		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
November 2016 | Vol. 93 No.2

Title:	DEVELOPMENT AND APPLICATION OF A STAGE-GATE PROCESS TO REDUCE THE UNERLYING RISKS OF IT SERVICE PROJECTS
Author:	EUN-JOO JEONG, SEUNG-RYUL JEONG
Abstract:	Recently IT service projects have increased to introduce new technology as like data analytics, IoT (Internet of Things), cloud and mobile computing and to change or improve business process of finance, manufacturing, service, and government and public organizations, but lots of projects were failed due to cost-overrun, schedule delay, and fail to pass user acceptance test on time, and fail to align companys objective and strategy. There are several critical factors of project failure, for example, incorrect project cost estimation, lack of enterprise-wide risk management, unfair contract agreement, and missing or incomplete user requirements, and low quality level of design and development, and lack of user participation or cooperation for user requirement definitions and user acceptance test. To prevent the critical risk factors of project, the risks should be identified and assessed during project lifecycle, and report to project governance board, and the project governance board should make the Go/No-Go decision at the end of each project stage. The purpose of this thesis is to develop the project SGP(Stage-Gate Process) for enterprise-wide risk management structure to reduce the project failure rate, and for helping to achieve the companys objective and strategy, and then to verify the effectiveness of the project SGP through application of the SGP to actual IT service projects. We can aware the SGP is very useful to reduce the failure rate of project through preventing the cost-overrun, schedule delay, and failure to pass for user acceptance test. The SGP is consisting of assessment of deliverable by project management office and quality assurance, and Go/No-Go decision making based on quality criteria by executives for enterprise-wide risk and quality management at the end of each project stage. And we confirmed the effectiveness of SGP through FGI (Focus Group Interview), the result show that the SGP is very useful to manage cost, risk, and quality, but the effectiveness of SGP is dependent on companys project governance structure and process, and project governance boards attention and support to the SGP process.
Keywords:	Stage-Gate Process, Project management office, Risk Management, Project Stakeholder, IT Service Project, Project governance board
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	TEXTURE CLASSIFICATION BASED ON STATISTICAL PROPERTIES OF LOCAL UNITS
Author:	M. SRINIVASA RAO, V.VIJAYA KUMAR, MHM KRISHNA PRASAD
Abstract:	One of the important and crucial tasks of image analysis is to derive significant features of the images. The gray level co-occurrence matrix (GLCM) and its features derived by Haralick are widely known for texture classification. The main disadvantage of GLCM is its high dimensionality when applied on the grey level image. The local features derived from local binary pattern (LBP) have shown significant results in various image and video processing applications. The present paper derived the fundamental rotational invariant local features from LBP in the form of uniform LBP (ULBP) and treated all non-uniform LBP (NULBP) as miscellaneous. After encoding the texture into ULBP coded texture the present paper derived GLCM features and performed texture classification rate, mean absolute error and root mean square error on Brodtaz textures using various machine learning classifiers. The proposed uniform local binary pattern matrix (ULBPM) is compared with GLCM method, cross diagonal texture unit matrix (CDTM) and texture spectrum (TS) methods. The results indicate high performance of the proposed method over the existing methods.
Keywords:	Local Features, Uniform Local Binary Pattern (ULBP), Texture Classification, Graylevel Co-Occurrence Matrix.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	SCALE TO COMPOSITION FAULT INCLINED (SCFI) &SCALE TO COMPOSITION HALENESS (SCH): DESIGN OF HEURISTIC METRICS TO ASSESS SERVICE COMPOSITION IS FAULT INCLINED OR HALE
Author:	V.SUJATHA , Dr.G.APPA RAO
Abstract:	One of the considerable research objective of the current decade is developing applications by composing individual services for web and cloud environment. The majority of research in this context is aimed to optimize the service composition, which is in the raise quality. Many of existing models are heuristic scales defined by machine learning approaches. The constraint of these existing models is that they are centric to one or two de-facto factors of the quality of service such as response time and reliability. This practice of optimizing service composition is not robust and scalable in order to achieve the optimal service composition towards the raise of quality. The other significant issue of research is many of existing models are not linear towards computational complexity, which is due to the compliment of evolutions against the raise in available services count. In this con-text here we devised a two QoS metrics called Scale to Composition Fault Inclined and Scale to Composition Haleness, which enables to assess the services based on multiple number of QoS metrics and also should stabilize the computational complexity to linear. The experiment results are indicating the significance of the proposed model towards scalable and robust QoS- aware service composition.
Keywords:	Web Service Compositions, Composition Support, Service Composition Impact Scale, Service Descriptor Impact Scale, Web Service Composition Fault Proneness.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	COMPARISON OF DISTRIBUTIONAL SEMANTIC MODELS FOR RECOGNIZING TEXTUAL ENTAILMENT
Author:	YUDI WIBISONO, DWI HENDRATMO WIDYANTORO, NUR ULFA MAULIDEVI
Abstract:	Recognizing Textual Entailment (RTE) is an important task in many natural language processing. In this paper we investigate the effectiveness of distributional semantic model (DSM) in RTE task. Word2Vec and GloVe are recent methods that suitable for learning DSM using a large corpus and vocabulary. Seven distributional semantic models (DSM) generated using Word2Vec and GloVe were compared to get the best performer for RTE. To our knowledge, this paper is the first study of various DSM on RTE. We found that DSM improves entailment accuracy, with the best DSM is GloVe trained with 42 billion tokens taken from Common Crawl corpus. We also found the size of vocabulary size in DSM does not guarantee higher accuracy.
Keywords:	Recognizing Textual Entailment, Distributional Semantic Model, Text Alignment
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	QUERY ADAPTIVE HASH BASED IMAGE RETRIEVAL IN INTENT IMAGE SEARCH
Author:	B. PRASANTHI, SURESH PABBOJU, D. VASUMATHI
Abstract:	Now-a-days in websearch engines like Google, Bingo enable image search, especially the crucial task of text feature-based image retrieval. Features are very important in Content Based Image Retrieval (CBIR) that deal with web scale image search. Features like color, shape, texture etc. are used to represent quality, efficiency and scalability of images from large image databases. Conventionally, CBIR was used for dealing with quality and other features in relevant image search for image retrieval. CBIR follows high time complexity on index arrangement in large image databases. Feature Extraction is also a complex task in CBIR to retrieve quality images from overall image databases. It is considered as a very important measure to solve ambiguity in text-based image retrieval. In this paper, we propose to develop a Novel Image Intent Query Adaptive Search approach based on user query image with limited focus on text-based image retrieval. Our research seeks to capture the users search intents from the click-based image retrieval approach. Experimental evaluation shows that our approach improves precision in top ranked images, apart from user experiences with intention and visual features.
Keywords:	Content Based Image Retrieval (CBIR), Intent Image Search, Color, Shape, Visual Features
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	AUTOMATION FRAMEWORK FOR ROGUE ACCESS POINT MITIGATION IN IEEE 802.1X-BASED WLAN
Author:	NINKI HERMADUANTI, IMAM RIADI
Abstract:	Wi-Fi hotspot is a product of wireless network technology than can be easily found in public places such as airport, cafe, or shopping mall. Besides offering ease in connection, the use of wireless network technology is also raises security issue because it lies in an open or public area. There needs to be a mechanism that can control access to the wireless network to protect it from attacker or intruder. Port-based authentication system or known as IEEE 802.1X standard is a framework that provides access control to the network. But still it is possible for the attack to occur in wireless network environment protected by IEEE 802.1X, i.e. rogue Access Point (rogue AP). A rogue AP can act like authorized Access Point (authorized AP), deceiving wireless users. Therefore, it is necessary to do mitigation steps including detection and elimination of rogue AP. In this research, live forensics method is used to detect the rogue AP. Output of this research is a framework for mitigating rogue AP in an IEEE 802.1X-based Wireless Local Area Network (WLAN). This framework can also be used as a basic for doing automation process to mitigate rogue AP, helping the network administrators to minimize their manual tasks for handling the rogue AP.
Keywords:	Framework, Rogue, Access Point, Forensics, IEEE 802.1X
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	AN EMPIRICAL ANALYSIS OF THE RELATIONSHIP BETWEEN THE INITIALIZATION METHOD PERFORMANCE AND THE CONVERGENCE SPEED OF A META-HEURISTIC FOR FUZZY JOB-SHOP SCHEDULING PROBLEMS
Author:	IMAN MOUSA SHAHEED, SYAIMAK ABDUL SHUKOR, ERNA BUDHIARTI NABABAN
Abstract:	Numerous studies mentioned that the quality initial population can affect meta-heuristics convergence speed, these studies are often theoretical. However, the functionality of the initial population is extensively ignored. This overlooking may due to the literature lack of statistical evidence on the relationship between the initialization method performance and a meta-heuristic convergence speed. Therefore, this study statistically investigated aforementioned relationship by conducting an experiment and used population quality and best error rate (BRE) to gauge the performance of the state of the art initialization methods for Fuzzy Job-Shop Scheduling Problems (Fuzzy JSSPs), namely, random-based and priority rules-based methods. Thereafter, this initialization approach utilised to initiate a memetic algorithm (MA). CPU time was used to compute the MA time to reach the lower bound of 50 different sized Fuzzy JSSP instances. A Spearman's test was operated to measure the intended correlation. As a result, there was effective negative association between the initial population quality and the MA convergence speed. While, there was a dominant positive relationship between the BRE and MA convergence speed. Consequently, it is highly recommended to develop advanced initialization approaches that can generate high-quality initial population, which consists of most favourable or near to best possible solutions.
Keywords:	Fuzzy Job-Shop Scheduling Problems, Initialization Methods, Memetic Algorithm, Population Quality, Best Relative Error, Convergence Speed
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	A ROBUST SCHEME TO DEFEND AGAINST DISASSOCIATION AND DEAUTHENTICATION DOS ATTACKS IN WLAN NETWORKS
Author:	HAITHAM AMEEN NOMAN, SHAHIDAN M. ABDULLAH, SINAN AMEEN NOMAN
Abstract:	Wireless 802.11 (also known as WLAN) has many flaws that expose the medium to numerous types of attacks. WLAN control frame consists of three major parts; data, management and control frames. Data frame is whereby data carried on, in the meantime, management and control frames are both responsible for maintaining the communication between the clients and the access point. The absence of encryption at both of these two frames exposes the medium to inevitable various types of DoS attacks at Data Link Layer. The attacker might spoof the unencrypted Deauthentication/Disassociation message together with the MAC address of the targeted access point and keep retransmitting it to all clients causing a continuous disconnection in WLAN networks. Wireless 802.11w standards has succeeded mitigating the flaw by encrypting the frames, yet only when WPA2 encryption is enforced. In this paper, we developed an enhanced proposed WLAN scheme to mitigate Deauthentication and Disassociation DoS attacks on WLAN networks. The proposed scheme is based on modifying the last twenty bits of the management frame in 802.11n standard using an enhanced version of Linear Congruential Algorithm called MAX algorithm. This is to provide a layer of authentication with no need to enforce WPA2 encryption. The proposed scheme is evaluated using CommeView Simulator and showed to be robust by slowing the attacks in an average of 3551 second on both encrypted and unencrypted networks.
Keywords:	WLAN, Wireless 802.11, Disassociation Attacks, Deauthentication Attacks, Denial of Service.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	REINFORCING TEACHERS ROLE IN RETAINING STUDENTS INTERESTS DISCUSSING ONLINE IN THEIR LEARNING PROCESS AT MALAYSIAN TERTIARY INSTITUTIONS
Author:	MOHD FADZLI ALI, NOORSHAZERIZA HISHAMUDDIN, LOKMAN MOHD TAHIR, MOHD NIHRA HARUZUAN MOHD SAID
Abstract:	Many studies from the literature related to asynchronous online discussions among tertiary students provide various advantages such as allowing students flexibility to provide feedbacks [38], enabling their knowledge construction [30], developing their critical thinking [39], and interacting with the lecturers regardless of time and space [1]. Thus, the use of online discussion has further become predominant to support tertiary education. Likewise in Malaysian context, research related to online discussion has demonstrated increased confidence in students’ learning. Although the findings showed positive response, there are studies [20], [3], [29], [24] proved otherwise mainly because of the teachers weaknesses in keeping students interests and motivation to use online discussions in their learning process. Based on Ames [4] teaching strategies and Keller [21] ARCS model, a systematic guidance was developed for teachers to properly help students discussing online in completing their assignments. With reference to this systematic guidance, a qualitative case study on how to retain the students motivation using online discussion was conducted. The respondents were final year students working in small groups. Each respondent was made compulsory to answer a checklist based on the items from Khan [22] that was used to gauge their background skills in using online forum before conducting the study. The research instruments used were online discussions and interviews. The transcripts from the online discussions were analyzed using a coding scheme developed from the systematic guidance (developed from Ames [21] teaching strategies and Keller [21] ARCS model while the data from the interviews with the group leaders were used to support the findings derived from the transcript analysis. The findings revealed that the teaching strategies used in this study were able to retain the students interest and motivation to continue discussing online in completing their project assignments.
Keywords:	Asynchronous Online Discussions, ARCS Model, Students’ Motivation, Teaching Strategy, Higher Education
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	STOCHASTIC METHOD OF DATA TRANSFORMATION RDOZEN+
Author:	IVANOV MIKHAIL, STARIKOVSKIY ANDREY, ROSLIY EVGENIY, POPOV ALEKSEY, MAKSUTOV ARTEM, KUSAKIN ILYA, KUTEPOV STANISLAV, BABALOVA IRINA
Abstract:	Analysis of information security threats and the trends in the development of computer technology allows to make an unambiguous conclusion about the increasing role of stochastic methods of information protection. The most promising method of protection, namely the method of introducing the unpredictability in the work of the funds and the objects protection is universal. It can be used in conjunction with any other method of protection automatically raising their quality. A special case of stochastic methods are cryptographic methods of information protection. The trend of recent years has been the advent of algorithms based on the use of 2D and 3D stochastic transformations. This article proposes a new algorithm of 3D stochastic data transformation, which is basically aimed for information security solutions. The algorithm is characterized by the high degree of parallelism at the level of elementary operations.
Keywords:	Cryptographic Primitives, 3D Transformation, Cube Architecture, Iterative Stochastic Transformation, MixState Transformation
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	PROTOTYPE EXPERT SYSTEM USING BAYESIAN NETWORK FOR DIAGNOSE SOCIAL ILLNESS
Author:	RAHMAD KURNIAWAN, AFRIZAL M. NUR, RADO YENDRA, AHMAD FUDHOLI
Abstract:	The social illness has become main problem in Indonesia such as drug addiction, prostitution, game addiction, and so on. Based on Indonesian government, through its anti-drug agency, the National Narcotics Board (BNN) in 2015 the number of drug users are 5 million people. Drugs have caused for as many as 15,000 deaths each year in Indonesia. Peoples did not get information about social ills such as the types of drugs that have the same characteristics. As a largest Muslim country in the world may be reduce the social ills with the Islam approach. Recently, the integration of Islamic science and technology has become popular. At times the people get obstacles to get information and advice directly from expert and scholars in Islamic science. This paper is to develop a prototype expert system by providing prevention and best treatment based on Quran and Hadith. We use some of the data for knowledge base obtained from Selat Panjang, Riau. Based on the preliminary results, it has similar diagnoses with expert. A prototype expert system using Bayesian Network has been successful and capability for early diagnosing and educating the peoples in social ills cases based on Quran, Hadith and advice of experts but still has plenty room for improvement.
Keywords:	Bayesian Network; Expert System; Social Illness
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	A PERSONALIZED SEARCH ENGINE BASED ON CORRELATION CLUSTERING METHOD
Author:	BOURAIR ALATTAR , NORITA MD. NORWAWI
Abstract:	Nowadays, search engines tend to use latest technologies in enhancing the personalization of web searches, which leads to better understanding of user requirements. This paper aims to address the problem of enhancing the efficiency of search system by mining data logs. Search logs are associated with all the interactions that have been done between the user and the search engine including the query, the resulted pages and the selection. The paper also aims minimize the ambiguity within the query whilst the partitioning-based clustering aims to reduce the search space by dividing the data into groups that contain similar objects. To do so, this paper conduct several experiments to evaluate correlation clustering method. The method of this paper includes a pre-processing phase, which in turn involves tokenization, stop-words removal, and stemming. In addition, we evaluates the impact of the two similarity/distance measures (Cosine similarity and Jaccard coefficient) on the results of the correlation clustering method. Experimental results obtained are quite satisfactory in terms of the Precision, Recall and F-score. .
Keywords:	Personalized Search Engine, Correlation Clustering algorithm, similarity/distance measures.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	DIFFERENTIAL SEARCH ALGORITHM IN MULTI MACHINE POWER SYSTEM STABILIZERS FOR DAMPING OSCILLATIONS
Author:	NAZ NIAMUL ISLAM, M A HANNAN, AZAH MOHAMED, HUSSAIN SHAREEF
Abstract:	Power system oscillations, a major problem in power system, is suppressed employing power system stabilizers (PSSs). Proper optimization of PSSs is a complex design problem. In this paper, a bio-inspired metaheuristic optimization technique named as differential search algorithm (DSA) is presented to solve the optimization problem of multi machine PSSs. The optimization of PSSs is converted as a cost function then DSA is applied to tune the optimal parameters for PSSs by minimizing the cost function. PSSs are optimized in order to achieve adequate damping for local and inter-area modes of growing oscillations in a multi machine power system. Simulations are conducted in linear and non-linear models of power system to verify the robustness of proposed algorithm. A comprehensive investigation is conducted to compare the performance of DSA based PSSs with the tuned PSSs using bacterial foraging optimization algorithm (BFOA) and particle swarm optimization (PSO) in terms of convergence, improvements of electromechanical modes and system damping over oscillations. The obtained results show that the presented DSA technique is efficient for PSS optimization for the safety of multi machine power system.
Keywords:	Differential search algorithm (DSA), Power system stabilizer (PSS), Power system oscillations, Damping controller, Multi machine power system
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	AUTOMATIC QUESTION CLASSIFICATION MODELS FOR COMPUTER PROGRAMMING EXAMINATION: A SYSTEMATIC LITERATURE REVIEW
Author:	MUSTAFA KADHIM TAQI, ROSMAH ALI
Abstract:	A test is the commonest method to evaluate the progress and potential of candidates in any field, especially in academic fields. In the academic field, exams help evaluate the understanding, applicative ability, and retainable knowledge of a student. Therefore, the questions need to be suitably set, so that all these areas can be judged. The results of these tests help determine if the student is fit for the next level of education. Setting the right question paper is a major challenge for the teachers concerned. The current study aims to analyze the ongoing question classification models with reference to the set of formulated research questions. In order to locate question classification models, relevant keywords were used in the search terms. A set of nine different studies were picked from the search processes. In the studies, 4 stands for journal articles, and 5 stands for conference papers. Question classification has been discussed in the computing domain, especially with respect to computer programming assessment. A more extensive examination of this classification reveals quite a few shortcomings of the prevailing classification methods. These include the absence of suitable taxonomy for computer programming questions, limitation in approaches to handle multi-labelling, and a need for methods compatible to tackle code-mixed question classification. Furthermore, the necessity to develop advanced hybrid feature selection methods in order to enhance the classification performance.
Keywords:	Question Classification, Feature Selection, Bloom Taxonomy, Computer Programming, Systematic Literature Review
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	CLOUD RADIO ACCESS NETWORK TECHNOLOGY FOR THE NEXT FIFTH GENERATION MOBILE NETWORKS
Author:	MAGRI HICHAM, NOREDDINE ABGHOUR, MOHAMMED OUZZIF
Abstract:	Traditional mobile networks become unable to cope with the huge use of wireless internet services and the growth of data traffic. The solution to this challenges can be found in a novel mobile network architecture called Cloud Radio Access Network (C-RAN) that is expected to be the essential part of the next fifth generation of mobile networks (5G). The C-RAN system will achieve increased significant cost and address number of challenges for mobile operators in terms of optimization, configuration, network controllability and software management. This paper will present and give an overview of C-RAN including system architecture and key techniques. It shows challenges and benefits of this technology. The paper presents also fronthhaul network requirements that must be achieved by the CPRI technology and transport options for C-RAN. User data plane, CPRI planes control, planes data Management and CPRI frame synchronization are also discussed.
Keywords:	C-RAN, 5G, CPRI, Fronthaul.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	BIG DATA ANALYTICS IMPLEMENTATION FOR VALUE DISCOVERY: A SYSTEMATIC LITERATURE REVIEW
Author:	CECILIA ADRIAN, FATIMAH SIDI, RUSLI ABDULLAH, ISKANDAR ISHAK, LILLY SURIANI AFFENDEY, MARZANAH A. JABAR
Abstract:	The growing number of big data technologies and analytic solutions has been developed to support the requirement of big data implementation. The capability of analyzing big data becomes critical issues in the big data implementation because the traditional analytics tools are no longer suitable to process and analyze the massive amount and different types of data. In the recent years, technological issues and challenges on big data adoptions have been actively conducted globally. However, there are still lacking of studies on how big data implementation can derive and discover values for better decision making. The intent of this review is to investigate the capability components for Big Data Analytics (BDA) implementation towards value discovery. Based on this investigation, it was found that the capability components that may impact value discovery is formulating big data framework that includes the enabler technology and processing and using sufficient analytic techniques for analysing big data.
Keywords:	Big Data Analytics Implementation, Capability Components, Processing, Analytics Techniques, Value Discovery
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	CLUSTERING AND SEARCHING TECHNIQUE FOR SELECTION HORTICULTURAL USING SELF ORGANIZING MAPS AND GENETIC ALGORITHM
Author:	ASTI DWI IRFIANTI, RETANTYO WARDOYO, SRI HARTATI, ENDANG SULISTYANINGSIH
Abstract:	The purpose of this study is to develop model for determination of horticultural commodities based on the terms of an area to grow crops. The method use in SOMnGA (Self Organizing Maps and Genetic Algorithm). This method consists of three stages: 1) Clustering, 2) Filtering and 3) Searching based on the shortest distance between the growing crop terms and region parameters (temperature, rainfall and humidity). The data used is secondary data obtained from Litbangdeptan, which is the data collection about the requirement needs of horticultural growth crops consisting of fruits, vegetables, ornamental and biofarmaka plants based on the standardization of the FAO (Food and Agriculture Organization). The test data used in this study were 30 types of horticultural crops. The parameters are used for the process of grouping consists of temperature, rainfall, humidity, base saturation, C-Organic, pH2O, alkalinity, salinity, rocks and Outcrop. SOMnGA method works with an algorithm that can contribute to this research. SOM role classifying plant data based on 10 parameters. Stages Clustering by using SOM created a group of plants that have a closeness characteristics to the needs of plant growth requirements. Then the result of grouped is filtered based on area parameters that user required. Furthermore GA has important part in chooseing the plant filtered result data to produce a list of the closest distance plants towards parameter region. SOMnGA testing consists of two parts: 1) using the method of Davies Bouldin Index (DBI) to produce numbers of 0,017 and an error rate of 10%. 2) comparing with SGA (Simple GA) and SOMnGA. In this study indicates that the SOMnGA method produced shorter iterations to produce outcomes. Testing of 25oC temperature, 125mm Rainfall and 40% Humidity generate a distance of 1941 with each iteration 2276 (SGA) and 25 (SOMnGA) Verify the model in the field using the accuracy method showed a value of 86%. SOMnGA method is a combination of methods that can be used to determine the main commodity based regional horticultural effectively and efficiently. So that the plants election result use SOMnGA could be used as a guide the alternative for farming planning team as one way to determine the main commodity of a region.
Keywords:	Clustering, Self Organizing Maps, Genetic Algorithm, Horticulture
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	3D PLANE-BASED MAPS SIMPLIFICATION FOR RGB-D SLAM SYSTEMS
Author:	Hakim ELCHAOUI ELGHOR, David ROUSSEL, Fakhreddine ABABSA
Abstract:	RGB-D sensors offer new prospects to significantly develop robotic navigation and interaction capabilities. For applications requiring a high level of precision such as Simultaneous Localization and Mapping (SLAM), using the observed geometry can be a good solution to better constrain the problem and help improve indoor 3D reconstruction. This paper describes an RGB-D SLAM system benefiting from planes segmentation to generate lightweight 3D plane-based maps. Our aim here is to produce global 3D maps composed only by 3D planes unlike existing representations with millions of 3D points. Besides real-time trajectory estimation, the proposed method segments each input depth image into several planes, and then merges the obtained planes into a 3D plane-based reconstruction. This allows to avoid the high cost 3D point-based maps as RGB-D data contain a large number of points and significant redundant information. Our algorithm guarantees a geometric representation of the environment so these kinds of maps can be useful for indoor robot navigation as well as augmented reality applications.
Keywords:	RGB-D SLAM systems, Pose Estimation, 3D Planar Features, 3D Planar Maps.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	A CLASSIFICATION METHOD FOR IDENTIFYING CONFIDENTIAL DATA TO ENHANCE EFFICIENCY OF QUERY PROCESSING OVER CLOUD
Author:	HUSSEIN ALBADRI, ROSSILAWATI SULAIMAN
Abstract:	With the increased use of Database-as-a-Service (DAAS), several issues also come in parallel, especially in translating and executing queries to and from the database securely and efficiently. These issues are in response towards potential attacks such as attempting to copy or eavesdrop the database via queries. Existing security mechanisms include securing the queries by using encryption. However, encrypting the queries significantly affects the efficiency of query processing because of the security overhead from the encrypting and decrypting processes. This study aims to address this problem by proposing a divide-and-conquer strategy in which partial encryptions is used on the queries. This is performed by classifying the data into sensitive and non-sensitive categories using a classification approach, so that only the sensitive data will be encrypted. The classification used in this study is based on the data classification policy from the Columbia University. Firstly, a manual annotation is conducted to label the data fields into sensitive and non-sensitive categories. Next, rules are generated in order to classify the queried data. If a query contains sensitive data, the encryption will specifically be applied to the sensitive data, whereas the non-sensitive data will remain unencrypted. Experiments have been conducted using real-time data from Baghdad University that is related to students information consisting 35 tables and 362 fields. The evaluation is based on the comparison of security overhead of the fully encryption (without classification) and partial encryption (with the classification) using Advance Encryption Standard (AES). Results shown that the classification method has significantly reduced the time used to process the query. This implies that the partial encryption based on classifying the data into sensitive and non-sensitive categories has improves the efficiency of query processing.
Keywords:	Cloud Computing, Cloud Database, Secure Query Processing, Cloud Query Processing
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	SUCCESSFUL IMPLEMENTATION OF QUOTEWIN SOFTWARE TENDERING SYSTEM: A CASE STUDY OF A MULTINATIONAL COMPANY
Author:	YUSRI ARSHAD, SHARIFAH NORHAFIZA BINTI SYED IBRAHIM, X.C.CHOOK
Abstract:	The aim of this study is to investigate role of QuoteWin software in tendering system in multinational companies. QuoteWin software is designed to make software quote management hassle free and straight forward to the tendering system. This robust software provides scalable and flexible solution to manage and respond projects of any complexity level. A framework called Semantic-based Planning Optimization Composition (SPOC) is composed to evaluate the request-for-quote software and observe tender respond. In the study, four phase of SPOC: Discovery, Planning, Quote Execution and Optimization were implemented to evaluate the software performance in company tendering system. The study is to investigate QuoteWin software fulfills requirements of company works needs to be leading business software in request-for-quote process. The data was collected from Flextronics Technology (Malaysia) Sdn Bhd, and Escatec Sdn Bhd. A series of interview were conducted with the software users in both companies. The researcher identified that there are five elements important to the success of tendering process. As a conclusion, the QuoteWin software is suitable to perform as an on-line tool for tendering system. The data collected from both companies has proved that the performance of this software is better and matches with Semantic-based Planning Optimization Composition.
Keywords:	Enterprise resource planning system, Decision support system, Multinational company, Malaysia, Case study
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	ON THE MODELING OF TOURISTS VISIT TO TOURIST ATTRACTION IN SURABAYA USING NEURAL NETWORK
Author:	R. PRAWIRO KUSUMO R., NUR IRIAWAN
Abstract:	Tourism has a strategic role in the developing of regional economy and society. Surabaya has some object and tourist attractions potentially attracting foreign and domestic tourists to come to Surabaya. The monthly number of tourist who visits to several tourist attractions in Surabaya shows a pattern as time serially data, seasonal, and could be correlated among them. The traditional vector autoregressive (VAR) would be firstly applied to the data. For the comparison, neural networks (NN) couple with VAR structure as an input is proposed to model this data. This paper shows that this proposed method gives better performance than when the data was directly modeled using VAR only. This research also shows that the increasing number of neurons in the hidden layer does not always give effect to the decreasing the value of MAPE as a tool to differentiate the models.
Keywords:	tourism, tourist visit, time series, VAR, neural network
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	THE EFFECT OF WEB 2.0 USAGE ON INNOVATIVE WORK BEHAVIOR AMONG ACADEMIA IN MALAYSIAN RESEARCH UNIVERSITIES
Author:	AZRA AYUE ABDUL RAHMAN, SITI AISYAH PANATIK, ROSE ALINDA ALIAS
Abstract:	Previous study indicates the users degree of Web 2.0 usage is positively associated with his or her behavior. However, there is a paucity in examining the effect of Web 2.0 usage especially on innovative work behavior among academia in research universities, even though it is imperative to be identified due to its demanding research nature. Web 2.0 is technologically driven and designed to allow people to communicate, share information and create online communities. Meanwhile, innovative work behavior refers to the creativity and involvement in bringing changes and new ideas in duties or in solving problems especially among academia in research universities which has become the focus of this study. Innovative work behavior consists of idea generation, idea promotion, and idea realization. Therefore, this study aims to identify the effect of Web 2.0 usage on innovative work behavior among academia in research universities. In our endeavor to this matter, we view the issue from a positivist paradigm with quantitative approach. This approach used surveys as research strategy by adapting questionnaire technique. The data collection has been conducted among 393 lecturers in five research universities and emphasizes on the lecturers research activities. Accordingly, data collected were analyzed using SPSS and SEM AMOS by looking at the exploratory factor analysis (EFA), confirmatory factor analysis (CFA), model fit, and path analysis. The result of this study indicates that the Web 2.0 usage has a positive and significant relationship with the idea generation, idea promotion and idea realization of innovative work behavior.
Keywords:	Web 2.0 Usage, Innovative Work Behavior, Academia
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	THE USE OF E-AUDIT IN INCREASING GOVERNMENT AUDIT FINDING
Author:	RINI RAHMA, INDRAWATI YUHERTIANA, SITI SUNDARI
Abstract:	The paper aims to explore the usefulness of e-audit implementation in enhancing government auditor performance. It scrutinized in depth the auditor behavior change related the new audit technique based on information technology. The study used a qualitative approach by observing and interviewing Indonesia government auditor. Participatory observation involved in gathering rich data and analysis in Miles Huberman interactive technique. The results showed that the availability of data hasnt been fulfilled yet by the entity and the period time given to the auditors to access the e-audit portal is too short, in addition, the auditors don't optimally take advantage of features available in the portal of e-audit. Implementation of e-audit has helped streamline the examination process, and increase the value of the audit findings comparison. This shows that the implementation of e-audit create of transparency and accountability in local government financial management.
Keywords:	E-Audit, Government, Qualitative Research, Audit Finding
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	PERFORMANCE AND RELIABILITY FOR IRIS RECOGNITION BASED ON CORRECT SEGMENTATION
Author:	KHIDER NASSIF JASSIM, ASAMA KUDER NSEAF
Abstract:	The recognition of Iris is regarded as the most dependable and accurate system of biometric identification so far. This system captures an individual's eye image in which the iris in the image is used for further normalization as well as segmentation to extract its feature. The iris recognition systems performance relies heavily on the segmentation process. In fact, segmentation process is employed for localizing the accurate iris region in a certain portion of an eye and this must be correctly and accurately carried out to take out the eyelashes, reflection, eyelids and pupil noises found in the region of iris. In this study, Enhance Hough Transform (EHT) approach in the segmentation process will be used. The enhancement locates the pupil region of eye image by using threshold and Circle Hough Transform (CHT). Hence, the pupil parameter will capture the region of iris from the image of eye and then apply Hough Transform for locating outer boundary in less space search. This approach is found more effective in emphasizing the accuracy of iris segmentation. The segmented iris region is normalized so as to reduce the dimensional inconsistencies among the regions of iris through adopting the Model of Daugmans Rubber Sheet. The iris features were, then, encoded through convolving the normalized region of the iris with 1D Log-Gabor filters and phase quantizing the output so as to create a bit-wise biometric template. The distance of Hamming was selected as corresponding metric which provided the measure of a number of bits which did not match up among the iris templates. This proposed method is tested with the eye images obtained from MMU V1 iris database. The performance of such a proposed method showed that the accuracy of the iris recognition increased.
Keywords:	Iris Biometrics, Iris Recognition, Enhance Iris Segmentation, Hough Transform, Geodesic Active Contour, MMU Iris Database
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	A NOVEL APPROACH OF MULTIMEDIA INSTRUCTION APPLICATIONS IN ENGINEERING EDUCATION
Author:	ATAOLLAH ZAREI , KHAIRIYAH MOHD. YUSOF, MOHD FADZIL BIN DAUD, HOSHANG KOLIVAND, TANZILA SABA
Abstract:	Effective use of educational technology depends on knowledge of why and how to utilize technology to solve teaching and learning problems. The present study first conducts a systematic literature review of the limited studies undertaken on multimedia instruction applications for engineering education to critique the current status of knowledge in this area. The conventional qualitative content analysis method was employed for data analysis. The results highlighted the incompatibility of three basic educational elements i.e. engineering curriculum, educational resources and engineering students learning characteristics all of which posed major challenges in teaching and learning engineering courses. Multimedia instruction enhances engineering students understanding of engineering concepts, procedures, problems and solutions through direct visualization. Furthermore, it could indirectly assist students in achieving higher order learning levels and skills through enhancing or supporting educational resources and increasing students motivation. Mobile multimedia instruction and a student-generated multimedia learning approach to improve engineering education are suggested for future research.
Keywords:	Educational Technology; Engineering Education; Multimedia Instruction; Teaching And Learning Problems; Systematic Literature Review
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	DEEP NEURAL NETWORKS FOR IRIS RECOGNITION SYSTEM BASED ON VIDEO: STACKED SPARSE AUTO ENCODERS (SSAE) AND BI-PROPAGATION NEURAL NETWORK MODELS
Author:	ASAMA KUDER NSEAF, AZIZAH JAAFAR, KHIDER NASSIF JASSIM, AHMED KHUDHUR NSAIF, MOURAD OUDELHA
Abstract:	Iris recognition technique is now regarded among the most trustworthy biometrics tactics. This is basically ascribed to its extraordinary consistency in identifying individuals. Moreover, this technique is highly efficient because of iris distinctive characteristics and due to its ability to protect the iris against environmental and aging effects. The Problem statement of this work is that the study presented an effective Iris recognition mechanism that is dependent on video. In this paper, it includes the data created based on best frame selected from iris video, then iris segmentation, normalization and feature extraction based on Hough Transform approach, Daugman rubber sheet modal and 1D Log-Gabor filter respectively. Flowed this proposed iris matching was proposed on the basis of two Deep Neural Networks models separately: Stacked Sparse Auto Encoders (SSAE) and Bi-propagation Neural network Models. Results are executed experimentally on the MBGC v1 NIR Iris Video datasets from the National Institute for Standards and Technology (NIST). The results displayed that Bi-propagation was the most efficient training algorithm for the iris recognition system based on video, and Stacked Sparse Auto Encoders (SSAE) is faster than Bi-propagation. Finally, that can be conclude an iris recognition system based on video that produces based on both separately models: Stacked Sparse Auto Encoders (SSAE) and Bi-propagation Neural network Models was achieves very low error rates was mean the both models are successfully for iris recognition system based on video.
Keywords:	Deep Neural Networks, Bi-Propagation Neural Network, Biometric Identification, Image Segmentation, Iris Recognition, Stacked Sparse Auto Encoders, Frame Selection, Video Iris Recognition.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	A SYSTEMATIC LITERATURE REVIEW OF TECHNOLOGICAL FACTORS FOR E-LEARNING READINESS IN HIGHER EDUCATION
Author:	ASMA ALI MOSA AL-ARAIBI, MOHD NAZRI BIN MAHRIN, RASIMAH CHE MOHD YUSOFF
Abstract:	E-learning is an innovation that is increasingly adopted in higher education settings. Although most higher education institutions have adopted e-learning, they still face challenges in its implementation, especially in relation to the technological aspects. The primary reason for e-learning implementation challenges is a lack of assessment of the readiness for e-learning. The successful implementation of e-learning relies on assessing the readiness of technological aspects in order to realize the benefits of e-learning and reduce the barriers to e-learning implementation. Studies on e-learning readiness lack agreement on the important technological aspects; thus, there remains a need to identify the relevant factors that shape the technological aspects of e-learning readiness. This paper provides a systematic review of the literature, with the aim to identify the technological aspects of e-learning readiness in higher education.
Keywords:	Systematic Literature Review (SLR), Technological Factors, E-Learning Readiness, Higher Education
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	OPTIMIZATION ECONOMIC POWER GENERATION USING MODIFIED IMPROVED PSO ALGORITHM METHODS
Author:	STEVEN HUMENA,. SALAMA MANJANG,. INDAR CHAERAH GUNADIN
Abstract:	Fuel consumption on operation of power generation is one of the things that need to get special attention because most of the operating costs incurred is fuel costs. The output of the power generation always strived to meet the needs of the loads. Economical optimization is an attempt to minimize the cost of power generation fuel. This research proposes the application of the Algorithm Methods of Modified Improved Particle Swarm Optimization (MIPSO) that are compared with the Lagrange method and the Improved Particle Swarm Optimization (IPSO) in the case of the IEEE 30-bus system as a validation, in which the results of the simulation of MIPSO method can minimize the cost to 575.28 $/hour compared to the Lagrange method at 575.32 $/hour and IPSO method at 575.29 $ /hour. Then MIPSO Algorithm Method applied to the SULSELBAR 150 kV interconnection system are compared with the cost of a real system, the results of the simulation showed that the MIPSO method algorithm can reduce the cost of power plant to Rp. 51,706,000.- per hour or decrease operating costs of around 13.73% per hour.
Keywords:	Optimization Economic, Modified Improved PSO Algorithm Methods, 150kv SULSELBAR Interconnection System
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	THE LEVEL OF ICT USAGE AND ITS EFFECT ON HRM FUNCTIONS IN EDUCATIONAL INSTITUTIONS IN ABHA - SAUDI ARABIA: AN EMPLOYEES' PERSPECTIVE
Author:	Dr. RAID M AL-ADAILEH, Dr. MOHAMMAD S. SARAIREH, RAJAE A AlOMIS
Abstract:	The present study aimed to identify the level of Information and Communication Technology (ICT) usage and the effect of ICT dimensions on Human Resources Management (HRM) functions in educational institutions in Abha according to employees' point of view. To achieve these goals, the study developed a questionnaire designed for this purpose. Convenient sample was selected consisting of (160) employees working in educational institutions in Abha. The results were as follows: There is a statistically significant effect at (0,05) level for "databases" and "softwar" on HRM functions. The level of agreement with the statements measuring ICT dimensions' usage is medium for all ICT dimensions The study provided some recommendations according to study results, among them: Make more efforts to improve both (Databases and software) as dimensions of ICT since these two dimensions significantly affect the functions of HRM. Educational management must improve the usage levels of ICT to realize the added value of ICT tools
Keywords:	ICT Usage, Human Resources Functions, Databases, Software, Hardware, Internet.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	ARTIFACT REMOVAL IN ECG SIGNALS USING MODIFIED DATA NORMALIZATION BASED SIGNAL ENHANCEMENT UNITS FOR HEALTH CARE MONITORING SYSTEMS
Author:	NAGESH MANTRAVADI, S.V.A.V. PRASAD, MD ZIA UR RAHMAN
Abstract:	Low complexity noise cancellation structures are needed for reliable transmission of ECG signals at real time environments. These low complexity structures can be developed with the help of the partial update techniques for better convergence and complexity. In this paper the same idea is used to derive several structures which are good at convergence and complexity. Based on partial update mechanism of the coefficients of the adaptive filter, we upgraded the conventional normalized least mean square (NLMS) algorithm. This modified algorithm updates only some coefficients of the taps where the signal characteristics widely deviate from the previous iteration. The modified NLMS (MNLMS) based on partial update mechanism is combined with signum based algorithms to minimize number of multiplications during filtering process. Further, we proposed maximum value of data for normalizing the step size to decrease the number of multiplications in the denominator of the normalization function. These are suitable to operate at high data rate applications, and to test the working of these structures in real time conditions the MIT-BIH arrhythmia database was used. Here the signal to noise ratio, the miss adjustment error is used as performance measures and all the test data is tabulated. The structures have shown good performance over the standard LMS algorithm in terms of the filtering, complexity and convergence.
Keywords:	Adaptive Noise Canceller, Artifacts, Computational Complexity, Convergence, ECG Signal.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	FEATURE SELECTION IN WEB NER USING GENETIC ALGORITHM APPROACH
Author:	MOHAMMED MOATH ABDULGHANI, SABRINA TIUN
Abstract:	Named Entity Recognition (NER) is the field of recognizing nouns such as names of people, corporations, places and dates. The process of extracting NEs is mainly relying on supervised machine learning techniques. Hence, utilizing proper features have a significant impact on the performance of recognizing the entities. Several approaches have been proposed for reducing the feature dimensionality of NER. However, these approaches have concentrated on the traditional features or so-called textual features. Recently, extracting information form web pages has caught the researchers attentions regarding the valuable information that lies on such pages. Extracting NEs from web pages has brought tremendous kinds of features which are inspired from the web nature. Apparently, combining the traditional features with the web features would expand the feature space. Therefore, there is an essential demand for accommodating feature selection for the process of extracting NEs from web pages. This paper proposes a feature selection approach based on Genetic Algorithm for extracting NEs from web pages. The dataset was collected from business web pages. Whilst, the feature set consists of text features such as n-gram and web features such as block position and font type. Finally, a SVM classifier was used to classify the NEs. Results shown that Genetic Algorithm has the ability to identify the most accurate features
Keywords:	Named Entity Recognition, Feature Selection, Genetic Algorithm, Support Vector Machine, Web Pages
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	PREDICTING THE OUTCOMES OF TRAUMATIC BRAIN INJURY USING ACCURATE AND DYNAMIC PREDICTIVE MODEL
Author:	HAMDAN O. ALANAZI, ABDUL HANAN ABDULLAH, KASHIF NASEER QURESHI, MOUSSA LARBANI, MOHAMMED AL JUMAH
Abstract:	Predictive models have been used widely to predict the diseases outcomes in health sector. These predictive models are emerged with new information and communication technologies. Traumatic brain injury has recognizes as a serious and crucial health problem all over the world. In order to predict brain injuries outcomes, the predictive models are still suffered with predictive performance. In this paper, we propose a new predictive model and traumatic brain injury predictive model to improve the predictive performance to classifying the disease predictions into different categories. These proposed predictive models support to develop the traumatic brain injury predictive model. A primary dataset is constructed which is based on approved set of features by the neurologist. The results of proposed model is indicated that model has achieved the best average ranking in terms of accuracy, sensitivity and specificity.
Keywords:	Predictive Model, Traumatic Brain Injury, Outcomes, Sensitivity, Specificity, Accuracy, Multi-Class Prediction
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	CPHC BASED PROCEDURE FOR AUTOMATIC DETECTION OF MICRO-ANEURYSMS IN RETINAL IMAGES
Author:	G. SRINIVASA RAO, Y.SRINIVASA RAO
Abstract:	Now a days micro-aneurysms (MA) in retinal color images is focusing concept to solution for diabetic retinopathy in recent applications researched by all the analysts in retinopathy. MA detection is a crucial step in diagnosis in retinal images, conventionally more number of concepts and techniques were introduced for automatic detection of MA in pre-processed retinal images. Cross section profile analysis realizes to detect MA based on length and color of each pixel values subsequently. Moral limitation of Cross-Section Profile Analysis is dimensionality of retinal images with respect to pixel changed values. So in this paper we propose to develop CPHC (Classification by Pattern-Based Hierarchical Clustering), a semi supervised pattern based cluster hierarchy by means of classification. CPHC methodology has been tested in ROC (Retinopathy Online Challenge) with competitive analysis in detection of MA in retinal images. Experimental results show efficient time complexity, sensitivity calculation with comparison of cross section analysis in recent contribution of MA with processing of retinal images.
Keywords:	Micro aneurysms, Color Retinal Images, Pattern based Classification, Hierarchal Clustering
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	PRELIMINARY STUDY FOR EXPLORING THE MAJOR PROBLEMS AND ACTIVITIES OF MOBILE LEARNING SYSTEM: A CASE STUDY OF JORDAN
Author:	MOHAMMED AMIN ALMAIAH, MASITA ABDUL JALIL, MUSTAFA MAN
Abstract:	Acceptance of new system or technology has been become a prior step for a successful implementation of any system. Previous studies revealed that the acceptance of mobile learning system among students in Jordan is still very low. Few studies have investigated what the actual challenges influencing acceptance of mobile learning system in Jordanian universities. The current study investigates the main challenges that impede acceptance of mobile learning in Jordanian universities. This study also determines the activities and services of mobile learning system based on potential needs of students. In this study, we employed the questionnaire and interview approaches, targeting students from five universities across Jordan. This paper presents two portions of the findings; qualitative findings identified four main challenges that include the quality of services, availability of learning content, design and technical issues and students' requirements. In contrast, quantitative findings presented the most important services that students would like to perform on mobile learning system.
Keywords:	Mobile learning system, Acceptance, Qualitative, Quantitative, Students perceptions.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text

Title:	EXPLORING FUNCTIONAL AND NON-FUNCTIONAL REQUIREMENTS OF SOCIAL MEDIA ON KNOWLEDGE SHARING
Author:	LIMING WU, NORAINI CHE PA, RUSLI ABDULLAH, WAN NURHAYATI AB.RAHMAN, MCXIN TEE
Abstract:	Social media (SM) are designed for easily online information sharing and communicating among people, and the sites relate to entertainment, educational and business domains. From requirement elicitation and analysis, social media provide effective communication and sharing on the knowledge and information of system development among stakeholders. This paper aims to identify the relevant functional and non-functional requirements for knowledge sharing (KS), and explore the relationships between the requirements and perceived social media to support knowledge sharing. Hence, a survey was conducted that involve software requirements practitioners in order to gather the requirements on KS. Besides that, partial least squares (PLS) method was used to evaluate the hypothesis and research model. The findings of this study represented that there was a positive and strong relationship between functional requirements and Perceived SM to support requirements knowledge sharing (RKS), however, non-functional requirements has a weak relationship with Perceived SM to support RKS.
Keywords:	Social Media, Functional, Non-functional, Requirements, Knowledge Sharing
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2016 -- Vol. 93. No. 2 -- 2016
Full Text