		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

August 2017 | Vol. 95 No.15

Title:	PROTECT SENSITIVE KNOWLEDGE IN DATA MINING CLUSTERING ALGORITHM
Author:	ALAA KHALIL JUMAA, AYSAR A. ABUDALRAHMAN, REBWAR RASHID AZIZ, ABDUSALAM ABDULLA SHALTOOKI
Abstract:	Privacy preserving knowledge discovery is a new and very important topic in data mining that is perfectly talked about the privacy of data and information. This paper focuses on protecting the knowledge in the clustering data mining techniques (K-Mean Clustering). Moreover, a new algorithm is suggested for protecting sensitive clusters, which uses the Adaptive noise techniques for protecting process. In the proposed algorithm, the adaptive noise values that are used for protecting sensitive clusters are evaluated depending on the original database values. In deep, the evaluated noise values depend on the distances (Euclidian Distance) between Sensitive Cluster and the rest of the other clusters (Non-Sensitive Clusters) for the original database. The proposed algorithm use three different techniques for protecting sensitive cluster. The prototype system was used to perform the proposed algorithm. For the three different datasets that are used in a prototype system implementation, the experimental results show that the proposed algorithm is protecting Sensitive Clusters with High Privacy Ratio and Low Information Loss Ratio. Hence, the proposed system provides a good accuracy with a low ratio of side effects, and it supports high level of privacy.
Keywords:	Privacy preserving, knowledge discovery, K-Mean Clustering, sensitive clusters Euclidian Distance, Privacy Ratio.
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	SATELLITE IMAGE CO-REGISTRATION BASED ON HYBRID INVARIANT LOCAL FEATURES
Author:	R. SWATHI, DR. A. SREENIVAS
Abstract:	It is a challenging task to attain significant automatic registration between the two satellite images due to variation in illumination and resolution of the images, dissimilar perspectives and the local deformations within the image. These concerns are rectified by an automatic registration scheme depends on a hybrid invariant feature combination of both Speeded-Up Robust Features (SURF) and Binary Robust Invariant Scalable Keypoints (BRISK). In the registration procedure, this feature combination speeds up the feature extraction and matching. Here, it makes the matching point pairs distributed consistently in satellite images and also further enhance the accuracy of input image rectification. Experimental results proves that the proposed scheme is very superior in Image Registration (IR) than the existing methods.
Keywords:	Automatic registration, Binary Robust Invariant Scalable Keypoints, Coarse matching, Speeded-Up Robust Features
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	THE ROLE OF THE OVERALL EQUIPMENT EFFECTIVENESS AS A DECISION SUPPORT TOOL FOR STRUCTURING THE ROADMAP OF A TFS TRANSFORMATION (CONSTRAINT THEORY, SAFETY OF OPERATION, AND SIX SIGMA)
Author:	RABIAE SAIDI, PR AZIZ SOULHI, PR JAMILA EL ALAMI
Abstract:	The purpose of this article is to explain how the overall equipment effectiveness (OEE) is used to initiate and structure reflection on a new approach called "TSF transformation", that can improve the perfor-mance of the means of production combining the theory of Constraints (ToC) and its translation to identi-fy machine-specific bottlenecks, Six sigma method to avoid variability of key maintenance parameters such as reliability and maintainability, availability and security, and (Such as survival law, reliability dia-grams, etc.) that could be integrated into the Six Sigma method, like MSP (Statistical Process Methods) methods.
Keywords:	Bottlenecks, Overall Equipment Effectiveness, Reliability-Based Maintenance, FMECA Anal-ysis, Operational Safety, Theory Of Constraints, Six Sigma
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	SURVEY ON NUDITY DETECTION: OPPORTUNITIES AND CHALLENGES BASED ON AWRAH CONCEPT IN ISLAMIC SHARI�A
Author:	GIAT KARYONO, ASMALA AHMAD, SITI AZIRAH ASMAI
Abstract:	The nudity or nakedness which known as awrah in Islam is part of the human body which in principle should not be seen by other people except those qualified to be her or his mahram or in an emergency or urgent need.Nudity detection technique has long been receiving a lot of attention by researchers worldwide due to its importance particularly to the global Muslim community. In this paper, the techniques were separated into four classifications namely methods based on body structure, image retrieval, the features of skin region, and bag-of-visual-words (BoVW). All of these techniques are applicable to some areas of skin on the body as well as on the sexual organs that should be visible to determine nude or not. While the concept of nakedness in Islamic Shari'a has different rules between men and women, such as the limit of male �awrah is between the navel and the knees, while the limit of female �awrah is the entire body except the face and hands which should be closed using the hijab. In general, existing techniques can be used to detect nakedness concerned bythe Islamic Shari'a. The selection ofhese techniques are employed based on the areas of skin on the body as well as or the sexual organs to indicate whether it falls to thenude category or not. While in Islamic Shari'a, different 'awrah rules are required for men and women such as the limit 'awrah, the requirements of clothes as cover awrah, and kinds of shapes and shades of Hijabs in various countries (for women only). These problems are the opportunities and challenges for the researcher to propose an �awrah detection technique in accordance with the Islamic Shari'a.
Keywords:	Awrah Detection; Nudity Detection; Based On Body Structure; Based On Content Image Retrieval, Based On Regions, Based On Visual Words
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	HYBRID METHOD FOR MEDICAL IMAGE SGMENTATION IN WAVELET DOMAIN
Author:	AREE ALI MOHAMMED, GORAN OMER ALI
Abstract:	In this research, a hybrid medical image segmentation in both spatial and frequency domain is proposed. It is aimed to detect tumor and find the accuracy detection in both spatial and frequency domain. An important algorithm is added to our research which is finding the biggest contour algorithm. This algorithm used to detect tumor region in digital image that differ in properties and provide complementary information about regions, which is not obtained from hybrid image segmentation. This filter is used to remove smaller objects (noise) and extracting only the biggest objects. Finally the average time is found in both spatial and frequency domain. Test results show that for the five set of the image samples, when the contour algorithm is used in both spatial and frequency domain the accuracy is getting better compared with the results obtained without using contour algorithm.
Keywords:	Medical Image Segmentation; Wavelet Transform; Contour Algorithm; K-Mean Clustering; Accuracy of Detection
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	BLOOD VESSEL EXTRACTION AND BIFURCATIONS DETECTION USING HESSIAN MATRIX OF GAUSSIAN AND EUCLIDIAN DISTANCE
Author:	DIANA TRI SUSETIANINGTIAS, SURYADI HS, SARIFUDDIN MADENDA, RODIAH, FITRIANINGSIHOne of the sign for diagnosing diabetic retinopathy is Intraretinal Microvascular Abnormalities (IRMA). IRMA is located in the superficial retina area that adjacent to the non-perfusion area resulting venous beading at least two quadrant in the fundus image. The difficulties in venous beading detection are the characteristics of the objects in retinal blood vessel images were varied. There are arteries and veins inside the fundus image. Two of these vessels also contain bifurcation. Bifurcation detection is a very crucial step to obtain the optimum result and proper classification between normal veins with the veins that have the beading. This study, the blood vessel and Eigen value of hessian matrix will be extracted from the fundus image. The extraction result then processed using morphological and Euclidian distance to detect the bifurcation point of the retinal fundus image. This step is the early stage of venous beading detection. Bifurcation detection was performed by combining morphological operation to eliminate the noises of fundus image as well as to compute Euclidian distance of the vessel. The result of this study is expected to detect bifurcation point accurately. The outcome of bifurcation features extraction will be used to classified normal veins from venous beading.
Abstract:	Bifurcation, Eigen Value, Euclidian Distance, Hessian Matrix, Venous Beading
Keywords:
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	MODEL RULE-BASED EXPERT SYSTEM FOR FIRE STATION ALLOCATION ASSESSMENT: APPLIED IN KENDARI CITY, INDONESIA
Author:	SABRILLAH TARIDALA, ANANTO YUDONO, M. ISRAN RAMLI, 4ARIFUDDIN AKIL
Abstract:	Kendari City is an urban region with the smallest area as well as the largest population in Southeast Sulawesi. Fires in Kendari City had rather frequently occurred and caused numerous materials loss. The amount of fire station in Kendari city is very limited, that is, one station is to serve all urban areas, as well as the the slow respond of the time service of firefighters, ≥15 minutes since the fire is started. The aim of this study is to develop an urban model of fire station allocation assessment. The model is developed by using Expert Systems with the Geographic Information System (GIS). The results show that the fire station chosen locations, i.e. (1) Suitable I, consists of grid no. 1268 and 1337, (2) Suitable II, amounting to 33 grids, and (3) Suitable III, amounting to 14 grids. The fire station allocation should be appropriately close to the high risk of the fire area, located on the arterial road and near with the potential water resources.
Keywords:	Urban Fire, Expert System, Fire Risk, Fire Station, GIS
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	WEIGHT ANALYSIS FOR WEIGHTED CLUSTER ALGORITHMS IN MOBILE AD-HOC NETWORK
Author:	HADEEL NOORI SAAD, MOHAMMED BAQER M. KAMEL
Abstract:	Mobile ad-hoc network (MANET) is an infrastructure-less network with unstable dynamic nature. Such environment may cause high control signaling for self-rearrangement, and scalable problems. Weight-based Cluster routing algorithms aim to reduce configuration steps, retransmission and collisions. These algorithms differ in principal of cluster head selection upon some weight criteria such as (energy, connectivity, no. of node�s neighbors and mobility). In this research an analytical model was proposed to examine different criteria�s weights themes for cluster head election. The result expos the effect of the significant of multi combinations of them. Computation of criteria weight upon another criteria gives a smooth weight update with different update steps as results show. This can reflect new trend of weighted clustering algorithms based on network state.
Keywords:	MANET, MANET Clustering, CH Selection, Weighted Clustering
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	AN INTELLIGENT SERVICE RECOMMENDATION MODEL FOR SERVICE USAGE PATTERN DISCOVERY IN SECURE CLOUD COMPUTING ENVIRONMENT
Author:	K. MANGAYARKKARASI, DR.M.CHIDAMBARAM
Abstract:	With the increase in the usage of web services in all business activities, the enormous amount of data is created and stored on different cloud servers. It is a challenging task to recommend the appropriate web services according to the demands of the user. The web recommendation techniques mainly concentrate on the mining of the association patterns among the web services from the historical compositions. But, the negative patterns denote the incorrect combination of web services. An accurate service recommendation model is presented by combining the positive patterns with the negative patterns in the large web service network. This paper proposed an intelligent service recommendation model for service usage pattern discovery in secure cloud computing environment. A RuleScore algorithm is proposed for predicting the future service collaboration based on the mined rules. The experiments on the real-time and synthetic datasets show that the proposed model ensures effective recommendation of web services in a large-scale network.
Keywords:	Association Rule Mining, Cloud Computing, RankScore, Semantic Tag, Web Service Recommendation
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	MEASURING CONTINUANCE PARTICIPATION IN ONLINE COMMUNITIES
Author:	MOHANA SHANMUGAM, YUSMADI YAH JUSOH, MARZANAH A. JABAR, ROZI NOR HAIZAN NOR
Abstract:	Social commerce is an emerging digital trend that involves participation from online communities. Members of online communities have become influential in ensuring the prolonged usage of social commerce sites. Drawing on the theories of planned behavior and social support as well as satisfaction and perceived value constructs, the purpose of this manuscript is to propose a continuance participation measurement framework. The framework integrates pertinent constructs that drive continuance participation measurement process, which applies the weighted checklist method. A simulation is performed to measure the significance level of online community sites. Additionally, data gathered from four experts confirm the efficacy of the proposed framework. The simulation discussed serves as a guideline and can be useful for developers and managers of social commerce sites for measuring the performance of their online community sites.
Keywords:	Social Commerce, Theory of Planned Behaviour, Social Support Theory, Online Communities, Continuance Participation, Weighted Checklist
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	A FRAMEWORK OF IMPROVING BUSINESS PRCOESS EXECUTION USING SOCIAL ARTIFACTS
Author:	ABDULLAH AL-BARAKATI1, AHMED BARNAWI1, FUAD BAJABER1, ABDULLAH ALMALAIS1, SEYED BUHARI1, RADWA EL SHAWI
Abstract:	A growing number of enterprises are seeking for socializing their business processes (BP) and capitalizing on Web 2.0 technologies and solutions in order to improve communication and content sharing among their stakeholders. To this end, it becomes crucial for enterprises to design social-based business process techniques (i.e., a process, language and tool) to transform its BPs into social BPs. This article discusses a set of methods that guide the transformation based on the socialization goals of the enterprise. The approach uses social relations that connect tasks/persons/machines together. These relations are the basis of developing specialized networks that capture the interactions during business process execution and are used to recommend corrective actions when conflicts on resources occur. The approach relies on three flows known as control, communication, and navigation. The control flow connects tasks together with respect to a certain business logic. The communication flow captures the messages exchanged between persons/machines when they perform tasks of processes. Finally, the navigation flow captures the interactions between specialized networks that offer solutions to exceptions. A validating scenario is used to show the effectiveness of the proposed methods.
Keywords:	Business Process, Social Process, Process Compliance, modelling, social BP
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	CENTROID K-MEANS CLUSTERING OPTIMIZATION USING EIGENVECTOR PRINCIPAL COMPONENT ANALYSIS
Author:	MUSTAKIM
Abstract:	K-Means is a very popular algorithm for clustering, it is reliable in computation, simple and flexible. However, K-Means also has a weakness in the process of determining the initial centroid, the change in value causes the change in resulting cluster. Principal Component Analysis (PCA) Algorithm is a dimension reduction method which can solve the main problem in K-Means by applying PCA eigenvector of covariance matrix as the initial centroid value on K-Means. From the results of conducted experiments with a combination of 4, 5 and 6 of attributes and the number of clusters, Davies Bouldin Index (DBI), Silhouette Index (SI) and Dunn Index (DI) cluster validity of PCA K-Means are better than the usual K-Means. It is implemented by testing 1,737 and 100,000 data, the result is the patterns formed by PCA K-Means can lower the value of DBI constantly, but for SI and DI, the formed pattern is likely to change. This study concluded that the cluster validity used as reference for comparing the algorithms is DBI
Keywords:	Covariance, Davis Bouldin Index, K-Means, PCA K-Means, Principal Component Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	AN EMBELLISHMENT OF SEMANTIC KNOWLEDGE BASE USING NOVEL CROWD SOURCING AND GRAPH BASED METHODS FOR IMPROVING SENTIMENT ANALYSIS
Author:	P. KALARANI, Dr. S.SELVA BRUNDA
Abstract:	Opinion Mining is given more attention now-a- days, because it helps decision makers to evaluate the success of a newly proposed schemes, new ad campaign or new product launch. There is several classification approaches proposed to classify people�s opinions in Literature. The contextualization and enriched semantic knowledge bases are used to improve the classification accuracy in Opinion Mining. Contextualization recognizes ambiguous terms then adds context information for their disambiguation and enrich the semantic knowledge bases for sentiment analysis using SenticNet. SenticNet is a lexical resource which gives polarity (positive, negative and neutral), semantics and sentic information in sentiment analysis. The process of SenticNet includes recognizes the ambiguous terms, provides context information which is mined from domain specific corpus and ground this contextual information to knowledge sources. But semantically enriched approaches have issues with context and Ambiguous terms occurrence in a same sentence. The concurrences of both the term in same sentence are avoided in this paper by using crowd sourcing method. In crowd sourcing methods, multiple people process each opinion and label them as their skill level, then the large corpora is constructed based on the aggregated crowd sourced labels. The constructed corpus is used to annotate sentence level labels. The combination of human annotation and machine intelligence reduce the time of constructing larger corpora. In proposed novel crowd sourcing method document Meta data is also used along with text features. However labeling using large corpora is not sufficient to obtain high sentiment classification, so that the natural language patterns are used along with text features to improve the sentiment classification. Thus the proposed method yields more generic contextualized lexicons and provides higher classification accuracy.
Keywords:	Opinion Mining, Sentiment analysis, Contextualization, Disambiguation, Knowledge Extraction
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	CLOUD SERVICE BROKER: SELECTION OF PROVIDERS USING DTRFV EVALUATION
Author:	ANUPRIYA KONERU, SREELATHA M
Abstract:	Multicloud environment possess new challenges to the Cloud Service Requesters. Cloud Service Requesters are not aware of the quality of service offered by Cloud Service Providers. To select the suitable provider for a service the requester meets the Cloud Service Broker. Broker finds the best suitable provider for every request. Broker identifies the previous service ratings to evaluate the Reputation Factor Value of provider. In this paper, we present Dynamic True Reputation Factor Value Evaluation algorithm to find the best providers. By using this algorithm Broker can identify the unfair ratings and reduce the effect of unfair ratings in the calculation of True Reputation Factor Value of provider. Results are presented to appraise the success of the proposed model.
Keywords:	Multicloud, Cloud service requester, Broker, Reputation, Provider
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	DESIGN AND DEVELOPMENT OF DICTIONARY-BASED STEMMER FOR THE URDU LANGUAGE
Author:	ZAHID HUSSAIN, SAJID IQBAL, TANZILA SABA , ABDULAZIZ S. ALMAZYAD, AMJAD REHMAN
Abstract:	Stemming reduces numerous variant forms of a word to its base, stem or root form which is essential for different language processing applications including Urdu IR. Urdu is a resource poor and morphologically rich language. Multilingual Urdu vocabulary is very challenging to process due to its complex morphology. Research of Urdu stemming has an age of a decade. However, there has not been any work reported on dictionary based Urdu stemming. The present work introduces a dictionary based Urdu stemmer with improved performance as compared to the existing Urdu stemmers. The significance of the study is the identification of dictionary-based approach for Urdu stemming as the most promising approach, especially with dictionary update feature. Testing shows 94.85% overall accuracy on test data and results can be further improved by cleaning test data and dictionary updates.
Keywords:	Dictionary based stemming; dictionary updates; infixes; Fused classification
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	DYNAMIC SELECTION OF CHILD PCE USING SDN CONTROLLED PARENT PCE
Author:	P.SELVARAJ, V.NAGARAJAN
Abstract:	The next generation optical network is expected to handle the needs of an emerging applications in a cost effective way while complying with the QoS requirements. With the emergence of software-defined networking, the control plane can be lifted out from the networking devices and kept at a central location. This logical separation of layered functionalities with centralized control and management, enables the operators to offer the new range of services in an on demand and agile manner. With software defined networking, the needs of an emerging applications can be catered in real time. This paper analyzes the problem of optical light-path computation and proposes a novel mechanism for the next generation optical networks. As by the fact, any single light-path computation algorithm does not behave consistently under the varying traffic scenarios, as each algorithm/heuristic explores the search space in a unique way. So choosing the appropriate light-path computation algorithm/heuristic according to the traffic scenario is a viable approach. Considering the strict QoS requirements and global optimization aspects of the next generation applications such mechanism would be highly preferrable. This paper proposes a novel algorithm selection methodology for the next generation software defined optical network. The parent and child path computation element based optical networking was considered. The match fields used with the software defined networking were considered in designing the algorithm selection mechansism. A simulational study of QoS constrained path establishment in ONOS based software defined controller environment was performed. A java based NOX controller was configured with the parent and child path computation elements. Each of the child path computation elements were configured with different path computation algorithms. The ability of the appropriate selection of child path computation element was tested in ONOS simulation environment. This algorithm selection mechanism would be an amenable solution for the next generation software-defined optical network in which the intelligent and cognitive behaviors are inevitable.
Keywords:	Next generation optical networks, Routing and wavelength assignment problem, Algorithm selection, Path computation element (PCE), software defined networking (SDN)
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	UTILIZATION OF CSE-UCLA MODEL IN EVALUATING OF DIGITAL LIBRARY PROGRAM BASED ON EXPERT SYSTEM AT UNIVERSITAS TEKNOLOGI INDONESIA: A MODEL FOR EVALUATING OF INFORMATION TECHNOLOGY-BASED EDUCATION SERVICES
Author:	DEWA GEDE HENDRA DIVAYANA
Abstract:	This study was aimed at finding out the services quality of an expert system-based digital library program implementation at Universitas Teknologi Indonesia. This study was an evaluative research using CSE-UCLA model that consisted of system assessment, program planning, program implementation, program improvement and program certification. The subjects were the head of library, the development team, the lecturers, and the students. The data were collected through questionnaire, observation, interview, and documentation. The data were analyzed using descriptive quantitative technique to analyze each of the components of the CSE-UCLA model and descriptive qualitative technique to analyze the constraints met in the program implementation. The results showed that the degree of services quality of the program implementation in the components of system assessment, program planning, program implementation, program improvement and program certification were 79.80%, 69.90%, 57.40%, 74.90%, and 66.80%, respectively. With the help of T-Score data converted into Glickman quadrant it was also found out that the degrees of services quality of the program implementation in the components of system assessment, program planning, program implementation, program improvement and program certification were High-High-High-High-High. The evaluation results of digital library services using CSE-UCLA model provides the right recommendation to create new ideas/breakthroughs in the development of digital libraries used to support the education process.
Keywords:	Evaluation, CSE-UCLA, Digital Library, Expert System
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	MEASURING THE ACCEPTANCE OF USING UTMS IN JORDAN UNIVERSITIES
Author:	BASSAM M. AL-MAHADEEN, AHMAD ALTHUNIBAT, SAEED M.Z A. TARABIEH
Abstract:	University Timetable management system (UTMS) are used to schedule courses, lecturers and rooms in university by considering some constraints. Although UTMS is a widely studied topic, the use of automated timetabling systems is not widespread among large universities. Therefore, it is important to investigate the factors that influence the intention to use university timetable management system (UTMS) among Higher education lecturers. This study proposed a model for determining the factors that affect the acceptance of using UTMS. The study was conducted by surveying different groups of university�s� lecturer community. A structured questionnaire was used to collect data from 120 respondents. Results of the study prove that the proposed model is comprehensive to study the acceptance of UTMS in higher education institution. Overall, the results indicated the appropriateness of fundamental elements of TAM in the UTMS context.
Keywords:	Acceptance, Timetable management system, university timetable, TAM model
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	APPLICATION OF CLONAL SELECTION IMMUNE SYSTEM METHOD FOR OPTIMIZATION OF DISTRIBUTION NETWORK
Author:	RAMADONI SYAHPUTRA, SLAMET SURIPTO, SOEDIBYO, INDAH SOESANTI
Abstract:	This paper proposes an application of clonal selection immune system method for optimization of distribution network. The distribution network with high-performance is a network that has a low power loss, better voltage profile, and loading balance among feeders. The task for improving the performance of the distribution network is optimization of network configuration. The optimization has become a necessary study with the presence of DG in entire networks. In this work, optimization of network configuration is based on an AIS algorithm. The methodology has been tested in a model of 33 bus IEEE radial distribution networks with and without DG integration. The results have been showed that the optimal configuration of the distribution network is able to reduce power loss and to improve the voltage profile of the distribution network significantly.
Keywords:	Artificial Intelligence; Artificial Immune System; Distribution Network; Distributed Generator
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	ELICITING SECURITY REQUIRMENTS FOR MOBILE APPS: A REPLICATION STUDY
Author:	NOORREZAM YUSOP, MASSILA KAMALRUDIN, MOKHTAR MOHD YUSOF, SAFIAH SIDEK
Abstract:	Mobile applications (mobile apps) are becoming a common medium for conducting transaction, saving data and exchanging information online. However, an important issue that has been overlooked is the emphasis on security issues at the early stage of mobile apps development. It has become a common practice among requirements engineers to deal with security issues after the mobile apps have been developed. This scenario has led to the failure of developing secure and safe mobile application based on the needs of the users. Motivated by this problem, we propose an automated support tool to assist requirements engineers to elicit security related requirements at the early stage of mobile apps development. This paper reported a replication of a study from our previous work that describes our user study and tool support, called MobiMEReq. This tool uses SecEUCs and SecEUIs prototype model to automatically elicit the security attributes requirements of mobile apps. In this paper, we reported the results drawn from an experiment of a user study to compare the capability of the MobiMEReq in relation to the manual approach. The results of the user study show that the tool support has higher accuracy rate in comparison to the manual approach to extract security attributes elicited from functional requirements. This implies that our tool is able to help requirements engineers to easily elicit security attribute requirements of mobile apps.
Keywords:	Security requirements, Security attributes, Mobile apps, Security requirements elicitation
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	ANALYSIS PERFORMANCE OF HYBRID SUBCARRIER MULTIPLEXED OCDMA SYSTEM BASED ON AND SUBTRACTION DETECTION AND SINGLE PHOTODIODE DETECTION
Author:	N.A.A AHMAD, M.N JUNITA, S.A. ALJUNID, C.B.M. RASHIDI, R. ENDUT
Abstract:	This paper demonstrates the comparison of two detections which are; AND subtraction detection and single photodiode detection (SPD). In this work, we evaluate the performance of hybrid subcarrier multiplexing (SCM) of spectral amplitude coding optical code-division multiple-access (SAC-OCDMA) system based on these two detections. SAC-OCDMA is applied due to its capability to reduce the effects of Multiple Access Interference (MAI) by employing code sequences with fixed-in phase cross correlation. This system utilizes the Recursive Combinatorial (RC) code as a one of the SAC-OCDMA codes. A part from that, SCM scheme is efficient to promote the channel data rate of OCDMA system. Hence, the hybrid technique is expected to boost up the spectral efficiency of the OCDMA system by providing large number of simultaneous users with fewer optical channels. The maximum allowable number of concurrent users can be improved by rising the number of subcarrier without effecting the number of code lengths and SAC-OCDMA codes. The result reveals that the implementation of SPD detection gives excellent performance in hybrid SCM SAC-OCDMA system in comparison to AND subtraction detection. This is due to the fact that the effects of MAI and phase induced intensity noise (PIIN) are suppressed at the optical domain.
Keywords:	Subcarrier Multiplexing, Hybrid SCM OCDMA, AND Subtraction Detection, Single Photodiode Detection (SPD), Recursive Combinatorial (RC) Code
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	SINGLE IMAGE DE-HAZING THROUGH IMPROVED DARK CHANNEL PRIOR AND ATMOSPHERIC LIGHT ESTIMATION
Author:	HUSSEIN MAHDI, NIDHAL EL ABBADI, HIND RUSTUM
Abstract:	De-hazing image is big challenge for the researchers, although there are many good algorithms but all of them not regards as a perfect algorithm. In this paper we try to introduce new de-hazing method based on many steps. We first preprocess the image to remove some of noise using average filter before we estimate the dark channel prior which is estimated based on average. The main contribution in this paper is the estimation of Air light value. We suggest new method based on comparing the standard deviation for RGB image and the HSV color space image. For that, we suggested many rules to control the Air light value according to experiments. Enhance local contrast implement based on V channel of color space HSV to construct visually pleasing images. The quality of de-hazed images measured visually and by using many quality measuring metrics (blind quality and reference quality) which gives promised results. Although the proposed method is not perfect method but it was more efficient than other algorithms when compared with them.
Keywords:	Haze Image, De-Hazing Image, Image Processing, Atmospheric Light, Dark Channel Prior
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	ALGEBRA FOR TRANSFORMING THE STRUCTURE OF THE SEARCH SPACES ASSOCIATED WITH THE COMBINATORIAL OPTIMIZATION PROBLEMS
Author:	ARTEM POTEBNIA
Abstract:	This article proposes the classification of the search spaces associated with the combinatorial optimization problems based on the type of their constituent solutions. The spaces belonging to each identified class are accompanied by the corresponding graph models. Against this background, the article introduces the original algebra allowing the representation of the search spaces in the unified homogeneous form. The proposed algebra consists of a set of transformations given in an analytical form and illustrated by the modifications of the graph models constructed for the search spaces.
Keywords:	Combinatorial Optimization Problem, Search Space, Bipartite Graph, Multigraph, Graph
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	FORMALIZATION OF VERSIONING RULES FOR XML SCHEMA USING UML CLASS DIAGRAM
Author:	HANANNI AMAN, ROSZIATI IBRAHIM
Abstract:	In agile software development methodology, XML schema is used for developing the web applications. The major problem in using the agile software development methodology is capturing the software requirements especially when versioning occurred in XML Schema. This paper presents how to capture software requirements for document changes when versioning occurred in XML Schema. UML Class Diagram is used in addressing the versioning rules. Once the versioning rules are captured, these rules are then being formalized for better understanding of the versioning problem occurred in XML Schema.
Keywords:	XML Schema, Versioning Rules, Traceability, UML Class Diagram, Document Changes
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	AN AUTOMATIC LEXICON WITH EXCEPTIONAL-NEGATION ALGORITHM FOR ARABIC SENTIMENTS USING SUPERVISED CLASSIFICATION
Author:	AYMAN MOHAMED MOSTAFA
Abstract:	Sentiment analysis is a kind of natural language processing that determines the feelings of people in a piece of text they are positive, negative, or neutral. Analysis of Arabic sentiments is considered a complex task due to the large linguistic and negation terms in Arabic language. Most recent researches are based on detecting the polarity term after the negation particle immediately. This can reduce the accuracy and performance of the analysis because many sentiments especially written in slang Arabic do not depend on having a negation particle before the polarity term. The aim of this paper is to develop a hybrid sentiment classification based on automatic lexicon algorithm and machine learning approach. The automatic lexicon is developed with a negation algorithm for both modern standard Arabic and colloquial Arabic. This algorithm detects the negation particle and traces all polarity terms even if they do not come after the negation particle. An exceptional negation is embedded into the negation algorithm which is based on the Arabic exceptional pattern in reversing the polarity term after the negation process. The experimental results are conducted using supervised machine learning methods such as SVM, KNN and NB that achieve high results in accuracy, precision, recall, and F-measure which are compared with the experimental results in three recent research papers.
Keywords:	Sentiment Analysis, Automatic Lexicon, Machine Learning, and Exceptional Negation
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	ADDRESS THE CHALLENGES OF IMPLEMENTING ELECTRONIC DOCUMENT SYSTEM IN IRAQ E-GOVERNMENT- TIKRIT CITY AS A CASE STUDY
Author:	MUHANED AL-HASHIMI, MOHANAAD SHAKIR, MAYTHAM HAMMOOD, ABDALLA ELDOW
Abstract:	Storing and archiving information plays a crucial role in any government�s strategy of serving its parties. One early step in achieving this goal is to implement a correct electronic document system for e-government agencies, which plays a crucial and important role in storing, processing, and managing data flow in an effective manner. However, this system in Iraq did not see the light so far even it is a strategic objective of e-government. This paper attempts to investigate the technological and human challenges that hinder the implementation of such system to support Iraqi e- government in overriding those challenges and speeding up its initiatives. The paper has utilized a quantitative approach via survey questionnaire from various public and private sectors at Tikrit city in Provence Salah al din to achieve its goal. The results indicate several challenges such as economic, computer illiteracy, technology acceptance, training and lack of series implementation steps by government.
Keywords:	Challenges; Implementation; E-government; EDMS
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	NEURAL NETWORK-BASED DDOS DETECTION REGARDING HIDDEN LAYER VARIATION
Author:	IMAM RIADI, ARIF WIRAWAN MUHAMMAD, SUNARDI
Abstract:	Distributed Denial of Service attack (DDoS) is a structured network attack coming from various sources and fused to form a large packet stream. DDoS attacks aiming to disrupt the services available in the target tissue by flooding the target bandwidth or processing capacity of the system by making the target network server becomes overloaded. Network packet classification is one method of network defense system in the organization of the Internet in order to avoid DDoS attacks. Network packet classification can be carried out either by utilizing the method of Artificial Neural Network (ANN). The proposed work of network traffic packet classification applying variation of hidden layer with Quasi-Newton method training function and statistical network traffic packet feature extraction have the result that ANN with two hidden layers outperformed than ANN with single or three hidden layers. ANN with two hidden layers gives overall consistent mse and convergence speed, also higher correct classification percentage at 99.04%. Quasi-Newton method (trainlm) is qualified and suit for classification task based on value of regression both in the training and validation phase.
Keywords:	DDoS, Classification, Neural-Network, Hidden Layer
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	GEOMETRIC-TOPOLOGICAL BASED ARABIC CHARACTER RECOGNITION, A NEW APPROACH
Author:	HAMED TIRANDAZ, MOHSEN AHMADNIA AND HAMIDREZA TAVAKOLI
Abstract:	Optical Character Recognition (OCR) is a very old and of great interest in pattern recognition field. In this paper, a new algorithm based on morphological structure is proposed for Arabic character recognition. Our proposed method uses center of mass calculation. It is invariant with the size, translation and rotation of the target image. In addition, topology-based landmarks like intersection pixels masking the intersection of loops and multiple strokes, as well as end points have been used to compute centers of mass of these points located in the individual quadrants of the circles enclosing the characters. After doing initial pre-processing operations like binarization, resizing, normalization, removing noise, skeletonization, the total number of intersection pixels as well as the total number of end points are determined and stored. The character image is then encircled and divided into four quadrants. The center of mass of the character image as well as the masses of each of its four quadrants are determined and the Euclidean distances (ED) of the intersection and end points in each of the quadrants with the massed are calculated. These quantities are determined for both the target and prototype image and then the best match is achieved with the character having the minimum ED. Results show that the presented method opens up a new direction for dealing with the complex problems of OCR.
Keywords:	Arabic Character Recognition, OCR, Center of Mass, Geometric-Topological features
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

Title:	COLOR QR CODE RECOGNITION UTILIZING NEURAL NETWORK AND FUZZY LOGIC TECHNIQUES
Author:	BAKRI BADAWI, TEH NORANIS MOHD ARIS, NORWATI MUSTAPHA, NORIDAYU MANSHOR
Abstract:	Quick Response (QR) code is popular type of two dimensional barcode. The key feature of QR code is larger storage capacity and high damage resistance compared to the traditional barcodes. Color QR code is the future as it provides much higher encoding capacity, but it also brings tremendous challenges to the decoding because of color interference and illumination. This research paper presents a method for QR code recognition using the Neural Network (NN) and fuzzy logic techniques. We created a framework for image decoding. First, the color QR code is converted to black and white then the QR code is recognized using neural network. Next, the original colors are returned to the QR code. The colors are enhanced using fuzzy logic and then, the enhanced color QR code is split into three barcodes which are red, green and blue. Finally, each QR code is converted to black and white and sent to ZXing library for decoding and obtained the original data. ZXing library has been utilized for decoding and recognition purposes and has produced satisfactory results. This research proof that by, utilizing NN and fuzzy logic techniques has produced better QR code success rates of five percent.
Keywords:	QR Code, Artificial Intelligence (AI), Neural Network, Fuzzy
Source:	Journal of Theoretical and Applied Information Technology 15^th August 2017 -- Vol. 95. No. 15 -- 2017
Full Text

dew