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

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

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

Journal of Theoretical and Applied Information Technology
October 2017 | Vol. 95 No.19

Title:	RULES REDUCTION AND OPTIMIZATION OF FUZZY LOGIC MEMBERSHIP FUNCTIONS FOR INDUCTION MOTOR SPEED CONTROLLER
Author:	ZULHISYAM SALLEH, MARIZAN SULAIMAN, FIZATUL AINI PATAKOR, ROSLI OMAR
Abstract:	Fuzzy logic controllers are widely used in induction motor drives systems for their robust performance. Several techniques have been promoted to lessen the computational burden and memory constraint for implementation of fuzzy logic controller in software and hardware. Rules reduction and optimization of fuzzy logic membership functions have been tested with full, medium and low speed under forward and reverse operation of induction motor using Matlab/Simulink. The simplified fuzzy rules and membership functions were analyzed on the design and simulation of the controller for vector control induction motor. The drives system was simulated with standard membership functions through 25 rules and simplified rules such 9 rules, 7 rules and proposed 5 rules for overview comparison. The simplified rules were simulated using optimization membership functions. The results of this investigation show that Optimized5 give exceptional performance for both forward and reverse operation at rated speed with no load condition. There were less than 1% overshoot ascend for Optimized5 while tested in medium and low speed environment. These investigations confirmed that Optimize5 firmly rejected load disturbances with same short period for different speed. As a result, the consideration of optimize membership functions is significant when apply rules reduction for robust speed controller.
Keywords:	Fuzzy Logic, Induction Motor, Membership Functions, Rules, Speed Controller, Optimization
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	A REVIEW OF INTRINSIC MOTIVATION ELEMENTS IN GAMIFIED ONLINE LEARNING
Author:	RUJIANTO EKO SAPUTRO, SAZILAH BINTI SALAM, MOHD HAFIZ ZAKARIA
Abstract:	The advent of information and communication technology provides the opportunity and convenience to anyone to be able to follow online-based learning, so that teaching and learning can be arranged without limits of space and time. Today, online-based learning is offered by many higher education institutions and commercial industries. A variety of strategies to increase student motivation approach on online-based learning has been studied, one of them by using gamification approach. Previous researches were found to adopt motivational theories to stimulate the intrinsic and extrinsic level of gamification approach in education, According to the promise of gamification to enhance the intrinsic motivation of students based on elements of motivation through online-based learning, in this research, we focus on examining; 1) How the application of gamification in online-based learning is, 2) what game design elements that exist in the gamified-based online learning are, and 3) how to increase student motivation in gamified-online learning based on intrinsic motivation elements. The results of our study showed that gamification on online based learning increased, both regarding to utilization, approaches, methods, testing and determination of game design elements are used. Gamification also gave positive impact on student motivation in learning, although it depended on various factors and conditions. We provided reviews and examples based on the literature for the designer in determining the game design elements based on intrinsic motivation elements in the online-based learning.
Keywords:	Gamification, Online Learning, Game Design Elements, Intrinsic Motivation Elements
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	CHRONOLOGY OF BRAIN TUMOR CLASSIFICATION OF INTELLIGENT SYSTEMS BASED ON MATHEMATICAL MODELING, SIMULATION AND IMAGE PROCESSING TECHNIQUES
Author:	NORMA ALIAS, YASEEN ALWESABI, WALEED MUGAHED AL-RAHMI
Abstract:	Tumor classification using image processing techniques is becoming a powerful tool nowadays. Based on the importance of this technique, the motivation of this review paper is to present the chronology of brain tumor classification using the digital images and govern the mathematical modeling and simulation of intelligent systems. The intelligent system involves artificial neural network (ANN), fuzzy logic (FL), support vector machine (SVM), and parallel support vector machine (PSVM). The chronology of brain tumor classification presents the latest part of the literature reviews related to the principal, type and interpretation of segmentation and classification of brain tumors via the large digital dataset from magnetic resonance imaging (MRI) images. This paper has been classified the modeling and simulation in classical and automatic models. Around 115 literature reviews in high ranking journal and high citation index are referred. This paper contains 6 contents, including mathematical modeling, numerical simulation, image processing, numerical results and performance, lastly is the conclusion to standardize the frame concept for the future of chronological framework involving the mathematical modeling and simulation. Research outcome to differentiate the tumor classification based on MRI images, modeling and simulation. Future work outlier in segmentation and classification are given in conclusion.
Keywords:	Tumor Classification, Chronology, Intelligent Systems, Mathematical Modeling And Simulation, Numerical Results And Performance
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	FROM LIVE INTERACTION TO VIRTUAL INTERACTION: ADDRESSING MORAL ENGAGEMENT IN THE DIGITAL ERA
Author:	MIFTACHUL HUDA , MARAGUSTAM SIREGAR , RAMLAN , KAMARUL SHUKRI MAT TEH , HAMDAN SAID , EZAD AZRAAI JAMSARI , SRI KARTIKA A. RAHMAN , JAMILUDDIN YACUB , M. IHSAN DACHOLFANY , WIDHIYA NINSIANA
Abstract:	The interaction among the society at large has been shifted from direct interaction to virtual one across borderless space. However, it seems to have led to emerge the challenging issues such as cyber bullying, uncertain information and etc. An exposure on moral engagement such as trust, care, friendship, and commitment needs to pay a serious attention to provide a foundational framework in driving the user interaction in the digital era. This paper aims to explore the moral engagement in underlying virtual interaction by providing an innovative way to help the human society in a good life. This study attempts to investigate the moral engagement which can underlie the interaction from live to virtual basis. To achieve this, literature review from peer reviewed journals, conferences and books was conducted to propose the framework model of strengthening moral engagement in the digital era. By using keywords on moral values and live and virtual interaction, multiple research findings can be achieved from met-synthesis with integrating, evaluating and interpreting process. As a result, phenomenological and grounded theories and ideas extracted to identify their common features, elements, and functionalities can be integrated and used to propose a framework model. The findings reveal that to exposure the moral engagement with professional and ethical basis associated with the instructional strategy and application in virtual interaction, reference model demonstrates how the human with all the potency they behave can become a significant contribution to the society at large to enhance the abilities to improve their capacities to operate the technological tools wisely and appropriately. Considering the way to go further with more challenging issues in the virtual interaction like cyberbullying, uncertain information and etc., exploring moral engagement should be regarded to provide the framework of interactional basis with human communities such as trust, care, friendship, and commitment.
Keywords:	Live Interaction, Virtual Interaction, Moral Engagement, Digital Era
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	A HYBRID METHOD OF RULE-BASED AND STRING MATCHING STEMMER FOR JAVANESE LANGUAGE
Author:	FATKHUL AMIN, WIWIEN HADIKURNIAWATI, SETYAWAN WIBISONO, HERNY FEBRUARIYANTI, JATI SASONGKO WIBOWO
Abstract:	Language is rich in morphological variations but poor in linguistic computational resources. Ngoko Javanese language is a morphologically rich language that has a different variant form of words. This paper describes an algorithm by which a stem for Ngoko Javanese language. Ngoko Javanese language stemmer is efficiently used in information retrieval. Through this algorithm, we can get a root from its actual word. We use a hybrid rule-based and string matching algorithm. Special rules are created to remove the prefixes and suffixes of the Ngoko Javanese terms. The algorithm has been tested on hundreds of Ngoko Javanese words. Results reveal that the accuracy reaches to about 67%.
Keywords:	Javanese Language, Stemming, String Matching, Rule Based Algorithm
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	WAVELET NEURAL NETWORK-BASED STABILIZER FOR ELECTRIC POWER SYSTEM STABILITY IMPROVEMENT
Author:	RUDY GIANTO
Abstract:	The application of adaptive control technique or procedure in designing control coordination of power system stabilizers is presented in this paper. The design is based on the use of a wavelet neural network which adjusts the parameters of the stabilizers to achieve system stability and maintain optimal dampings as the system operating condition and/or configuration changes. The developed wavelet neural network-based adaptive stabilizer is tested with a representative multi-machine power system. The test results show that the proposed adaptive stabilizer can maintain and improve the stability even with the changes of system operating conditions and configurations.
Keywords:	Wavelet Neural Network, PSS, Adaptive Stabilizer, Power System, Stability
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	THE DIGITAL FORENSIC ANALYSIS OF SNAPCHAT APPLICATION USING XML RECORDS
Author:	MUKHLIS PRASETYO AJI, IMAM RIADI, AHMAD LUTFHI
Abstract:	The use of social media such Snapchat is quite popular in the United States. It is a free chatting application that allows the users to send images and videos, but it will remove the postings temporally. Uploading improper images and videos on social media becomes recent trends done by teens, even children. They do not realize the negative impact of posting their personal images and videos in virtual public area; it can trigger cyber-bullying and sexting. Some previous researches on the issue observed whether or not the files of image and video uploaded in Snapchat are really removed permanently. The researchers also observed whether or not metadata trace relating to images and videos location that have been sent by the users, and where Snapchat saves the files sent by them. The previous researchers found digital evidences of XML Records relating to Snapchat in saving images on a folder named com.snapchat.android_preferences.xml. The folder contains important information. The other things is existence of a folder named received_image_snaps. It contains program/s for removing files; it is “.nomedia” extention. If a directory has a file named “.nomedia” extention, so the hardware saving media would not scan and record metadata file in the directory.Therefore, this research is expected to reveal where Snapchat saves the data, how to recover images or videos, and how the correlation between XML Records and image name on Snapchat. Therefore, it is important to know the related files in XML records and image name to ease and accelerate investigation process.
Keywords:	Digital Forensics, Snapchat, XML records.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	THE ACCOUNTING INFORMATION SYSTEM QUALITY IMPROVEMENT THROUGH INTERNAL CONTROL AND TOP MANAGEMENT SUPPORT EFFECTIVENESS
Author:	AZMI FITRIATI, AZHAR SUSANTO
Abstract:	Information is needed for effective decision making. Thus, quality accounting information generated by a qualified accounting information system. This study uses two components of the DeLone & McLean Information System Success Model such as system quality and information quality which identified as the entry key to the information system succeess. Besides, internal control and top management support are important factors that affect AIS quality. The objectives of this study are to measure (1) the influence of internal control and top management support on AIS quality and (2) the influence of AIS quality on the quality of accounting information. The population were Muhammadiyah higher education institutions and choosing samples by simple random sampling technique. PLS-SEM was used as an analytical tool. Primary data were collected by questionnaires as research instruments. The results have shown that the AIS quality can be reflected by integration, flexibility, ease of use and accessibility dimensions. Thus, the quality of accounting information was reflected of relevant, accurate, timely and complete dimensions. Besides, AIS quality was enhanced by the effective implementation of internal control and top management support. The implementation of qualified AIS had been caused accounting information to be qualified as well.
Keywords:	Internal Control, Top Management Support, Information System Success, Accounting Information System Quality, Accounting Information Quality
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	OPTIMAL COMPLEX WEIGHTS ANTENNA ARRAY WITH EFFICIENT FUZZY PARTICLE SWARM OPTIMIZATION ALGORITHM
Author:	BRAHIMI MOHAMED, KADRI BOUFELDJA
Abstract:	In this article, a stochastic optimization technique called fuzzy particle swarm optimization (FPSO) is presented to determine an optimum set of microstrip antenna arrays excitation weights (amplitude and phase), the use of the fuzzy controller allows to dynamically adjust its parameters such as, the inertia weight and acceleration coefficients in order to produce an optimal pattern of the antenna array able to approach a desired pattern. Simulation results are proposed to compare with published results to verify the effectiveness of the suggest method for both linear and planar array.
Keywords:	Fuzzy Controller, Linear Array, Particle Swarm Optimization, Pattern Synthesis, Planar Array
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	A SELF ORGANIZED SPECTRAL KEY AUTHENTICATION FOR SECURED TRANSMISSION IN MANET
Author:	PROF. CHIDAMBAR INAMDAR, DR. CHANDRASEKAR C, DR. S. NITHYA REKHA
Abstract:	A Mobile Ad hoc Network (MANET) is a system of wireless mobile nodes that dynamically self-organized and temporary network topologies. MANET is a collection of wireless networks which consists of large number of mobile nodes. Nodes in MANETs are connected wirelessly without fixed infra structure. Due to the nodes mobility, the wide range of intrusion takes places in MANET. Therefore, security in data packet transmission between the mobile nodes plays major role in MANETs. In order to improve the secured transmission, Self Organized Spectral Key Authentication (SO-SKA) technique is introduced in MANET. Initially, the public and public key certificate of each mobile node in MANET is generated by the mobile node itself. Secondly, the trust values of the mobile nodes with their neighboring nodes are measured regarding the data packet forwarded and dropped to improve the security factor. Finally, Spectral clustering is applied to group the mobile nodes and certificate exchange Key authentication helps the mobile nodes to authenticate themselves with their neighboring mobile nodes to improve the data packet transmission. The simulation is carried out to analyze the performance of proposed SO-SKA technique with the parameters such as data packet delivery ratio, Average end to end delay and data packet security level.
Keywords:	Mobile Ad Hoc Networks, Self Organizing, Public Key, Public Key Certificate, Trust Value, Spectral Clustering, And Key Authentication
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	GRAPH BASED SIMPLIFIED CRACK MODELING IN BATIK PATTERN GENERATION
Author:	PURBA DARU KUSUMA
Abstract:	Crack pattern is very rare in traditional or classic batik pattern. So, it is very challenging to explore crack pattern as batik pattern. Unfortunately, existing crack model or crack propagation model is very complex so that it is very resource consuming because crack modeling usually is used in mechanical engineering which is needed exact calculation. In the other hand, in computer based batik pattern generation, algorithm must be simple so that batik pattern can be generated fast. Exact calculation is not necessary in batik pattern generation. In this research, we propose simplified crack modeling and it is implemented in batik pattern generation. This proposed model is developed based on graph model. The proposed model adopts crack characteristics, such as: initial stress, energy reduction, and material resistance or toughness. Crack propagates randomly in certain direction. This model has been successfully implemented in generating batik pattern. Improvisations occur both in batik object pattern and background image. Based on the test, crack split probability has positive linear relation with number of crack segments and number of split activities. Ratio between initial energy and energy reduction has positive linear relation with the number of crack segments.
Keywords:	Crack, Graph, Batik, Traditional Pattern.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	ON ARABIC OBJECT CHARACTER RECOGNITION USING DYNAMIC TIME WARPING
Author:	ABDELWADOOD MESLEH, OMAR ARABEYYAT, SHARHABEEL ALNABELSI, JAMAL AL-NABULSI
Abstract:	Due to the large volume of Arabic texts in many generated and historical documents, it is essential to use computers in order to make generated texts editable, this is actually the main task of Arabic Object Character Recognition (OCR) systems. The task of automatically OCRing is to type documents within close-to-human performance, such OCR system is still an open research problem. In this paper, we propose an Arabic OCR based on Dynamic Time Warping (DTW) algorithm that is empowered to properly recognize Arabic words. Rather than using the usual practice of character segmentation, this paper proposes a segmentation of Arabic texts into lines and characters. The proposed Arabic OCR algorithm overlaps the segmentation and the recognition processes – an online segmentation-recognition. That is, in order to overcome the challenges of segmenting highly cursive Arabic texts into isolated characters. The accuracy of the proposed Arabic OCR algorithm is tested on randomly selected articles from Jordanian newspapers. Interestingly, results demonstrate the robustness of our proposed Arabic OCR algorithm that achieves 96.2% character recognition accuracy in the worst case.
Keywords:	Object Character Recognition, Dynamic Time Warping, Online Arabic OCR, Typed Arabic OCR
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	OPTIMIZATION OF PID CONTROLLER USING GENETIC ALGORITHM FOR MISSILE’S AUTOMATIC STEERING SYSTEM
Author:	MOHAMMAD ISA IRAWAN, IMAM MUKHLASH, FEDRIC FERNANDO
Abstract:	Missiles steering system is one of systems that use Proportional Integral Derivative (PID) controller. The difficulty in using this controller is tuning the parameters, because PID controller uses 3 controllers. There are a lot of different ways to get values of the controller’s parameters, such as using classical method or even using evolutionary algorithms. One of evolutionary algorithms is Genetic Algorithm (GA). GA is a search algorithm that is based on genetic principles and usually used in optimizing systems. In this research, performance of the controller that is obtained using GA and using conventional method (i.e. Ziegler-Nichols (Z-N)) are compared in order to optimize missile’s steering system. The result of the simulation shows that PID controller obtained using GA is faster in making the system going towards the setpoint than PID controller obtained using Z-N method. Furthermore, parameters of PID controller from GA make system more robust than parameters from Z-N.
Keywords:	Parameter Optimization, PID Controller, Ziegler-Nichols, Genetic Algorithm (GA)
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	HAND WRITTEN CHARCTER RECOGNITION USING NEURAL NETWORK AND DEEP BELIEF NETWORK
Author:	MAJID HAMEED KHALAF, BELAL AL-KHATEEB, RABAH NORY FARHAN
Abstract:	In this paper a comparison is done between two classification architectures, those are Standard Neural Networks (NN) that contain one hidden layer and Deep Learning concept using Deep Belief Networks (DBN). Both algorithms are applied on Capital English Character with same architectures and parameter for comparison purpose. The Standard Neural Network was trained as a supervised learning using Back Propagation (BP) algorithms while Deep Belief Network was trained using two phases of learning, the first phase as unsupervised learning using Contrastive Divergence (CD) algorithm and the second phase as a supervised learning using Back Propagation algorithms for fine tuning the network. Each character represented as an image in grayscale pixels. The features are extracted depending on the intensity of pixel in image that white color represents as a 0’s and black color represent as a 1’s. DBN is represented as a stack of Restricted Boltzmann Machines (RBM). The DBN learning procedure undergoes a pre-training stage and a fine-tuning stage. DBN gave a higher performance as compared with the Standard neural networks with an accuracy of approximately 92.3% for a classification of Capital English handwritten characters.
Keywords:	Backpropagation, Supervised Learning, Contrastive Divergence, Character Recognition, Deep Belief Networks
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	A OT-k LABEL LEARNING CLASSIFICATION BASED ON ASSOCIATION RULES FOR MULTI-LABEL DATASETS
Author:	L. KIRAN KUMAR REDDY, Dr. S. PHANI KUMAR
Abstract:	The real-world application has grown in need of heterogeneous data classification for almost all kind of datasets. The complexity in learning a class for a single object which is associated with multiple label sets is a key problem for multi-label datasets. Existing methods might be unfavourable for classification as each label consists of specific features characterization. This paper propose a One-To-k (OT-k) Label learning method through exploiting the labels characterization and using association rules to discover label dependencies for the classification. The main objective is to find One-Label which will be highly suitable for class suggestion using a OL-Prediction Table and k-labels to constructs a patterns of labels to deal with the multi-label database classification. The efficiency of OT-k is verified against other multi-label learning algorithms. The result analysis shows an improvisation in different case studies being performed.
Keywords:	Label Learning, One-To-K, Pattern, Classification, Association Rules, Multi-Label Datasets
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	INSIDER RISK PROFILE MATRIX TO QUANTIFY RISK VALUE OF INSIDER THREAT PREDICTION FRAMEWORK
Author:	ISZAIDA ISMAIL, ROHAYANTI HASSAN, MUHAMMAD RAZIB OTHMAN, ASRAFUL SYIFAA AHMAD, NADA ELYA TAWFIQ
Abstract:	An insider threat refers to the threat arising from an individual inside an organization that maliciously leverages his or her system privileges, and closeness and proximity in a computerized environment to compromise valuable information and inflict harm. This scenario is an example of system violation that decreases the degree of system trustworthiness. Most cases of system trustworthiness use a peer judgment formulation, which may involve bias sentiments towards document sensitivity values. Moreover, audit trails of risky document navigation paths are important as an alarm to indicate any violation. Therefore, this study presents a combination of the trust criteria and document sensitivity level of an insider to obtain a risk value, which will be used to predict the occurrence of an insider threat. This study begins by investigating the prominent attributes of insiders with a focus on their degree of experience and skill in line with system trust. Subsequently, these prominent attributes are used to construct an insider Trust Profile Matrix (TPM). From the TPM, the trust value is calculated and combined with the sensitivity value of each document to produce a Risk Matrix (RM). As a result, (i) risk value and (ii) prediction rate and risky path are then calculated and analyzed using an Insider Threat Prediction Framework as an alarm for violation occurrence.
Keywords:	Insider Threat, Insider Threat Prediction, Sensitivity Level, Trust Value, Risk Value
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	ROBUST EDGE DETECTION BASED ON CANNY ALGORITHM FOR NOISY IMAGES
Author:	HAIDER O. LAWEND, ANUAR M. MUAD, AINI HUSSAIN
Abstract:	The aim of many edge detection techniques is to highlight edges in an image. However, due to nature of the edge detection that is based on the derivative operation, this process often amplifies noises too. Therefore, there is always a trade-off in the edge detection technique between extracting information and suppressing noise. There is variety of edge detectors or operators with different sizes of kernel. This paper proposes an edge detection technique based on traditional Canny edge detector. Unlike many established edge detection techniques that focus on the gradient in grayscale image, the proposed technique includes two more features: the length and the directional change of the edges. The inclusion of the two features helps to increase the robustness of the proposed technique towards noise. The proposed technique is tested with synthetic and natural images. Results are compared with other established edge detection techniques and demonstrate that the proposed technique is able to detect low contrast edges and highly resistance to different types of noise. As a result, the trade-off between the information and noise in image edge detection is reduced.
Keywords:	Canny Edge Detection; Edge Gradient; Edge Length; Directional Change; Noise Suppression.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	DEVELOPMENT OF MATHEMATICAL MODELS AND SOFTWARE OF FLOW DISTRIBUTION: THE PROBLEM OF EVACUATION
Author:	AMIRGALIYEV YEDILKHAN, KALIZHANOVA АLIYA, KOZBAKOVA АINUR, KENSHIMOV CHINGIZ, SHAMILUULU SHAHRIAR
Abstract:	The paper herein is dedicated to mathematical models and software development for evacuation problems in emergency situations at educational organization, there is offered the problem solution method and algorithm, allowing to structure the evacuation optimal plan, changing in real time, according to a time-table and people amount. The optimization task is proposed and algorithms to find maximum flow on limited base are proposed.
Keywords:	Algorithm, Evacuation, Stream Of People, Optimal Plan, Software
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	IMPLEMENTATION OF LIGHTWEIGHT CRYPTOGRAPHIC PRIMITIVES
Author:	BARAA TAREQ HAMMAD, NORZIANA JAMIL, MOHD EZANEE RUSLI, MUHAMMAD REZA ZABA, ISMAIL T. AHMED
Abstract:	Lightweight cryptography is not a new branch in cryptography. It is a subject specifically addressing the implementation of security mechanism in pervasive computing that are characterized by smart but resource constrained devices. There are at least two main lightweight symmetric cryptographic primitives namely lightweight block cipher and lightweight hash algorithm. Most of the previous surveys were focusing on implementation of specific cryptographic primitives. In this paper we present a comprehensive survey of all lightweight symmetric cryptographic primitives, from hardware and software perspectives. The survey covers analysis of these algorithms and a comparison between these primitives in terms of throughput, number of cycle, comprehensive area, power, and energy. We also provide a classification of the structure of lightweight block cipher and lightweight hash function. These classifications are very useful because the primitives have different and sometimes contrary characteristics. Finally this comprehensive survey highlights some of the issues related to security aspect of small key length in lightweight cryptographic primitives.
Keywords:	Lightweight Cryptography, Symmetric Cryptography, Block Cipher, Hash Function
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	THE DRIVERS OF ERP CLOUD COMPUTING FROM AN INSTITUTIONAL PRESPECTIVE
Author:	MOHAMMAD ATWAH AL-MA AITAH
Abstract:	The purpose of this study is to examine the impact of the institutional factors (coercive, mimetic, and normative pressures) and the organizational context on the adoption of cloud ERPs in the Jordanian business institutions. Therefore, a questionnaire was developed to gather data from seventeen companies with a sample of 122 respondents. Structural equation modeling using PLS3 was processed to analyze the data. The conclusion from this study designates that the cloud ERPs adoption can be understood through the external and internal factors that have an important influence on cloud ERPs adoption. The main findings of this study confirm that institutional pressures have a significant impact on the adoption of cloud ERPs models, but they do not have a important influence on the adoption of cloud ERPs applications. In contrast, the organizational context has an effect on the adoption of cloud ERPs application, but it does not have a significant impact on the adoption of cloud ERPs model.
Keywords:	Cloud ERPS; Institutional Pressures; Cloud Model; Top Management Support, Expected Performance.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	THE DIMENSIONS OF PETRI NETS: MODELLING STRATEGIES FOR BIOLOGICAL ASPECTS APPLICATION TO E. COLI
Author:	OMED HASSAN AHMED, ZANA AZEEZ KAKARASH, ARAM MAHMOOD AHMED
Abstract:	Petri net is a formalism which is very beneficial for biologists. The analytical and simulation abilities of Petri net may assist the elaboration of experiments because it can be used to test hypotheses and collect related information. This paper is a survey about PN formalisms regarding gene regulatory network (complex systems of genes, proteins and other types of molecules), considering the advantages and disadvantages of each method. In addition, a model of genetic regulatory network is demonstrated for the response of carbon starvation stress in E. coli. It was previously represented by differential equation; however, it has been transformed into Hybrid functional Petri net (HFPN) model. The HFPN formalism has yielded its suitability for modeling the carbon starvation response network in E. coli cells. Therefore, by utilizing this model on a current available tool, and by using simulations, results have been gained which are identical to previous studies
Keywords:	Hybrid functional Petri Net, Gene Regulatory Network, E. coli, Modeling and Simulation
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	COMPARISON STUDY OF AUTOMATIC CLASSIFIERS PERFORMANCE IN EMOTION RECOGNITION OF ARABIC SOCIAL MEDIA USERS
Author:	ABDULLAH DAOOD, ISSAM SALMAN, NADA GHNEIM
Abstract:	Emotion recognition from text gained a lot of interest in the last years, but some languages such as Arabic (with its different spoken dialects) have not been given such attention. In this paper, we present our work in the Emotion detection of Arabic texts, with a focus on Levantine Twitter Messages. We have constructed a corpus of Arabic Levantine tweets, and annotated it with correspondent emotions. We implemented different methods to automatically classify text messages of individuals to infer their emotional states. We compared the results of different machine learning algorithms, and the inclusion of different features, to determine the best configuration of the emotion recognition system.
Keywords:	Emotional Analysis, Data Mining, Emotion Detection From Arabic Text, Twitter, Syrian Dialects
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	THE CLASSIFICATION PERFORMANCE USING LOGISTIC REGRESSION AND SUPPORT VECTOR MACHINE (SVM)
Author:	AGUS WIDODO, SAMINGUN HANDOYO
Abstract:	In the global world, data processing will have a key role for an organization in winning a competition because it will produce the useful information. The mathematical modeling in practice must be able to answer the challenging of information needed by users such as object classification. Many researchers from the various field of study have implementation and development the methods of classification in the real world. The popular classification methods are logistic regression and Support Vector Machine (SVM). This paper will investigate comparison in performance of both methods fairly using to actions, three types background of the data set and transformation to categorial scale for all predictor variables. The performance of both methods will be evaluated using Apparent Error Rate (Aper) and Press’Q statistic. Before modeling process, we divided each data set to become training data that have 80% part of data set and the remain as testing data. In this paper, we successfully show that the SVM has the performance of classification better than logistic regression not only in both training and testing data but also in three difference types and background of data set.
Keywords:	Aper, classification, logistic Regression, SVM
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	HUMAN ACTIVITIES RECOGNITION BASED ON AUTO-ENCODER PRE-TRAINING AND BACK-PROPAGATION ALGORITHM
Author:	NADIA OUKRICH, 2CHERRAQI EL BOUAZZAOUI, ABDELILAH MAACH, ELGHANAMI DRISS
Abstract:	In this paper, Auto-Encoder algorithm (AE) has been used in unsupervised feature selection, then, Back-propagation (BP) algorithm has been used to train reconstructed subsets in supervised learning; in order to recognize human activities inside smart home. Subsequently, the performances of auto-encoder have been evaluated and compared with traditional weighting technique for features selection. The experimental results demonstrate that neural network using auto-encoder achieves an average of over 91.46 % for one user and 90.62 % for two-users, relatively better than neural network using traditional weighting technique.
Keywords:	Auto-Encoder Pre-Training, Deep Network, Activity Recognition, Back-Propagation Algorithm, Smart Home.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	VIRTUAL REALITY ENGINE DEVELOPED IN PANDA 3D FOR A CAVE BASED SYSTEM
Author:	IBAÑEZ MEJÍA R., OLGUIN-CARBAJAL M., RIVERA-ZARATE I
Abstract:	There is now a virtual reality laboratory in CIDETEC, which uses as a primary tool an immersion cabin, who consists of three projectors, mirrors and a structure of three screens, which display the virtual environments for educational purposes and simulation. It was noted that the virtual environment to run the tests did not meet the necessary requirements for optimal performance of immersion cabin. It was proposed to solve the problem caused by the usage of VRML to create the virtual environment by replacing that tool for one that also allows the usage of new hardware devices and improve the visual quality of the models represented. After testing several tools the decision was made to use Panda3D for the development of the virtual environment, which can load models created in design tools such as Blender and 3ds Max, allowing the optimal usage of the endless road system, alongside with collision detection, providing a better alternative to the use of virtual environments.
Keywords:	Virtual Reality, Panda3D, Multipersonal VR Cockpit, Endless Road.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	A HEURISTIC METHOD FOR IMPROVING TCP PERFORMANCE BY A GREEDY ROUTING ALGORITHM
Author:	S.P. VALLI, Dr.SHARMILA SANKAR, Dr.K.M MEHATA
Abstract:	Transmission Control Protocol (TCP) is a reliable transport layer protocol that works well in a wired network. TCP achieves this reliability by sending an acknowledgment for the data packets transmitted. During data transmission packets might be dropped. In wired networks packet loss is a rare event and the reasons for loss in most cases is attributed to buffer overflow. In such cases this is handled by TCP by reducing the transmission rate. However the same might not be the scenario in a wireless network. In wireless network packet loss may be due to various reasons such as node failure, link failure of an intermediate node, signal loss, network partitions, hidden and exposed terminals. Thus TCP performance degrades in a wireless network and TCP for wireless adhoc networks has to withstand these challenges. Route instability is another major challenge in Mobile Adhoc network and the role of a routing protocol has a significant impact on the performance of TCP throughput. This paper improves the performance of TCP in mobile Adhoc networks by using a Greedy cross layer routing algorithm which reduces the route instability problem in TCP for Adhoc networks. The simulations were done using Qualnet 5.0. The simulation results show a significant improvement in the throughput, reduction in the number of packets lost and the number of retransmissions.
Keywords:	Transmission Control Protocol (Tcp), Throughput, Hidden And Exposed Terminal, Routing Instability, Retransmissions, Routing Algorithm
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	COMPUTER AIDED SYSTEM FOR DETECTION AND CLASSIFICATION OF BRINJAL LEAF DISEASES USING THERMAL AND VISIBLE LIGHT IMAGES
Author:	S. VENI, P.M.VISHNU PRIYA, G.M. AISHWARYA MALA, ASHWINI KAYARTAYA, R. ANUSHA
Abstract:	Agriculture plays a significant role in the overall socio-economic fabric of India. One of the several problems it faces in the country is the decline in productivity due to the drastic increase in plant diseases. The observations for detection of such diseases can be prohibitively expensive. Hence, a system which provides a faster and more accurate solution is necessary. Thermal images have a fine potential for early detection of diseases due to the temperature variations that occur as a result of the change in transpiration rate in plant leaves. Thus an attempt is made for the combined analysis of the visible light and thermal image features for early and accurate disease detection. The proposed work aims at developing a computer aided system that uses image processing algorithms to detect and classify plant diseases from Solanum Melongena (brinjal) leaves. The process starts with image acquisition using thermal and RGB cameras to obtain the data set, these images are then pre-processed and the region of interest is segmented out. The colour and temperature features are extracted and are used to detect and classify the healthy and diseased leaves. For classification, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are used and their performances are compared. The experimentation reveals that SVM has a better accuracy (90.9%) than that of ANN (89.1%).
Keywords:	Thermal Image, Silhouette extraction, Image registration, Support Vector Machine (SVM), Artificial Neural Network (ANN)
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	IMPLEMENTATION OF SOFTWARE SYSTEMS PACKAGES IN VISUAL INTERNAL STRUCTURES
Author:	AHMAD ABDULQADIR AlRABABAH
Abstract:	This manuscript discusses the visualization methods of software systems architecture with composition of reverse engineering tools and restoration of software systems architecture. The visualization methods and analysis of dependencies in software packages are written in Java. To use this performance graph it needs to describe the relationships between classes inside the analyzed packages and between classes of different packages. This article discusses system visualization with using matrices of incoming and outgoing packet dependencies, allowing analyzing existing dependencies between classes within a package, and between classes of different packages. Obtaining such Information allows us to understand the reason for the emergence of dependencies between packages that determine architecture of the system, and also if necessary refactoring systems. In the manuscript also described the possibility of tools to provide the infrastructure for subsequent detection and error correction design in software systems and its refactoring.
Keywords:	Software Visualization, Reverse Engineering, Software Architecture, Dependency, Package
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	ABNORMAL BEHAVIOR DETECTION IN AUTOMATED SURVEILLANCE VIDEOS: A REVIEW
Author:	AHLAM AL-DHAMARI, RUBITA SUDIRMAN, NASRUL HUMAIMI MAHMOOD
Abstract:	Abnormal detection refers to infrequent data instances that come from a diverse cluster or distribution than the majority normal instances. Owing to the increasing demand for safety and security, discovery abnormalities from video streams has attracted significant research interest during recent years. By automatically finding abnormal actions, it significantly decreases the cost to label and annotate the videos of a huge number of hours. The current advancements in computer vision and machine learning have a remarkable role in enabling such intelligent frameworks. Different algorithms that are specially designed for building smart vision frameworks seek to scene understanding and building correct semantic inference from observed dynamic motions caused by moving targets. Unfortunately, although there are many algorithms have been proposed in this interesting topic, the research in this area still lacks strongly to two important things: comparative general assessment and public-accessible datasets. This study addresses these inadequacies by presenting an overview of most recent research algorithms that concentrate significantly on abnormal behavior detection in surveillance applications. This study extensively presents state-of-the-art algorithms in a way that enables those interested to know all the key issues and challenges relevant to the abnormal behavior detection topic and their applications as well as their specific features. Additionally, there are five important evaluation benchmarks from 2007 to 2017. The performance and limitations of those benchmarks are discussed, which will help largely research in this area.
Keywords:	Video Surveillance, Abnormal Detection, Feature Extraction, Learning Methods, Clustering, Spatio-temporal Compositions, Sparsity
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	TECHNOLOGY MANAGEMENT TO INCREASE THE EFFICIENCY OF THE SUPPLY CHAIN
Author:	DIAZ MARTINEZ, JORGE J., RUIZ-ARIZA, JOSE D., CONTRERAS-SALINAS, JHEISON., HERNANDEZ PALMA, HUGO G
Abstract:	This article is an effort to determine the status and contribution of technology management as an integral part of the supply chain, In the present article it starts from the premise that, the technology management system is an integral part of the supply chain; To corroborate the hypothesis, a field study was carried out in the city of Barranquilla, Colombia, aimed at medium-sized service, commercial and industrial companies, in order to diagnose the management of technological processes related to identify how technological management processes related to the supply chain are carried out and Logistic processes in these organizations. One of the conclusions reached in the study is that although the majority of participating companies currently use the technology management, this is not effective, since some activities in the supply chain are outside of its scope which prevents a true control and traceability of the products and services offered by companies.
Keywords:	Technology Management, Supply Chain, Logistics Processes.
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	3D MEDICAL IMAGE VISUALIZATION AND VE MODEL TO DETERMINE THE PATHOLOGY ZONE OF TUMOR EVIDENCE-BASED USING SOME NUMERICAL METHODS AND SIMULATION
Author:	NORMA ALIAS, YASEEN ALWESABI, MAIZATUL NADIRAH MUSTAFFA, SHAMYSHATU, WALEED MUGAHED AL-RAHMI
Abstract:	This paper presents some integrated mathematical modeling and simulation for visualizing a 3D medical image and estimating the volume of tumor growth. Thus, these two indicators will determine the pathology zone and to provide revised evidence-based on tumor histology, location, growth and the treatment effect. There are three phases of modeling and simulation for volume visualization of the 3D tumor. The first phase is converting from 2D signal images to 2D digital images based on edge detection of the tumor. Geodesic Active Contour (GAC) model based on additive operator splitting (AOS) will be used to detect the contour line of a brain tumor on 2D images. The second phase is pre-constructing of 3D digital image from the 2D images by applying two numerical models such as an image manifold model (IM) and volume estimation model (VE). The third phase is implementing the numerical simulation and visualizing the 3D medical image on a hardware and software computational platform. The numerical comparison of VE and IM will be investigate using some performance measurements and interpretation in terms of VE, RMSE, run time and computational complexity cost. In this case study, the medical image is based on a set of 2D MRI brain tumor images from Kubang Krian Hospital Malaysia (HKK). The numerical results will determine the pathology zone and to provide revised evidence-based on tumor informatics. As a conclusion, this paper proof an alternative numerical model is superior to construct and visual the 3D medical images. Thus, volumetric image estimation from the 2D image and extended to a 3D volume image is essential for accurate evaluation of the high resolution 3D medical images.
Keywords:	Pathology Zone, Numerical Simulation, edge detection, 3D Visualization
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	A COMPARISON OF EVOLUTIONARY TECHNIQUES FOR TEST CASE GENERATION AND OPTIMIZATION
Author:	MS. NAMITA KHURANA, DR. RAJENDER SINGH CHHILLAR
Abstract:	The key objective of this paper is comparative evaluation of test case generation and optimization for two bio-inspired algorithms Genetic Algorithm and Ant Colony Algorithm. These Search Optimization techniques provide the best solution. These algorithms are used to generate test paths and then optimize them. The case study is being presented using Activity Diagram on Airline Reservation System by applying both Optimization Algorithms. Activity Diagram is transformed into Activity Graph. The Nodes of the graph show a test path which is being optimized using Genetic Algorithm and Ant Colony Optimization.The study done is measured in terms of number of iterations and execution speed. The empirical results prove that the algorithm for Ant Colony Optimization shows better results as compared to Genetic Algorithm. The proposed technique gives the comparative results of bio-inspired Algorithms. The two Algorithms can be combined to get better optimization results. The proposed technique can be used to develop automated tool.
Keywords:	Ant Colony Optimization, Genetic Algorithm, Test path Generation, Test case Optimization, Activity Diagram
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text

Title:	MEASURING SMARTPHONE USAGE TIME IS NOT SUFFICIENT TO PREDICT SMARTPHONE ADDICTION
Author:	MYOUNGHEE SHIN, KANGWOO LEE
Abstract:	Usage time is a major criterion to determine whether a user is addicted to their smartphone, and many smartphone apps aiming to decrease smartphone addiction have been developed with this criterion in mind. However, this rule of thumb is based on an incorrect assumption that develops from studies on internet addiction. Our study tests how applicable this rule truly is, through correlation and discriminant analysis on smartphone usage patterns. Using a self-diagnosis scale for smartphone addiction (S scale for short) and smartphone usage tracker, we collected S scale scores and smartphone usage patterns from 195 undergraduate participants. The statistical results indicate that 1) smartphone addiction is highly correlated with communication but not entertainment and 2) solely measuring the total usage time is not enough to predict whether a smartphone user is addicted. Our results imply that additional measures to capture richer information on smartphone-related activities are necessary for developing anti-addiction apps.
Keywords:	Smartphone addiction, Smartphone usage time, Smartphone usage pattern, Fishers linear discriminant analysis, Communication
Source:	Journal of Theoretical and Applied Information Technology 15^th October 2017 -- Vol. 95. No. 19 -- 2017
Full Text