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

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

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

Journal of Theoretical and Applied Information Technology
June 2017 | Vol. 95 No.11

Title:	GENETIC NETWORK PROGRAMMING-REINFORCEMENT LEARNING BASED SAFE AND SMOOTH MOBILE ROBOT NAVIGATION IN UNKNOWN DYNAMIC ENVIRONMENTS
Author:	AHMED H. M. FINDI, MOHAMMAD H. MARHABAN, RAJA KAMIL, MOHD KHAIR HASSAN
Abstract:	The problem of determining a smoothest and collision-free path with maximum possible speed for a Mobile Robot (R) which is chasing a moving target in an unknown dynamic environment is addressed in this paper. Genetic Network Programming with Reinforcement Learning (GNP-RL) has several important features over other evolutionary algorithms such as combining offline and online learning on the one hand, and combining diversified and intensified search on the other hand. However, it was used in solving the problem of R navigation in static environment only. This paper presents GNP-RL as a first attempt to apply it for R navigation in dynamic environment. The GNP-RL is designed based on an environment representation called Obstacle-Target Correlation (OTC). The combination between features of OTC and that of GNP-RL provides safe navigation (effective obstacle avoidance) in dynamic environment, smooth movement, and reducing the obstacle avoidance latency time. Simulation in dynamic environment is used to evaluate the performance of collision prediction based GNP-RL compared with that of two state-of-the art navigation approaches, namely, Q-learning (QL) and Artificial Potential Field (APF). The simulation results show that the proposed GNP-RL outperforms both QL and APF in terms of smoothness movement and safer navigation. In addition, it outperforms APF in terms of preserving maximum possible speed during obstacle avoidance.
Keywords:	Genetic Network Programming with Reinforcement Learning (GNP-RL), Mobile robot navigation, Obstacle avoidance, Unknown dynamic environment
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	MUSIC INTEREST CLASSIFICATION OF TWITTER USERS USING SUPPORT VECTOR MACHINE
Author:	YUSRA, MUHAMMAD FIKRY, BAMBANG RIYANTO TRILAKSONO, RADO YENDRA, AHMAD FUDHOLI
Abstract:	Interest determination in music is very beneficial for business communities such as social network advertiser, music studio rental, musical instrument sales, and music concert promoter. This research discusses the classification of music interest of Twitter users based on their tweets in Bahasa Indonesia (Indonesian language). We classify tweets into three music genre categories (jazz, pop, or rock) and three sentiments (positive, negative, or neutral) using Support Vector Machine (SVM). Tweet text classification includes user text, retweet text, mention, hashtag, emoticon, and link (URL). Preprocessing is initiated with word segmentation, removal of symbol and numeric character codes, stemming, word normalization, removal of stopwords, and searching DBpedia for some important words that does not have basic words. This research use dataset of 450 tweets. By generating SVM model on training process that use 360 tweets, Gaussian RBF kernel, and 10-fold cross validation, a pair of parameter (C=0.7, γ=0.9) for music genre category and a pair of parameter (C=0.7, γ=0.8) for sentiment were obtained. The testing process use 90 tweets and resulting the best accuracy for music genre category (96.67%) and the best accuracy for sentiment (86.67%).
Keywords:	Music Genre Category, Sentiment, SVM, Tweet
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	TUNING PHYSICAL PARAMETERS FOR ENHANCED RECEIVER PERFORMANCE OF PULSED-BASED ULTRA-WIDEBAND IN SHORT RANGE WIRELESS COMMUNICATIONS
Author:	EZEDDIN SANAM, KAMARUZZAMAN SEMAN, MOHD ZALISHAM JALI
Abstract:	Based on recent research about UWB communication, its clearly that one of the most interesting feature of the Pulse-based UWB technology is it’s high flexibility in term of the generated signal at the physical layer level. This feature combined with simple transceiver as it is almost digital communication structure allows this technology to be a good solution of different short-range wireless applications. This paper proposes enhancements on the receiver performance by tuning the most important physical parameters of the generated pulses as pulse modulations, coding and frame timing structure as these parameters are in great influences on the performance of the receiver. This performance can be defined as the probability of the lost packet in certain signal to noise ratio in varied distances and data rate scenarios. The method followed to validate the achievements of the enhancements of the receiver performance can be explained as proposing a communication link of certain pulse-based wireless system where at the beginning the physical parameters are set as reference parameters then the performance of the receiver measured. After that, tuning each parameter separately to check the enhancements of the receiver performance in certain different data rates an distances. Results showed that the performance can be enhanced significantly in term of the received signal errors for certain signal noise to power ratio with approximately up to 50% by tuning some physical parameters that have significant effects on received signal quality.
Keywords:	Ultra Wideband, Time Hopping, Pulse Position Modulation, Physical Parameters, Signal to Noise Ratio, Bit Error rate.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	PCE BASED PATH COMPUTATION ALGORITHM SELECTION FRAMEWORK FOR THE NEXT GENERATION SDON
Author:	P.SELVARAJ, V.NAGARAJAN
Abstract:	The network operators are striving for the optimization of transmission resources while achieving network performance and efficiency. The current optical networking is rolling out towards the next generation intelligent optical network to offer high capacity and better quality according to the attribution of the service. One of core problems in optical network is path computation which involves finding the route between source to destination with appropriate wavelength. The constrained optical path computation involves finding the route with appropriate wavelength while optimizing one or more criteria (ex: less congestion). At present scenario, the centralized PCE with GMPLS control plane could control the optical network with traffic engineering. This approach may be incapable or costlier for the next generation voluminous and dynamic application needs with range of QoS gurantees. The PCE has to rely on a certain routing protocol along with some path cost measures, may not explore the required optimal solutions space, and end up with the best effort path most of the time. Moreover the traffic engineering can potentially add additional cost while maintaining the quality of the path. This article intends a path computation algorithm selection framework amenable for the next generation software defined optical network to solve the problem of QoS constrained path computation. The framework exploits the right proportion of enabling technologies to realize the constrained optical flows in a cost effective and optimal manner. The simulation study was performed to analyze the characteristics of the PCE based algorithm selection model in the SDN based optical network.
Keywords:	Bit Error Rate (BER), Path Computation Element (PCE), Generalized Multi Protocol Label Switching (GMPLS), Quality of Service (QoS), Software Defined Optical Network (SDON).
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	DYNAMIC MULTICAST TREE MAINTENANCE PROTOCOL FOR SECURE GROUP COMMUNICATION IN MANET
Author:	G.NARAYANA, M.AKKALAKSHMI , A.DAMODARAM
Abstract:	In mobile ad hoc network (MANET), the nodes communicate wirelessly through multiple hops as it has several nodes inside each network. Each node can enter and leave the network in a dynamic way without having any restriction in its mobility. Group key management technique is employed for ensuring security and integrity in MANET. When devised appropriately, this technique offers security to the data in the network with high key computation cost and overhead. This is because there is a need to compute the group key every time a new node joins or leaves the network. To overcome this issue, we have proposed a dynamic multicast tree maintenance protocol for secure group communications. When a new node enters the network or leaves the network, only the subtree involved with the node joining or node departure needs to recompute a group key. The group key of remaining part of the multicast tree will not be changed. Simulation results show that this process reduces overhead and unnecessary key computation process, thereby enhancing the network performance.
Keywords:	MANET, Multicast Tree, Group Communication, Protocol, AODV, DSR
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	MOBILE-BASED EXPERT RELIANT SYSTEM OF APPLICATION DETERMINING THE ADEQUACY OF COWS FOR ISLAMIC QURBAN RITUAL USING METHOD OF FORWARD CHAINING
Author:	ENDAH PURNAMASARI, KHAIRA ALMISRI, INGGIH PERMANA, NURMAINI DALIMUNTHE
Abstract:	The most prevalent livestock used for qurban ritual on Islamic festival of Eid Al Adha is cow. There are a number of criteria must be adhered to before a livestock is deemed elligible for sacrificial slaughter. However, these requirements are often overlooked or ignored by the general public which derives from their inadequate understanding of these criteria. Also, the number of expert who are asked to examine the elligibility of livestocks and socialize the skills required to the public is limited. This study has designed and created a web based system of expert reliant application to determine the adequacy of livestock so as to help the laymen to determine the satisfactoriness of cows. Forward chaining the inference technic used in the research. The study was done in two stages namely the creation of knowledge basis and implementation stage. In the former stage extensive repository of information on the implementation of animal slaughtering is acquired from numerous scholars in their respective fields. These scholars who are consulted include (1) religious scholars; (2) veterinarians; and (3) animal science experts. The acquired information is arranged in the forms of rules that can be converted into a computer program. In the latter stage analysis on the need basis for application functionality, interface design, creating and testing of the application is conducted. The outcomes are arranged categorically which result in 90 rules that determine the adequacy of cows for sacrifice. The three main features revealed from this implementation of expert reliant system of application are: (1) examine the acceptableness of cows; (2) features designed for responses to inquiries; and (3) features designed for presentation of latest facts from inferences. Based on the unit test shown, this application is successful in performing inferences on the knowledge aspect based on the facts correctly entered by users. Moreover, based on the black box test conducted by using 10 different smartphones with various specifications, the test showed 100% success rate on the need basis in the ongoing application functionality. Considering the results demonstrated in the unit test and black box test it can be concluded that this application can be recommended to settle the issue assessing the adequacy of cows for Islamic qurban rituals.
Keywords:	Forward Chaining, Adequacy of Animal for Qurban Ritual, Mobile, Cow, Expert Reliant System
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	AN EFFICIENT DESIGN MODEL VALIDATION FOR THE QUALITY SOFTWARE DEVELOPMENT
Author:	MULUGU. NARENDHAR, Dr.K. ANURADHA
Abstract:	Models are the main artifacts of the software development process which generally follows a model-based paradigm. Business process models and data models play an important role in building information systems and to represent the perspective on business knowledge and close depended on relations, which is important to be validated to maintain the fault free and quality software development. Therefore, the design relevant models are acts as the blueprints for the quality assurance in software development. In this paper, we propose an efficient design model validation (DMV) supported utilizing the prescribed "specification language" for the proclaiming construction of transformation attributes based on the invariants, pre and post-conditions for generating partial functions used can be transformed for testing evaluation. We broaden the utilize of specification languages for automatic creation of input test models. We also used the prototypes of the Eclipse plug-in to provide specifications and calculations of metrics in related to models supported by the Eclipse Modeling Framework.
Keywords:	Design Modelling, Model Transformation, Quality Software Development, Validation Metrics
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	PERFORMANCE INCREMENT OF HIGH SCHOOL STUDENTS USING ANN MODEL AND SA ALGORITHM
Author:	ANAS BLASI
Abstract:	In this study, Artificial Neural Network (ANN) model has been used for modeling and design of students’ grades in high school level to predict their grades and increase their performance depends on four factors: grades average of ninth level, grades average of tenth level, grades average of eleventh level, and the average of studying hours per day. To do so a Neural Network has been designed. The input parameters were the grades average of ninth stage, grades average of tenth stage, grades average of eleventh stage, and average studying hours per day. One hidden layer was considered with ten neurons. The output layer is Grades average of high school level. One hundred data points were considered to train the network and calculate the weights. After that, the results of ANN model have been used by Simulated Annealing (SA) optimization algorithm to maximize the students’ grades in high school level. MATLAB software was used to do the implementation part. The main goal of this study has been achieved by predicting high school students’ grades, which can help in increasing the students’ performance in this level of education.
Keywords:	Artificial Neural Networks, Back Propagation Network, Simulated Annealing, Data Mining
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	RANSOMWARE ANALYSIS BASED ON THE SURFACE, RUNTIME AND STATIC CODE METHOD
Author:	LULUK USMAN, YUDI PRAYUDI, IMAM RIADI
Abstract:	Ransomware is one of the latest malware in recent years that can infect computers and smartphones. The malware is able to encrypt the files inside the computer or smartphone, thus prevents the users (victims) from accessing their system. In addition, the victims will be asked to pay the ransom through certain online payment methods to get a decrypt key. Due to the latest development of ransomware variants, a solution is required to prevent the malware attack. This study analyzes the cryptolockers ransomware which utilize three method such as surface, runtime and static code method. The result provided the detail characteristics of ransomware through three aforementioned methods as well as the solution to prevent the attack.
Keywords:	Ransomware, Surface, Runtime, Static Code.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	CLOUD TECHNOLOGIES IN EDUCATIONAL SYSTEM OF REPUBLIC OF KAZAKHSTAN
Author:	AIGUL SADVAKASSOVA, MERUERT SERIK
Abstract:	Objectives: analysis of using cloud technologies in High education system of Republic of Kazakhstan, determination of theoretical basis, development and practical realization of academic cloud storage on local network of university on improvement training of future teachers of computer science. Methods: during this study there were used pedagogical studies’ methods, such as study analysis on theme, methods of theoretical comparison and generalization, studying international experience, questioning. Findings: Academic cloud storages were developed by authors, which nowadays are realized by local network, but further are planned with internet access. For realization were analyzed cloud solutions and development strategy of IT-system for Kazakhstan universities on this issue. On work were described designed cloud storages, were provided practical and methodical guidance for its usage, which are convenient for students. In article reviewed and evaluated the benefits of developing and using cloud storage in educational process on training of future teachers of computer science, as well as practical recommendations given for realization of cloud technologies on educational process in universities. Application/Improvements: Practical significance of study lies in the fact that proposed scientific and methodological results of study will be used to improve the training of future teachers in universities of republic.
Keywords:	Cloud Storage, Cloud Technologies, Development Of Cloud Reserves, Education, Network Training.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	AN EFFICIENT IMAGE COMPRESSION BASED ON MODIFIED HAAR WAVELET
Author:	ABDULLAH MOHAMMED AWAD, MUZHIR SHABAN AL-ANI
Abstract:	Haar transform is one of the simplest and basic transformation from the multi-resolution spectrum. The attracting features obtained from Haar transform make it a potential candidate in modern applications, such as signal and image compression. The Haar wavelet transform provides mean values that compress the image so that it takes up much less storage space, and therefore transmits faster electronically and in progressive levels of detail. The main objective of this work is to modify the weighting factor in or der to study their effects on image compression. This paper tries to implement different scale of weighting factor and study their performance on the overall system of compression. Scale of weighting factor is used in order to prevent the pixel value from exceeding their limits. Different values of weighting factor are applied, these values are spans into two range to evaluate the implemented system. These values are implemented for various levels of 2D-DWT then we measure the performance via mean square error (MSE) and peak signal to noise ration (PSNR) in each step. The implemented system is simulated for wide range of weighting factors. The obtained results indicated that a good results can be achieved between a=1.6 to a=5.0.
Keywords:	2D-DWT, Image Compression, Discrete Wavelet Transform, Haar Transform; Weighting Factor
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	A RULE-BASED SYSTEM FOR ADVISING UNDERGRADUATE STUDENTS
Author:	MS.GHALIA MUSALAM SALIM ALFARSI , DR. KHALED ABDALGADER M. OMAR, MS.MARYAM JUMA ALSINANI
Abstract:	Academic advising of the undergraduate students is playing a fundamental rule and one of the most important responsibilities for the academic staff in most of the leading universities. The expert system is considered as one of most achievement area in artificial intelligence. This research was motivated by the idea that successfully being able to develop an academic advisory system of this nature, will increase the breadth and scope of students and academic staff problems solved, and subsequently academic activities can successfully be achieved to an excellent level in the university learning process. However, the performance of any advisory expert system will be limited by the quality of the gained knowledge (i.e., knowledge acquisition). The aim of this research is to propose a modification of the exiting knowledge acquisition framework to be suitable to use for higher education institute (e.g., Al-Buraimi University College) in pursuance of developing a prototype rule-based expert system, dedicated for undergraduate students academic advising. The output of the system also provides the undergraduate students proposal courses that are precise and non-conflict, working as an advisor. .; it gives the undergraduate student a plan and advisee with the appropriate subjects according to the courses that have been taken, prerequisites, and project scope if it is already determined by him/her with the explanation The Empirical results show that the implementation of proposed model for undergraduate advisory expert system leads to a significant improvement in performance.
Keywords:	Rule-Based Expert System, Knowledge Acquisition, Knowledge Base
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	HIT-RATIO STORAGE-TIER PARTITION STRATEGY OF TEMPEATURE DATA OVER HADOOP
Author:	NAWAB MUHAMMAD FASEEH QURESHI, DONG RYEOL SHIN, ISMA FARAH SIDDIQUI, ASAD ABBAS
Abstract:	Big data analytics refers to a simplified solution of managing huge datasets in a distributed computing environment. Apache Hadoop is an open-source solution that processes large datasets in parallel scenario. The ecosystem consists of three-tier architecture i.e. client, Namenode and Datanode. When a client requests a task processing, Namenode assigns resources and schedules the task over slave node. The Datanode processes the task and returns an output over heterogeneous storage-tier of the cluster. The dataset used for task processing can be categorized into four types i.e. Hot, Warm, Cold and Frozen data. The temperature feature indicates the frequency of accessibility to a dataset and facilitates storage areas i.e. DISK and ARCHIVE. Since the data temperature is identified through number of blocks used per day and data age i.e. 7 days, the storage-tier bears an additional task burden to monitor the changes. Moreover, the temperature data is not relocated but declared with a mark of DISK and ACHIVE proforma. Therefore, storage-tier suffers from data block contention and I/O accessibility latency issues. To overcome these issues, we propose Hit-Ratio Storage-tier Partition Strategy (HRSP), which create logical partitions i.e. Hot partition over a storage-tier media. The presented approach provides direct accessibility of temperature data and reduces I/O accessibility latency and block contention problem. The experimental results depict that the proposed approach disposes the concept of defragmentation and improves I/O accessibility of Hadoop cluster.
Keywords:	Hadoop, HDFS, Data Temperature, Network contention, Storage-tier.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	A NEW PROCESSING OF CHAOS-BASED FAST IMAGE ENCRYPTION ALGORITHMS
Author:	WALEED KHALID ABDULJABBAR, SYARIZA ABDUL-RAHMAN, RAZAMIN RAMLI
Abstract:	Recently, many studies has been shown that the image encryption could be done using some techniques like RES, DES, IDEA but the new and effective technique for speedy and secure encryption using chaos-based cryptography is the most preferred encryption technique. Chaos-based encryption algorithms are a hybrid technique of multiple chaotic maps and can be repeated the same process for multiple cycles to increase the security. But, the increasing the number of steps to process an image will increase the processing time too. Another reason, if the number of pixels being encrypted increased will increase the processing time. Since, chaos-based algorithms are selected as a good choice for encrypting images during the real time applications, lesser response time and even the higher security are important. This paper will focus on evaluating encryption techniques by using two dimensional chaotic maps and comparing the strength of the encryption algorithms security and the time responses for many images have different sizes. Finally, quantitative results are compared evaluated and implemented of the serial implementation, parts of encryption and decryption process that can be parallelized (using GPU and CUDA programming) with the serial implementation.
Keywords:	Image Encryption; Cryptography; Information Security; Chaos; Network
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	A NORMS TRUST MODEL FOR NORM ADOPTION IN AN OPEN AGENT COMMUNITY
Author:	AL-MUTAZBELLAH KHAMEES ITAIWI, MOHD SHARIFUDDIN, ALICIA Y.C. TANG
Abstract:	In recent developments, norms have become an important entity that is considered in agent-based system’s design. Norms are not only able to organize and coordinate the actions and behaviour of agents but have a direct impact on the achievement of agents’ goals. Therefore, an agent in a multi-agent system requires a mechanism to detect the right norms and adopt them. For this reason, the agent needs a mechanism to evaluate the trust in each norm it detects. On the other hand, the impact of norms on the agent’s goal and its plan may be at risk ensuing from the probability of positive or negative results when the agent adopts the right or wrong norms. In this paper, we propose a norm’s trust model that could be utilized in norms adoption or rejection. Ultimately, we determine the benefits of adopting the norm as a consequence of a favourable trust value as an additional factor in norms’ adoption.
Keywords:	Norms Benefits, Norms Trust, Norm Detection, Normative Multi-agent Systems, Intelligent Software Agent.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	PERFORMANCE EVALUATION OF COMBINED CONSISTENCY-BASED SUBSET EVALUATION AND ARTIFICIAL NEURAL NETWORK FOR RECOGNITION OF DYNAMIC MALAYSIAN SIGN LANGUAGE
Author:	SUTARMAN, MAZLINA ABDUL MAJID, ENNY ITJE SELA
Abstract:	Dynamic sign language recognition is important to intelligent human-computer interaction technology, but it is also very difficult to deal with, especially when the environment is quite complex. This paper proposes the use of consistency-based Subset Evaluation and Artificial Neural Network (ANN) in order to increase accuracy rate in the recognition of sign language. At the first stage, image acquisition data gets from the Kinect sensor, using skeletal data tracking with eight joint positions. The second stage, the skeletal feature extraction (data X, Y, and Z are taken the value relative to the torso and head; spherical coordinate a conversion process; segmentation of the frame to get the same number of dimensions). The third stage, the selection of feature data using the Consistency-based Subset Evaluation algorithms with the best first search method subset. Then last stage is the classification using Artificial Neural Networks, by variations of nodes in hidden layer. The data samples tested are 15 dynamic signs taken from the dynamic of Malaysian Sign Language (MySL). The results of the experimental show that our system can recognize with accuracy of 93.67%. The feature selection can contribute toward the improvement in the accuracy rate of sign language recognition data
Keywords:	Malaysian Sign Language, Sign Language Recognition, Artificial Neural Network, Kinect, Consistency-based Subset Evaluation
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	ENHANCING VISUAL PROPERTIES OF GRAPH COMMUNITIES
Author:	JAMAL ALSAKRAN
Abstract:	Systems that take the form of graphs of nodes and edges are common in various fields of study such as biology, and social and organizational studies. Typically, these systems exhibit community structure that corresponds to modular decomposition of functionality and common features of interest. In this paper, we endeavor to contribute to the efforts to enhance the visual representation of community structure. We propose refinements to the visual layout produced by force-layout model and treemap to foster desirable visual properties. Experiments are conducted on real world datasets to show the effectiveness of our approach and discuss its impact on the system overall performance.
Keywords:	Graph Community, Modularity, Visualization, Treemap, Force-layout
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	PROTOTYPE OF VEHICLES POTHOLES DETECTION BASED BLOB DETECTION METHOD
Author:	DEWIANI DJAMALUDDIN, ANDANI ACHMAD, RIVANTO PARUNG
Abstract:	Potholes on road causes majority of traffic incidents. It happens with driver’s unawareness to potholes on the road, while potholes location data mining is still performed manually by technician nowadays. This issues drives these following research and prototyping to be performed. This paper presents a prototype of a pothole detection system using image processing. The system will detect the potholes by assuming potholes as a blob, using blob detection. Live feed from a camera module will be processed by the algorithm that is embedded to a microcontroller simultaneously to determine the potholes. Every detected potholes and its location will be recorded and displayed on a webpage. The prototype will be an embedded system Linux-based running on a Raspberry Pi, featured with camera and a computer program utilizing OpenCV. Several blob parameter such as shape, including circularity, convexity, and inertia value is utilized to optimize the pothole detection. The prototype is tested on actual road with different pothole shapes and size, and the result has 82.5% accuracy.
Keywords:	Blob Detection, OpenCV, Potholes, Raspberry Pi
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	IMPLEMENTATION OF MULTIMEDIA BASED GRAPH COLORING LEARNING MODEL
Author:	MUHAMMAD RUSLI, HADI SUTOPO
Abstract:	This research is intended to implement a Graph Coloring Learning Model for a Discrete Mathematics course. This learning model should encourage student’s ability to integrate all information resources from CD-ROM to learn Graph Coloring. The learning model focuses on how learners can learn graph coloring according to the instructions in the CD-ROM. Each lesson is provided with a step-by-step instruction for doing specific task. Learners can follow the tutorial from beginning to the end, or do only the lessons that correspond to their interests and needs. This is a descriptive case study with informatics students at a university as the subject. The data is analyzed using the analytic descriptive method and obtain findings that the learning model can affect the delivery of education and enable wider access to be the complement of learning process. Based on the research findings, the learning model can be used by students and motivate them to learn discrete mathematics.
Keywords:	Model; Multimedia; Graph; Learning Model
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	DESIGN AND TESTS OF A WEARABLE FUNCTIONAL ELECTRICAL STIMULATION (FES) SYSTEM FOR KNEE JOINT MOVEMENT USING CYCLE-TO-CYCLE CONTROL METHOD
Author:	AIDATUNISADINA LINAZIZAH BASITH, STANLEY SETIAWAN, ACHMAD ARIFIN, FAUZAN ARROFIQI, MUHAMMAD NUH
Abstract:	Paralysis has became more widespread nowadays. Mostly caused by stroke, spinal cord injury, and multiple sclerosis, the growing number of paralysis case also implied for a better treatment for its bearer. Some of the main problems for individual with paralysis is to improve health problems related to paralysis and to decrease the dependence to other people by regaining muscle function. In this study, a wearable functional electrical stimulation with cycle-to-cycle control system for knee joint movement restoration was developed. The system consists of sensor system, electrical stimulator, and fuzzy logic controllers. The controller was developed as Single Input Single Output (SISO) controller for knee flexion movement and Multi Input Single Output (MISO) controller for knee extension movement. Sensor system was used to measure angle of knee joint. A combination of two inertial sensors, accelerometer and gyroscope, made up the sensor system. The angle measured by sensor system was also used as feedback to realize closed-loop control. The data from the system could be monitored and saved as database using user interface program in a PC/laptop. Tests with neurologically intact subjects was done to test the performance of the system designed. It resulted in small number of RMSE and Settling Index for both maximum knee flexion and maximum knee extension control. The system designed was expected to be developed further to provide a full wearable FES system for lower limb motoric restoration.
Keywords:	Functional Electrical Stimulation, Cycle-to-cycle Control, Knee Joint, Fuzzy System
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	PARTICLE SWARM OPTIMIZATION FOR OPTIMIZING LEARNING PARAMETERS OF FUNCTION FITTING ARTIFICIAL NEURAL NETWORK FOR SPEECH SIGNAL ENHANCEMENT
Author:	OMAIMA N. A. AL-ALLAF
Abstract:	Speech signals are effected by noise generated by various sources of interferences. Removing noise from speech signals can be regarded as an active research area in signal processing. Thus, we need powerful methods in this area. Therefore, Function Fitting (FitNet) Artificial Neural Networks model was used in this paper for enhancing speech signals. Particle Swarm Optimization (PSO) was used during FitNet learning process to optimize the FitNet learning parameters (such as learning rate, momentum variable and network weights) to achieve best results of speech signal enhancement. At the same time, different optimization techniques for optimizing the values of learning parameters were suggested in this work. This is done to improve the performance of FitNet model for signal enhancement. Better results (320 learning steps, PSNR equal 38 and mean square error (MSE) equal 0.0027) from experiments were achieved when adopting PSO with FitNet with swarm size equal 40 and PSO number of iterations equal 100. Good results (312 learning steps, PSNR equal 35.94 and MSE equal 0.00002) were obtained also when adopting the suggested optimization techniques (learning rate equal 0.00003, 5 hidden units in one hidden layer with the using of Levenberg-Marquardt (LM) as learning algorithm) for optimizing the learning parameters.
Keywords:	Signal Enhancement, Artificial Neural Networks, Function Fitting Model, Particle Swarm Optimization
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	CLINICAL DECISION SUPPORT SYSTEM FOR DIAGNOSIS OF ACUTE RESPIRATORY TRACT INFECTIONS (ARI)
Author:	MUHAMMAD SYAUKANI, SRI HARTATI, HARI KUSNANTO, SURYO GURITNO
Abstract:	Acute Respiratory Infection is the disease that sometimes happens to children that can lead mortality. In emergency room there are still some cases of Acute Respiratory Infection that cannot be handled quickly and appropriately, so there should be a model of clinical decision support system as an assisting tool of the doctors to diagnose Acute Respiratory Infection especially pneumonia on children and under-five years children. In clinical decision supporting system, decision maker should provide rating value of alternative working load toward the criteria; the value given is in the form of ordinal data. This paper offers problem solving of ordinal data on clinical decision support systems using Extended TOPSIS. The test used 30 samples of medical records from the hospitals by comparing between TOPSIS method and Extended TOPSIS. Based on test results, it states that Extended TOPSIS method can produce proper diagnostic decision alternatives according to the medical records with sensitivity value of 93%, specificity value of 96%, precision value of 93% and value accuracy of 95%.
Keywords:	Clinical Decision Support Systems, TOPSIS, Extended TOPSIS
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	COPY-MOVE FORGERY DETECTION: A SURVEY ON TIME COMPLEXITY ISSUES AND SOLUTIONS
Author:	SITI FADZLUN MD SALLEH, MOHD FOAD ROHANI, MOHD AIZAINI MAAROF
Abstract:	As the image processing especially image editing software evolve, more image manipulations were possible to be done, thus authentication of image become a very crucial task. Copy-move forgery detection (CMFD), a popular research focus in digital image forensic, is used to authenticate an image by detecting malicious copy-move tampering in an image. Copy-move forgery occurs when a region in an image is copied and paste into the same image. There were many survey and review papers discussed about CMFD robustness and accuracy yet less attention was given to performance and time complexity. In this paper, we attempts to highlight the key factors contribute to the time complexity issue. Before that, the CMFD processes were first explained for better understanding. The trends of tackling those issues are then explored. Finally, numbers of proposed solutions will be outlined to conclude this paper.
Keywords:	Copy-Move Forgery, Digital Image Forensic, Duplicated Region Detection, Block Matching, Time Complexity.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	IMPROVING TRANSIENT PERFORMANCES OF VEHICLE YAW RATE RESPONSE USING COMPOSITE NONLINEAR FEEDBACK
Author:	M.K ARIPIN, Y.M SAM, 3KUMERESAN A.D, M.H CHE HASAN, M.FAHEZAL ISMAIL
Abstract:	This paper studies and applied the composite nonlinear feedback (CNF) control technique for improving the transient performances of vehicle yaw rate response. In the active front steering control design and analysis, the linear bicycle model is used for controller design while the 7DOF nonlinear vehicle model is used as vehicle plant for simulation and controller evaluations. The vehicle handling test of the J-turn and single lane change maneuvers are implemented in computer simulations in order to evaluate the designed yaw rate tracking controller. The simulation results show that the CNF technique could improve the transient performances of yaw rate response and enhance the vehicle maneuverability.
Keywords:	Composite Nonlinear Feedback, Yaw Rate Response, Active Front Steering Control, Vehicle Yaw Stability, Lateral Dynamic Control
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	SATISFYING SLA OBJECTIVES OF SEAMLESS EXECUTION OF MOBILE APPLICATIONS IN CLOUD WITH NET PROFIT
Author:	L.SHAKKEERA, LATHA TAMILSELVAN
Abstract:	Mobile Cloud Computing (MCC) technology enables the resource-constrained Smartphones to outsource its richer applications onto resource-abundant cloud. Cloud computing has emerged as a platform to extend the capabilities of mobile devices regarding energy and resources. MCC offers the services to enhance mobile user convenience, the energy-hungry applications require selective offloading of tasks onto the cloud and optimally scheduling the tasks by taking into account the cloud resources. Even though, the MCC offers the services with high level user convenience, it creates numerous challenges for the service providers. This paper proposes Maximizing User anTicipation on cloUd-based mobile AppLications BesidE NEt proFIT (MUTUAL-BENEFIT), an optimization approach that satisfies the Service Level Agreements (SLA) of the users and simultaneously maximizes the profit of the service provider. The MUTUAL-BENEFIT significantly enhances task offloading, scheduling and resource allocation in MCC environment. Initially, offloading manager of ThinkAir architecture judiciously offloads the intensive tasks based on the knowledge of device energy and performs parallelized execution. Secondly, the non-recursive dynamic programming assisted Ant Colony Optimization (ACO) method schedules the intensive tasks for an extended battery and quick response. It contemplates the SLA objective factors such as execution time, load and profit as the pheromone value of ACO while selecting the optimal resources. Together with SLA-aware task scheduling and the utility function based optimal VM resource allocation maintains an excellent trade-off between the service satisfaction and profit. The experimental results show that MUTUAL-BENEFIT approach preserves the device energy while ensuring the optimal SLA objectives and profit of the provider.
Keywords:	Mobile Cloud Computing, Resource Allocation, Dynamic Programming, Ant Colony Optimization, Energy aware, Load Balancing, Profit.
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	WEB-EXPERT SYSTEM FOR THE DETECTION OF EARLY SYMPTOMS OF THE DISORDER OF PREGNANCY USING A FORWARD CHAINING AND BAYESIAN METHOD
Author:	HELIZA RAHMANIA HATTA, FITRIA ULFAH, DYNA MARISA KHAIRINA, HAMDANI HAMDANI, SEPTYA MAHARANI
Abstract:	Web-Expert system (Web-ES) is used to recognize the symptoms early in women pregnancy disorders. Every pregnancy risk factors will endanger the safety of the mother and the baby, if the information obtained is less in the treatment of pregnancy disorder. This study aims to build web-based expert systems (ES), such as a doctor or a patient to diagnose pregnancy in any place, so it can help women to know about the symptoms of pregnancy disorder. ES is analyzed using forward chaining (FC) method and the Bayesian theorems. One of the Techniques that has been used to make a decision tree, then does a search with FC and the calculation of the probability by Bayesian. Based on the selected input symptoms dataset used 35 patients, the results of a pregnancy disorder which have the highest risk of disruption in eclampsia, with a value of 97% and the suitability of 82.86% system accuracy. Subsequent research, we perform hybrid Bayesian theorem and FC with fuzzy-neural network environments to produce values higher accuracy and will also make a decision in group clinical results.
Keywords:	Pregnancy disorders, Web, Expert System, Forward Chaining, Bayesian Theorem
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	THE ROLE OF MANGER EXPERIENCE AND FORMAL METHODOLOGY IN SOFTWARE DEVELOPMENT
Author:	MOHAMMAD MAHMOUD AL_TARAWNEH
Abstract:	This research examines the role of manger experience and formal methodology in software development, such as Reporting to senior management, Communication with users, Planning and scheduling, Coordinating project activities, Budget, schedule, risk, and quality control, people management, Project Definition. Estimating. Risk Assessment. The study population consists of all Jordanian institutions (n = 96) operating in the field of software development. From previous studies that have been reviewed and applied study conducted by researchers at the Jordanian companies show us the importance of manger experience and formal methodology factors. It is therefore important for the project team to deal with these factors in a serious and careful. Should the project manager and his team they have a good knowledge in how to deal with these factors. It should be the project manager and his team have their efficiency in the process of comparison between the benefits of the proposed system do not exist in the old system for each of the groups and individuals in the organization, and convince them of the benefits gained from the proposed system better and more for individuals and groups in the organization of the current system the old one.
Keywords:	Software Development, Formal Methodology, Manger Experience
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	INVESTIGATING THE ADOPTION AND IMPACT OF E- LEARNING IN KSA: PRINCE SATTAM BIN ABDULAZIZ UNIVERSITY CASE STUDY
Author:	TARIG MOHAMED AHMED, MOHAMED E. SELIAMAN
Abstract:	The kingdom of Saudi Arabia has given high priorities to the use of ICT to enhance teaching and learning processes in national institutes of higher education. E-learning has recently received intensive research attention. This research aims to identify the predictors of learners’ continuance intention to use E-learning systems in the Kingdom of Saudi Arabia based on the Unified Theory of Acceptance and Use of Technology (UTAUT), DeLone and McLean IS success model and the Technology Fit Model. The survey questionnaire measurement tool used included 34 items forming twelve latent variables. Based on the SEM analysis, fourteen out of seventeen research hypotheses were supported leaving three hypotheses not supported in this research. Study results show that the most significant the predictors of learners’ continuance intention to use E-learning systems are Perceived Benefits, Perceived Satisfaction and Academic Motivation. The influence of each of Task-technology fit, Performance expectancy, Knowledge Quality and Information Quality on user’s Perceived Satisfaction with using E- learning systems was also significant.
Keywords:	Technology Acceptance Model, E-learning Systems
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text

Title:	A SUGGESTED SCHEME FOR IMAGE CRYPTOGRAPHY EMPLOYING GENETIC ALGORITHM
Author:	MOHAMMED A. F. AL-HUSAINY, HAMZA A. A. AL-SEWADI
Abstract:	The extensive use of digital information storage and transfer over communication channels nowadays have raised tremendous hazards. Basically, it has exposed the information confidentiality, integrity, authenticity, copyright, and ownership protection to the danger of being breached. Of the most important concerns is the security of digital images, hence they either be protected by the embedding of watermarks if they are to be publicly visible or by converting them into an unintelligible cipher form. This conversion can be achieved by many existing encryption algorithms with proper secret keys, however, due to the increased computation efficiency, new and stronger algorithms are continually sought. In this paper, a novel image encryption scheme that is based Genetic Algorithms is developed and implemented to convert the image into cipher-image. This approach is made possible by exploiting the Genetic Algorithm (GA) properties, namely crossover and mutation that fulfill Shannon’s principle of information diffusion and confusion. Obtained experimental results of the proposed scheme has succeeded in protecting digital images against noise and attacks, and is promising as compared with currently used standard cryptographic algorithms, such as Data Encryption Standards (DES) and Advanced Encryption Standard (AES).
Keywords:	Image security, Genetic Algorithm, Secret key cryptosystems, Crossover, and Mutation
Source:	Journal of Theoretical and Applied Information Technology 15^th June 2017 -- Vol. 95. No. 11 -- 2017
Full Text