieve the QoS requirements for real-time users and meets the user’s throughput demands of NRT streaming video, especially in CLSM transmission scheme when compared with conventional ICS algorithm.
Keywords:	Carrier Aggregation (CA), MIMO Schemes, 5G, LTE-Advanced, ICS, QoS-ICS, Service Utility Factor, OLSM, CLSM.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	MODEL FOR MEASURING MULTIPLE FACTORS IN E-LEARNING SYSTEMS’ ADOPTION IN MALAYSIAS UNIVERSITIES: AN EXPERIENCE FROM MANAGEMENT AND SCIENCE UNIVERSITY (MSU)
Author:	DEOGRATIUS MATHEW LASHAYO, MOHAMMED HAZIM ALKAWAZ, MD GAPAR MD JOHAR
Abstract:	The problem of finding comprehensive model to measure e-learning systems’ adoption in universities is the global agenda like Malaysia in particular. This problem has been contributed by limited factors of existing models. The main purpose of this research study is to develop the robust multi-factors model for measuring adoption of e-learning systems in Malaysia’s universities with special focus in the Management and Science University (MSU). This research study is addressing this problem by adopting preliminary factors suggested by Lashayo and Gapar in their model in 2017, the model was initial tested at Open University of Tanzania (OUT) in Tanzania. The same factors will be integrated together and validated against the sample of 142 students from Management and Science University (MSU) in Malaysia. The Structural Equation Modelling (SEM) is used in analysis of the collected data. The results show that the model with eleven factors is significant measuring e-learning systems’ adoption with 65.3% coefficient of determination which implies that the model with adequate number of factors capture well the needs of e-learning systems in Malaysia. These results aimed at providing a tool for measuring e-learning systems’ adoption in universities and it further enhances the strategy and policy of information technology/e-learning managers in their efforts of adopting and measure these systems. The novelty of this research lies in the unique set of integrated multi-factors model developed especially addition of the following constructs: Trust, Environmental Factors and University Readiness on DeLone and McLean (2003) Information System Model
Keywords:	E-learning system, Universities, Factors, Model, Malaysia
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	FINGERPRINTS MATCHING USING THE ENERGY AND LOW ORDER MOMENT OF HAAR WAVELET SUBBANDS
Author:	ZAINAB J. AHMED
Abstract:	Fingerprint recognition is one among oldest procedures of identification. An important step in automatic fingerprint matching is to mechanically and dependably extract features. The quality of the input fingerprint image has a major impact on the performance of a feature extraction algorithm. The target of this paper is to present a fingerprint recognition technique that utilizes local features for fingerprint representation and matching. The adopted local features have determined: (i) the energy of Haar wavelet subbands, (ii) the normalized of Haar wavelet subbands. Experiments have been made on three completely different sets of features which are used when partitioning the fingerprint into overlapped blocks. Experiments are conducted on FVC2004 databases that have a four database; every database is eighty fingers and eight impressions per finger. The implemented recognition results of the proposed system show high recognition performance which is 100%.
Keywords:	Fingerprint Recognition, Identification System, Energy, Normalize, Haar Wavelet.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	EMPOWERMENT OF CSE-UCLA MODEL BASED ON GLICKMAN QUADRANT AIDED BY VISUAL APPLICATION TO EVALUATE THE BLENDED LEARNING PROGRAM ON SMA NEGERI 1 UBUD
Author:	P WAYAN ARTA SUYASA, PUTU SUKMA KURNIAWAN, I PUTU WISNA ARIAWAN, WAYAN SUGANDINI, NI DESAK MADE SRI ADNYAWATI, I DEWA AYU MADE BUDHYANI, DEWA GEDE HENDRA DIVAYANA
Abstract:	The purpose of this research was to obtain information about effectiveness level of blended learning program implementation on SMA Negeri 1 Ubud through evaluation result evaluated from the component of system assessment, program planning, program implementation, program improvement, program certification by using CSE-UCLA model based on Glickman quadrant aided by visual application. Besides, this study also aims to obtain information about the constraints found in the implementation of blended learning program on SMA Negeri 1 Ubud. The approach used in this research was qualitative with an evaluative method. The evaluation design used in this research was the CSE-UCLA model, which consists of five evaluation components, such as system assessment, program planning, program implementation, program improvement, and program certification. Subjects involved in this research, consist of head of school, head of computer laboratory, and two Information technology teams, all subjects involved during the interview. The activity to obtain data from questionnaire distribution results, it involves five teachers and ten students. Determination of all research subjects using purposive sampling technique. The results showed good category on the effectiveness of blended learning program implementation on SMA Negeri 1 Ubud. Those statement reinforced by an evaluation based on the Glickman quadrant aided by visual application, where the evaluation results lie in the ‘Good’ quadrant, which is indicated by a combination of + + + - + values for each evaluation components.
Keywords:	CSE-UCLA, Evaluation, Glickman Quadrant, Blended Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	ENHANCING AODV ROUTING PROTOCOL BASED ON DIRECTION AND VELOCITY FOR REAL-TIME URBAN SCENARIO
Author:	NADIA M. ALFAHAD, SALAH A. ALIESAWI, FOAD SALEM MUBAREK
Abstract:	Vehicular ad-hoc network (VANET) considers as a promising technology to support the communication between vehicles, and between vehicles and road side units. A reliable routing algorithm for such networks is challenging task because of high mobility and periodic changes of the network topology. To improve the performance of ad-hoc on demand vector (AODV) protocol in VANET, the routing overheads should be reduced by reducing the transferred control packets that consumes portions from the available bandwidth. In urban environments, the network topology plays an essential role in traffic optimization in terms of mobility patterns, and also in the connectivity and available infrastructure. Further, the road intersections come with many configurations and their definition significantly affects mobility and connectivity. However, the increased number of nodes and movements in such environments will add additional routing overheads to the current overheads in AODV protocol. In this paper, URBAN-AODV (U-AODV) routing protocol is proposed for use in real map topology VANET for urban conditions as in USA, Chicago city. In proposed U-AODV protocol, new fields based on velocity and direction of vehicles are added in request packet and routing table to decrease the transferred control packets. The performance of the proposed protocol is studied and compared with the original AODV using different metrics and statistical tools in real-time world urban VANET control vehicles mobility in two lines and urban intersections. Results demonstrate that U-AODV has dissimilar values in overhead ratio in both density and vehicles velocity, while in end to end (E2E) delay metrics the U-AODV was faster than original AODV and cause low ratio in delay in both different vehicle density and velocity.
Keywords:	NS2, VANET, AODV, Urban, Overhead
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	CCC: AN APPROACH FOR DETECTION THE MASS OF BREAST CANCER IN MAMMOGRAM IMAGES
Author:	MOHAMMAD ALFRAHEED
Abstract:	Due to the need to early detection of the breast cancer, the mammogram images are taken for cancer patient. The poor visibility and weak contrast are usually highlighted as challenges in such mammogram images. These challenges decrease normally the accuracy in computerized mammogram image segmentation. In this work, an effective method has been developed to detect and extract the cancer mass for breast cancer from mammogram images. The proposed method has been developed to first, extracting the breast area (i.e. foreground area) from other objects in mammogram image (i.e. background area). Second, the Mahalanobis distance value has been introduced as a solution for detecting the cancer mass from objects in breast area. The idea behind using the Mahalanobis distance value is the need to decrease the computation complexity and increase the detection accuracy. In addition, the running time of the proposed method has to be reduced. Therefore, the proposed method reduces the running time to approximately 1.2 second. Compared to other methods, the proposed method reduces the running time and avoids the training stage of the cancer mass detection. Furthermore, the proposed method does not resize the original mammogram image in order to keep the original details of the cancer mass.
Keywords:	Breast Cancer, Mammograms Images, Segmentation, Detection
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	PREDICTING THE STOCK PRICE TRENDS USING A K-NEAREST NEIGHBORS-PROBABILISTIC MODEL
Author:	LOCK SIEW HAN, MD JAN NORDIN
Abstract:	This paper examines a hybrid model which combines a K-Nearest Neighbors (KNN) approach with a probabilistic method for the prediction of stock price trends. One of the main problems of KNN classification is the assumptions implied by distance functions. The assumptions focus on the nearest neighbors which are at the centroid of data points for test instances. This approach excludes the non-centric data points which can be statistically significant in the problem of predicting the stock price trends. For this it is necessary to construct an enhanced model that integrates KNN with a probabilistic method which utilizes both centric and non-centric data points in the computations of probabilities for the target instances. The embedded probabilistic method is derived from Bayes’ theorem. The prediction outcome is based on a joint probability where the likelihood of the event of the nearest neighbors and the event of prior probability occurring together and at the same point in time where they are calculated. The proposed hybrid KNN-Probabilistic model was compared with the standard classifiers that include KNN, Naive Bayes, One Rule (OneR) and Zero Rule (ZeroR). The test results showed that the proposed model outperformed the standard classifiers which were used for the comparisons.
Keywords:	Stock Price Prediction, K-Nearest Neighbors, Bayes’ Theorem, Naive Bayes, Probabilistic Method
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text

Title:	A SOLUTION FOR TRAVELING SALESMAN PROBLEM USING GREY WOLF OPTIMIZER ALGORITHM
Author:	AMEEN SHAHEEN, AZZAM SLEIT, SALEH AL-SHARAEH
Abstract:	This paper presents an algorithm based on Grey Wolf Optimizer (GWO) for solving the Traveling Salesman Problem (TSP), which is called (GWO-TSP). Traveling Salesman Problem is a well-known NP-Hard problem in optimization which aims at finding the shortest path between cities, where each city must be visited exactly once. The GWO is a recently established meta-heuristic algorithm for solving optimization problems which has successfully solved many optimization problems. GWO-TSP has been compared with well-regarded algorithms such as: Chemical Reaction Optimization (CRO) and Genetic algorithm (GA). In addition, GWO-TSP has been evaluated analytically and by using simulations in terms of error rate and execution time. The algorithms are tested on a number of benchmark problems. Experimental results show that GWO is promising in terms of optimal cost, error rate and standard deviation in comparison with other algorithms.
Keywords:	Grey Wolf Optimizer, Traveling Salesman Problem, Optimization Problems, Meta-Heuristic.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2018 -- Vol. 96. No. 18 -- 2018
Full Text