		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 Informtion Technology
December 2017 | Vol. 95 No.24

Title:	THIN FILM ROUGHNESS OPTIMIZATION IN THE TIN COATINGS USING GENETIC ALGORITHMS
Author:	NUR FAIQAH FAUZI , ABDUL SYUKOR MOHAMAD JAYA , MUATH IBRAHIM JARRAH , HABIBULLAH AKBAR
Abstract:	Optimization is important to identify optimal parameters in many disciplines to achieve high quality products including optimization of thin film coating parameters. Manufacturing costs and customization of cutting tool properties are the two main issues in the process of Physical Vapour Deposition (PVD). The aim of this paper is to find the optimal parameters get better thin film roughness using PVD coating process. Three input parameters were selected to represent the solutions in the target data, namely Nitrogen gas pressure (N2), Argon gas pressure (Ar), and Turntable speed (TT), while the surface roughness was selected as an output response for the Titanium nitrite (TiN). Atomic Force Microscopy (AFM) equipment was used to characterize the coating roughness. In this study, an approach in modeling surface roughness of Titanium Nitrite (TiN) coating using Response Surface Method (RSM) has been implemented to obtain a proper output result. In order to represent the process variables and coating roughness, a quadratic polynomial model equation was developed. Genetic algorithms were used in the optimization work of the coating process to optimize the coating roughness parameters. Finally, to validate the developed model, actual data were conducted in different experimental run. In RSM validation phase, the actual surface roughness fell within 90% prediction interval (PI). The absolute range of residual errors (e) was very low less than 10 to indicate that the surface roughness could be accurately predicted by the model. In terms of optimization and reduction the experimental data, GAs could get the best lowest value for roughness compared to experimental data with reduction ratio of 46.75%.
Keywords:	Roughness, TiN coating, PVD, GAs, RSM
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	ONLINE PERFORMANCE DIALOGUE SYSTEM MODEL (e-DP): A REQUIREMENT ANALYSIS STUDY AT BATU PAHAT DISTRICT EDUCATION OFFICE
Author:	ASRAR NAJIB YUNOS, ABD SAMAD HASAN BASARI, AHMAD NAIM CHEE PEE, MD SAID MD DAIMON, ABD RAHIM ABDUL RAHMAN, LOKMAN TAHIR
Abstract:	This study aims to identify the viewpoint of school leaders the need of developing Online Performance Dialogue (EDP). The model based on the method of inquiry for educational leaders and the School District. The theory is used as a model UTAUT basis for this study. Survey methods used between 222 schools investigate the needs of leaders to adopt Online Performance Dialog (eDP) The data obtained were analyzed through descriptive Statistics using statistical package for social science (SPSS) software. Interpretation of the data is based on the value of the mean and standard deviation. Overall findings indicate that school leaders need on-line performance dialogue (eDP) with an average mean 4.309. The findings of this study reveal that school leaders have access to the necessary technology to eDP. The results also showed the level of acceptance and the intention to use the eDP model among school leaders.
Keywords:	Model, Online Performance Dialogue, Need Analysis
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	ACCEPTANCE SAMPLING FOR NETWORK INTRUSION DETECTION
Author:	C. MADHUSUDHANARAO, Dr. M. M. NAIDU
Abstract:	Network Intrusion Detection System (NIDS) is to prevent entry of anomalous network flows into networks. Hundred percent inspections of all the fragments of network flows for detecting malicious fragments and thereof anomalous flows are highly prohibitive. The Selective Sampling Method (SSM) considers only network flows of small size not exceeding 80 fragments. Further, it is applicable for detecting port scan and host scan attacks only. This study proposes a novel NIDS adapting acceptance sampling method, referred to as ASNID. It is applicable to detect Land, Xmass, Nestea, Rose, Winnuke, NULL Scan, Teardrop, Fraggle, Port scan, Host scan. A randomly chosen sample of fragments from a network flow is inspected for detecting whether it is anomalous or not. It reduces the computational effort by a factor of 0<k<1 where k is the ratio of sample size to total fragments of a network flow. It is proved experimentally that the GMAI, performance metric of ASNID tends to one as the sample size increases to 60%. It is also proved that as the percentage of anomalous flows increases GMAI increases. Hence, ASNID would of immense use in network intrusion detection.
Keywords:	Acceptance Sampling, Selective Sampling, Geometric Mean Accuracy Index, Network Intrusion Detection, Network Attacks
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	A SURVEY ON PRIVACY OF LOCATION-BASED SERVICES: CLASSIFICATION, INFERENCE ATTACKS, AND CHALLENGES
Author:	MOHAMAD SHADY ALRAHHAL, MAHER KHEMAKHEM, KAMAL JAMBI
Abstract:	In recent years, Location-Based Services (LBS) have become very popular, especially in the light of enhancements that are daily performed on both mobile devices and wireless networks. The popularity of LBS is derived from its valuable benefits, where they enable the users to search for nearest Points of Interest (POI), share ideas and comments, and enjoy playing games, making our life easier and more enjoyable. However, LBS have some risks associated with it. The privacy issue is considered one of the most important risks in this field since the users are forced to build their queries based on their real geographic locations. This paper studies the different privacy protection approaches through a survey, where a new classification is proposed based on the amount of collaboration between LBS users and LBS server. The protection goals (identity ID, Location Information LI, and Temporal Information TI) that any LBS user aims to protect are defined and measured. Based on the provided protection goals, the most advanced inference attacks (Location Homogeneity Attack LHA, Map Matching Attack MMA, Query Sampling Attack QSA, and Semantic Location Attack SLA) are analyzed and evaluated. As for challenges in LBS privacy protection field, an eight research questions and open problems are explored. In addition, we present some rules-based recommendations, which can help the LBS users to select the most optimal way to achieve a higher privacy protection level.
Keywords:	Inference Attacks, Research Questions, Privacy Protection, Protection Goals, Privacy Metrics, Rule.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	NETWORK LIFETIME MAXIMIZATION BASED ON ENERGY FORECAST AND COMPRESSIVE SENSING WITH INTEGRATED SINK MOBILITY FOR HETEROGENOUS WIRELESS SENSOR NETWORKS
Author:	A.KARTHIKEYAN, Dr.T.SHANKAR, KRUTHIKA CHAKKA, ARCHIT DWIVEDI
Abstract:	Optimum usage of battery resources and efficient consumption of energy are the primary concerns and design parameters for any WSN. Irregular energy consumption is the major problem in current WSNs. This paper focuses on efficiently using the energy resources and to maximize the network lifetime by the application of compressive sensing and optimum CH selection process coupled with sink mobility model. Compressive sensing allows us to reduce the number of transmissions taken for complete data transfer, while optimum CH election mechanism gives efficient energy consumption at the initial stages of transmissions and data transfer. The residual energy of the network is further optimized by using the sink mobility model, increasing the total lifetime of high energy nodes thereby leading to increased network lifetime. The algorithm was simulated in MATLAB and verified.
Keywords:	Wireless Sensor Network, Compressive Sensing, Sink Mobility
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	LIFETIME MAXIMIZATION OF HETEROGENEOUS WIRELESS SENSOR NETWORKS USING IMPROVED ENERGY AWARE DISTRIBUTED CLUSTERING APPROACH WITH RENDEZVOUS NODES AND MOBILE SINK
Author:	A.KARTHIKEYAN, Dr.T.SHANKAR, MUDITA PRAKASH, RAJAT PUSHKARNA
Abstract:	Energy efficiency and its optimization are of paramount importance in data transmission in Wireless Sensor Networks. The lifetime of the deployed sensor node should be maximized with even distribution of the energy across the network so that the data transmitted is not lost .The MS helps in enhancing the lifetime of the network by reducing the energy spent in long distance transmission. The introduction of RN helps in storage and data transmission from CH to MS. In the proposed protocol I-EADC_RN, the field is divided into two regions Sensing region[A] and Storage region[B]. The nodes deployed within the storage region are called RN. The nodes deployed in the sensing region participate in CH selection based on average energy computed from the neighboring nodes. The RN store the collected data and transmit it to the MS when the MS comes near to them. The objective of the proposed algorithm is to maximize the effective lifetime of the network with the help of RN and MS, reduce energy hole problem with efficient distribution of energy among the network with the help of efficient competition radius assignment and by efficient mean of data transmission with the help of relay node selection based on energy spent in transmission and reception and the minimization of data loss with the help of data storage in the RN.
Keywords:	CH-Cluster Head, RN-Rendezvous Node, RN-Region , Deployment Region, MS-Mobile Sink
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	ASYMPTOTIC ESTIMATES OF THE SOLUTION OF A SINGULARLY PERTURBED BOUNDARY VALUE PROBLEM WITH BOUNDARY JUMPS
Author:	D.N. NURGABYL, U.A. BEKISH
Abstract:	In this article the boundary value problem for ordinary simple differential equations of the third order with small parameter at the higher derivatives is considered. In the given work the author researches the singularly perturbed boundary value problems under the condition that real parts of the roots of additional distinctive equation have opposite signs. Boundary and initial functions are defined; their existence and uniqueness are proved. On the basis of the constructed boundary and initial functions analytical representation of the solution of a boundary value problem is found. On the basis of an analytical representation of a solution of a singularly Perturbed Boundary Value Problem for the differential equations of conditionally the steady type, we describe the character of growth of the derivatives of a solution of Perturbed Problem with . The class of boundary value problems with boundary jumps is singled out. Sizes of boundary jumps are determined. Asymptotic estimates of the solution of a boundary value problem are found. Estimates for the difference between solutions of the degenerate and perturbed value problems are obtained.
Keywords:	Asymptotic, Initial Function, Boundary Function, Boundary Value Problem, Additional Characteristic Equation, Perturbed and Degenerated Problems
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	ENERGY CONSUMPTION PATTERNS OF MOBILE APPLICATIONS IN ANDROID PLATFORM: A SYSTEMATIC LITERATURE REVIEW
Author:	HASAN SAJID ATTA AL NIDAWI, KOH TIENG WEI, KAREEM ABBAS DAWOOD, AMMAR KHALEEL
Abstract:	Studies related to resource consumption of mobile devices and mobile applications have been brought to the fore lately as mobile applications depend largely on their resource consumption. The study aims to identify the key factors and holistic understanding of how a factor influences Consumption Pattern (CP) effectiveness for an android platform mobile application. The study presents a Systematic Literature Review (SLR) on existing studies that examined factors influencing the effectiveness of CP for android mobile application and measured the effectiveness of CP. Therefore, the current SLR is conducted to answer the following questions: (1) What is the evidence of CP factors that drain the battery of a mobile device? (2) What are the energy conservation techniques to overcome all the factors that drain battery life? and (3) How can developers measure the effectiveness of an energy conservation technique?. The SLR investigated factors affecting the effectiveness of CP for android platform mobile application. The analyses of forty papers were used in our synthesis of the evidence related to the research questions above. Therefore, the analyses showed 22 studies that investigated how to measure the energy conservation technique effectiveness while 18 studies focused on better understanding of how the resources of mobile devices are actually spent. In this sense, 2 studies show the effectiveness of early analysis of software application design. Additionally, five factors i.e., architecture, interface, behavior of the application, resources, and network technologies that affect CP effectiveness were identified. This study investigated a SLR targeting at studies of CP effectiveness in android platform. The total of 40 studies were identified and selected for result synthesis purpose in this work (SLR). The evidences show there are five factors affecting the CPs effectiveness. Three of them have received a little attention among developers regarding choosing the most suitable: software architecture, application interface and behavior of the application in terms of resource consumption.
Keywords:	Energy Consumption Patterns, Energy Conservation Technique, Android Mobile Application, Systematic Literature Review
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	USING MODIFIED BAT ALGORITHM TO TRAIN NEURAL NETWORKS FOR SPAM DETECTION
Author:	AMAN JANTAN, WAHEED A. H. M. GHANEM, SANAA A. A. GHALEB
Abstract:	Nowadays a monumental amount of spam and junk email clutter email inboxes and storage facilities. Spam email has a significant negative impact on individuals and organizations alike, and is a serious waste of resources, time and effort. The task of filtering spam or junk e-mail is complex and very difficult to solve. Hence, learning-based filtering is considered an important method for detecting spam emails as the filtering technique requires training to epitomize the knowledge that can be used for detecting the spam. Thus, Artificial Neural Networks are being relied on to create a learning based filter. In this article, we particularly propose the Feedforward Neural Network (FFNN) for identification of e-mail spam; the weights and biases of this network model are set to optimum using a new modified bat algorithm (EBAT). Experiments and results based mainly on two datasets (SPAMBASE and UK-2011 WEBSPAM datasets) show that the developed FFNN model trained by EBAT achieves high generalization performance compared to other optimization methods.
Keywords:	Artificial Intelligent (AI), Swarm Intelligence (SI), Feed-forward Neural Network (FFNN), Bat Algorithm (BAT), Spam Email, Spam Detection
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	DEEP RESIDUAL LEARNING FOR TOMATO PLANT LEAF DISEASE IDENTIFICATION
Author:	HABIBOLLAH AGH ATABAY
Abstract:	Deep Learning for plant leaf analysis has been recently studied in various works. In most cases, Transfer Learning has been utilized, where the weights of networks, which are stored in the pre-trained models, are fine-tuned to use in the considered task. In this paper, Convolutional Neural Networks (CNNs), are employed to classify tomato plant leaf images based on the visible effects of diseases. In addition to Transfer Learning as an effective approach, training a CNN from scratch using the Deep Residual Learning method, is experimented. To do that, an architecture of CNN is proposed and applied to a subset of the PlantVillage dataset, including tomato plant leaf images. The results indicate that the suggested architecture outperforms VGG models, pre-trained on the ImageNet dataset, in both accuracy and the time required for re-training, and it can be used with a regular PC without any extra hardware required. A common feature visualization and verification technique is also applied to the results and further discussions are made to imply the importance of background pixels surrounding the leaves.
Keywords:	Deep Learning, Convolutional Neural Network, Plant Leaf Disease, Tomato Disease
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	EMPIRICAL STUDIES ON CLOUD COMPUTING ADOPTION: A SYSTEMATIC LITERATURE REVIEW
Author:	ABDULNOOR SALEH, SULFEEZA MOHD DRUS, SITI S. M. SHARIFF
Abstract:	Cloud computing is a major topic of discussion among IT professionals. This practice is a good alternative for higher education institutions of limited budget in operating their information system efficiently without spending high capital for infrastructure resource. According to the annual report of educational indicators of the Republic of Yemen, the education and training sectors in Yemen face several obstacles and challenges in delivering quality education to the entire population of the country; for example, limited infrastructure resources and IT budget, and lack of teaching staff, technical experts, and IT skilled personnel. This study aims to (1) review empirical studies on cloud computing adoption in general, (2) identify the influencing factors of cloud computing adoption, and (3) categorize these influencing factors into technological, organizational, environmental, and individual factors. The influencing factors of cloud computing adoption in the government and industrial and educational sectors are also reviewed. Cloud computing adoption in the educational sector is clearly demonstrated. A total of 50 models are reviewed and discussed. Findings show that theoretical and empirical studies on cloud computing adoption in the educational sector are few. Moreover, 18% and 82% of studies investigate factors related to cloud computing adoption in the educational and industrial sectors, respectively. Furthermore, 26% of studies use individual-level theory for cloud computing adoption, 61% use organizational level theory, and 13% integrate individual- and organizational-level theories.
Keywords:	Cloud Computing, Cloud Computing Adoption, Higher Education Institution (HEI), Individual-Level Theory, Organizational-Level Theory
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	DEVELOPING LEARNERS EMPLOYABILITY SKILL OF CRITICAL THINKING THROUGH COLLABORATIVE ONLINE DISCUSSION AT TERTIARY INSTITUTION
Author:	MOHD FADZLI ALI, LOKMAN MOHD TAHIR, NURUL NADWA ZULKIFLI
Abstract:	Various studies reported that Malaysian students at tertiary institutions were lack of certain employability skills namely critical thinking. Lack of critical thinking skills is identified when the students are unable to perform tasks, especially those of problem solving. Consequently, the students who lacked this skill were unemployed upon their graduation. A drastic approach to overcome this issue must be addressed. Instead of blaming unemployed graduates, the tertiary institutions with e-learning technology were urged to play a significant role. Through online forum discussions, the students were taught to use Socratic questions (Paul, 1993) as this would help them to develop critical thinking skill when they look deeper into the viewpoints, perspectives and evidence in analysing the assumptions (Walker, 2005). This study adopts a mixed-method case study approach. The quantitative data derived from Watkins and Corrys (2005) questionaires measures the students e-learning readiness and their usage of online forum discussions. The qualitative data derived from the transcripts of the students online discussions explains how the students develop their critical thinking using Socratic questions. The transcripts were analysed in two stages using (1), the Socratic Question Prompts and (2), a content analysis approach of the Interaction Analysis Model by Gunawardena et. al. (1997). The findings indicated that students critical thinking skills could be developed from collaborative learning through online forums. The outcome could be used to propose the best practice for lecturers at higher learning institutions to promote students to think critically through collaborative online discussion.
Keywords:	Critical Thinking, Employability Skills, Online Discussions, Socratic Questioning Prompt, Interaction Analysis Model (IAM)
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	MINING OPTIMIZED POSITIVE AND NEGATIVE ASSOCIATION RULE USING ADVANCE ABC ALGORITHM
Author:	I.BERIN JEBA JINGLE, J.JEYA A.CELIN
Abstract:	One of the imperative mining used in data mining is the association rule mining which mines many eventual information and association from outsized databases. The Association rule mining has many research challenges. The generation of accurate frequent and infrequent itemset by reducing the candidate itemset and reducing the space in the memory is one of the challenges. The generation of positive and negative association rule with high confidence and high quality is another challenge. The next research challenge is to mine an optimized positive and negative association rule. Numerous existing algorithms have been used to overcome these challenges but many such algorithms cause data loss, lack of efficiency and accuracy which also results in redundant rules and loss of space in memory. The major issue in using this analytic optimizing method is specifying the activist initialization limit were the quality of the association rule relays on. In the Proposed work, it is proved that an efficient optimized Positive and negative association rule can be mined by the proposed Advance ABC algorithm. The advance ABC (Artificial Bee Colony) algorithm is swarm intelligence based algorithm highly efficient optimization algorithm. The Advance ABC Meta heuristic technique is stimulated through the natural food foraging behaviour of the honey bee creature. The result shows that the proposed algorithm can mine incredibly high confidence non redundant positive and negative association rule with less time.
Keywords:	Data Mining, Association Rule Mining, Apriori Algorithm, Accurate Multi Level And Multi Support,Advanceabcalgorithm,GPNAR
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	CLASSIFICATION OF EMG SIGNALS BASED ON CURVELET TRANSFORM AND RANDOM FOREST TREE METHOD
Author:	SUBHANI SHAIK, DR. UPPU RAVIBABU
Abstract:	Electromyography (EMG) signal is most powerful signal processing tools for electrical activity of neuromuscular associated with a corresponding muscle. In this paper, the analysis of EMG signals using curvelet transform and Random forest tree is presented. The EMG signal including noise though dissimilar media. The curvelet transform is used for clear away noise from the surface electromyography and superior order of statistics is used for analyzing the signal. The first level is to evaluate the surface of EMG signal and extract features using curvelet transform. The second level is best EMG quality segment was chosen and the rebuilding of the useful data signal was finished using random forest classifier. The intention of this work is introducing a novel approach for discover, analyzing and classifying of EMG signals. The proposed method is applied using clinical dataset and the parameters like mean root mean square, correlation coefficient and absolute value are calculated and to get better quality of class separability. A comparison is made with other traditional methods and the EMG characteristics extracted from rebuilding of EMG signals provide the enhancement of class separability in feature space than. Statistical results shows maximum classification accuracy of 99% and higher information transfer rate is achieved.
Keywords:	Electromyography (EMG) Signal, Curvelet Transform, Random Forest Tree, Clinical Dataset.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	WARNING CRITERION ONTOLOGY FOR MEASURING OF COMPLIANCE IN STANDARD OPERATING PROCEDURE IMPLEMENTATION
Author:	HANIF AFFANDI HARTANTO, RIYANARTO SARNO, NURUL FAJRIN ARIYANI
Abstract:	Management processes without responsive to abnormal activity that might occur can affect the performance of an organization. The Publishing Workflow Ontology (PWO) will be modified for detect abnormal activity, such as wrong pattern, wrong resource, throughput time maximum and wrong duty combine that occurs in the event logs. The new model from modification called Warning Criterion Ontology (WCO) can be represent the knowledge base to detect abnormal activity in the business process especially this knowledge can be used distinguishes the activity is allowed to be done by the superior and any activity which should only be done by direct superior. The model used some rule for reasoning, then after reasoning used some SPARQL to detection abnormal activity. Results of detection abnormal activity can be used as attributes for assessment Key Performance Indicator (KPI) activity in determining The compliance in Standard Operating Procedure (SOP) implementation. This research obtained a value of 96.29% of accuracy resulted comparing into the experts assessment score.
Keywords:	Warning Criterion Ontology, Key Performance Indicator, the Publishing Workflow Ontology
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	STUDYING NETWORK TRAFFIC USING NONLINEAR DYNAMICS METHODS
Author:	SHARAFAT A. MIRZAKULOVA, VYACHESLAV P. SHUVALOV, ALEKSEY A. MEKLER
Abstract:	The development of the Internet, the constantly growing number of network users, and their mutual exchange of information is becoming an important communication bridge. However, this causes a series of technical difficulties, one of which is the growing requirements to network and server equipment and its maintenance. Therefore, the purpose of this study is to develop a computer program for teaching a neural network based on a computer network traffic table. A set of methods was used to achieve the set goal, including analysis, deterministic chaos, and systematization. The study used such software packages as TISEAN, MatLab, NetEmul, and Excel. The study generalized the experience that was relevant to the problem at hand. The study calculated the Lyapunov exponent, which characterizes the presence of chaos in the system. Analysis of the Lyapunov exponent enables using nonlinear dynamics methods to study the nature of the incoming and outbound traffic. With the help of the developed program, the neural network router is capable of prediction short-term parameters of a computer network; this information is sent to the system administrator, which will allow adapting the router to the estimated changes in the computer network.
Keywords:	Distribution series, Self-similarity, Chaotic processes, Phase portrait, Mutual information
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	IMPLICATIONS OF DISCRETIZATION TOWARDS IMPROVING CLASSIFICATION ACCURACY FOR SOFTWARE DEFECT DATA
Author:	POOJA KAPOOR, DEEPAK ARORA, ASHWANI KUMAR
Abstract:	Since the advent of new software architectures, paradigms and technologies the software design and development has developed a cutting edge requirements of being on the right track in terms of software quality and reliability. This leads the prediction of defects in software at its early stages of its development. Implications of machine learning algorithms are now playing a very crucial role in classification and prediction of the possible bugs during the systems design phase. In this research work a discretization method is proposed based on the Object Oriented metrics threshold values in order to gain better classification accuracy on a given data set. For the experimentation purpose, Jedit, Lucene, tomcat, velocity, xalan and xerces software systems from NASA repositories have been considered and classification accuracies have been compared with the existing approaches with the help of open source WEKA tool. For this study, the Object Oriented CK metrics suite has been considered due to its wide applicability in software industry for software quality prediction. After experimentation it is found that Naive Bayes and Voted Perceptron, classifiers are performing well and provide highest accuracy level with the discretized dataset values. The performance of these classifiers are checked and analyzed on different performance measures like ROC, RMSE, Precision, Recall values in this research work. Result shows significant performance improvements towards classification accuracy if used with discrete features of the individual software systems.
Keywords:	Discretization, Software Defect Prediction, Classification, CK metrics
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	COLLABORATIVE DETECTION AND FILTERING TECHNIQUES AGAINST DENIAL OF SERVICE ATTACKS IN CLOUD COMPUTING
Author:	IMAN EL MIR, ABDELKRIM HAQIQ, DONG SEONG KIM
Abstract:	Nowadays, cloud computing technology is experiencing a fastest growing in terms services demand and number of cloud clients which make the business organizations against a critical issue must be addressed (How to Secure Cloud Data Center (CDC)). As result, this major challenge has attracted the attention of several research works. The attacker is looking for unavailability of service, dysfunctioning of resources and maximization of financial loss costs. There are many types of attack such as Denial of service (DoS) and Distributed Denial of Service (DDoS) where the key objective for the attacker is to cause an overloading of the system network. They seek to send through a victim server a huge size of data as flooding packets so as to block and prevent the users to be served. This paper introduced a defending system for DoS attack mitigation in CDC environment. Generally, it discussed the different techniques of DoS attacks and its countermeasures as well proactive filtering and detection mechanisms. Consequently, to validate our proposed solution, we have implemented our analytical model in Discrete Event Simulator. The proposed mathematical model considers many performance parameters including response time, throughput, drop rate, resource computing utilization, and mean waiting time in the system, mean number of legitimate clients in the system when varying the attack arrival rate. Indeed, we have estimated the incurred cost from the attack. Implementing performance analysis using queueing theory and simulation experiments, the proposed solution would improve the flexibility and accuracy of DoS attack prevention, and would obviously make the cloud computing environment more secured.
Keywords:	Queueing Theory, Cloud Computing, Security, Performance Modeling, Dos Attacks
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	COTTON TEXTURE SEGMENTATION BASED ON IMAGE TEXTURE ANALYSIS USING GRAY LEVEL RUN LENGTH AND EUCLIDEAN DISTANCE
Author:	SABIQ ADZHANI HAMMAM, TITO WALUYO PURBOYO, RANDY ERFA SAPUTRA
Abstract:	Combed cotton and viscose cotton (CVC) is 2 types of cotton commonly used as the main ingredient in manufacture of clothes. Clothes made from cotton combed known as good materials for clothes. CVC cotton, made by combining cotton combed and cotton viscose so that in the manufacture CVC cotton quality is assumed under the combed cotton. Manually distinguish combed cotton and CVC cotton is by wearing clothes made of combed cotton and CVC cotton. Basically the texture in combed cotton and CVC fabrics can be analyzed by image texture segmentation process based on image texture analysis to get patterns showing the type of cotton. In this research explains the texture of cotton that through the process of image texture segmentation can release the value of features that can be used for the classification process, so that can determine the type of cotton. In this image texture segmentation includes grayscaling process, image normalization and texture feature extraction. Feature Extraction uses the Gray Level Run Length (GLRLM) method to get a feature value on the texture used for the classification process. Classification using method euclidean distance with 4 testing images and 2 training images by changing the original image to 5x5 and 10x10 pixels generate 100% accuracy. These results indicate that accuracy using the euclidean distance method results in high accuracy.
Keywords:	Image Texture Segmentation, Texture Analysis, Gray Level Run Length (GLRLM), Euclidean Distance, Cotton
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	A SYSTEMATIC REVIEW ON THE RELATIONSHIP BETWEEN STOCK MARKET PREDICTION MODEL USING SENTIMENT ANALYSIS ON TWITTER BASED ON MACHINE LEARNING METHOD AND FEATURES SELECTION
Author:	GHAITH ABDULSATTAR A.JABBAR ALKUBAISI, SITI SAKIRA KAMARUDDIN, HUSNIZA HUSNI
Abstract:	This study is mainly a systematic review analysis which discusses studies related to the role of sentiment analysis, Twitter data, and features in predicting stock market returns. Studies show that it is not only the historical financial data of firms or stock markets that can predict the returns of the stock market, but sentiments and emotions of people can also help in predicting stock market returns. One primary source of information that is available now to everyone is Twitter, and tweets made by significant personals affect the emotions of people and which will ultimately affect their investment decisions. If the news is positive, then most probably it will affect people positively, and they will invest more in stocks of that firm. If the news is negative, the reaction of people is expected to be opposite. Besides the sentiments of people, there are features like spatial and temporal that can also affect the stock market returns. The spatial feature is a geographical division, it can either be different emotions of different people from different geographical regions, or they can be other stock markets which can affect the home stock market by any relation. Similarly, temporal effect shows the change in something over a span of time. People might have different opinions at different times, and they can behave differently according to their sentiments at that specific time. Finally, all these factors help us in predicting the future stock market returns.
Keywords:	Sentiment Analysis, Features, Spatial, Temporal, Stock Market
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	EVALUATION OF LEARNING PROGRAMS AND COMPUTER CERTIFICATION AT COURSE INSTITUTE IN BALI USING CSE-UCLA BASED ON SAW SIMULATION MODEL
Author:	I NYOMAN JAMPEL, I WAYAN LASMAWAN, I MADE ARDANA, I PUTU WISNA ARIAWAN, I MADE SUGIARTA, DEWA GEDE HENDRA DIVAYANA
Abstract:	One form of competence held namely computer certification for his protege, which was carried out after the students finish carry out training/learning. The main reason was held at the Institute of computer certification courses is to prepare graduates into the workforce that have a high competence and ready to compete in search of work. That is because the competition work in the era of the AEC (ASEAN Economic Community), the seekers workers cannot just rely on a certificate of learning, but is most needed is a competence that can be demonstrated by the presence of a certificate of competence. In the implementation of a computer certification program is a form of educational service organized by the course institute was still found to be constraints. To be able to find the constraints and improvements/refinements against obstacles that have been found, then it needs to be implemented evaluation of the program. This research aims to know the effectiveness of the implementation of the program of learning and computer certification at Institute courses. This research belongs to the evaluative research using CSE-UCLA model. The subject of this research consists of: teachers, program manager, and a team of students. Method of data collection is done by questionnaires, observation, interviews, and documentation. Technique of data analysis in this research is descriptive quantitative percentage to analyze the effectiveness of every component in CSE-UCLA (Center for the Study of Evaluation-University of California in Los Angeles) model and qualitative descriptive for analyzing constraints that lead to results not in accordance with the standards of the evaluation of its success. In addition, the dominant constraints affecting the implementation of the program based on the results obtained using the method of calculation of the SAW (Simple Additive Weighting) simulation model. The results of the evaluation of the implementation of the program as a whole shows the effectiveness of 80.44%, this indicates that the implementation of the program belongs to the category of good. The dominant constraints affecting the program implementation is empowerment of technical personnel for operational management.
Keywords:	Evaluation, Learning, Computer Certificate, CSE-UCLA, SAW
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	ECLIPSE JDT-BASED METHOD FOR DYNAMIC ANALYSIS INTEGRATION IN JAVA CODE GENERATION PROCESS
Author:	A. ELMOUNADI, N. BERBICHE, F.GUEROUATE, N. SEFIANI
Abstract:	In software engineering, The Unified Modeling Language (UML) is generally used as the de facto standard notation for modeling in the analysis and the design of the object oriented software systems. As known, throughout the modeling phase, the structural and behavioral elements go together, because they have complementary relationship in the understanding of systems architecture. However, structural analysis has always attracted the interest of designers more than the behavioral analysis, due to its prominent role in the code generation processes. This vision influenced the computer-aided software engineering (CASE) tools and the model-driven engineering (MDE) approach. As a result, by using CASE tools and taking up MDE approach as it is, the obtained code artefacts are incomplete and become the developers responsibility. Therefore, the models abstraction is broken, which leads to a paradoxical situation while adopting model-driven development. To cope with this challenge, the purpose of our paper is to bring balance to the design stage by integrating the behavioral analysis into the code generation processes, in order to empower and promote delivering applications without the need for hand coding.
Keywords:	MDE, UML, Dynamic Analysis, Abstract Syntax Tree, Code Generation
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	DECIDABILITY PROPERTIES OF THE CLASS OF FORMAL LANGUAGES RECOGNIZED BY K-EDGE FINITE STATE AUTOMATA
Author:	ANUCHIT JITPATTANAKUL
Abstract:	Finite state automata (FSA) are computational models which are used for studying theoretical complexity of computational problems. The computational model of k-edge finite state automata (k-FSA) have been introduced to compute naturally ordered data such as data in music processing and time series domain. The k-edge finite state automata contain theoretical interest that numbers of their edges are bounded with a k value. In order to use such model in practice, some theoretical properties need to be investigated by way of their classes of formal languages. This paper investigates the closure properties and decidability of the class of formal languages recognized by k-edge finite state automata called k-acceptable languages (k-ACC). The results include the following: (i) for k  1, the class of k-acceptable languages is closed under complement. (ii) for k  2, the class of k-acceptable languages is closed under complementation, union, intersection, concatenation and Kleene-star operation. (iii) The infiniteness problem, membership problem, equivalence problem and emptiness problem of k-acceptable languages are decidable.
Keywords:	Decidability, Closure Properties, K-Acceptable Languages, K-Edge Finite State Automata
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	A CONCEPTUAL OF KNOWLEDGE MANAGEMENT SYSTEM MODEL WITH EARLY WARNING SYSTEM IN CLINICAL DIAGNOSTIC ENVIRONMENT OF DENGUE FEVER
Author:	NORZALIHA MOHAMAD NOOR, RUSLI ABDULLAH
Abstract:	Knowledge management system (KMS) support the activities of knowledge management (KM) in early warning system (EWS) to provide early warning and aid in decision facilitation. Both KMS with EWS are also applicable in the clinical diagnostic (CD) environment during the CD activities to provide early warning and aid in decision facilitation of disease outbreak such as dengue. However, lack of proper data or information management and limited knowledge sharing and dissemination within the organization is a main challenge for mitigation of risk. In which the problem that may relate to this challenge is the timeliness for timely reporting and decision facilitation during CD activities. Therefore, a conceptual of KMS model with EWS in CD environment of dengue fever is formulated based on the existing components of KM, KMS with EWS. Then, the components of CD activities and dengue fever are also identified and studied for the model implementation. A pre survey and the analysis of five existing previous models were carried out to determine the significant components of KMS and EWS. The pre survey results analysis and gaps drawn from the analysis of these five models are used as a basis to the initial proposed of KMS model with EWS in CD environment of dengue fever. Next, the KMS model with EWS was then validated via prototype to verify the model reliability and is evaluated via a post survey. The model which is the integration between KMS with EWS is known as KMS with EWS is to enable the capturing, storing, reusing and managing of knowledge in order to provide early warning and aid in decision facilitation of dengue fever.
Keywords:	Knowledge Management, Knowledge Management System, Early Warning System, Clinical Diagnostic, Dengue Fever
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	NATURE INSPIRED SOFT COMPUTING BASED SOFTWARE TESTING TECHNIQUES FOR REUSABLE SOFTWARE COMPONENTS
Author:	PREETI GULIA, PALAK
Abstract:	Software is the inseparable part of todays human life. Each and every gadget that we use is dependent on some or other kind of software. Component based software engineering (CBSE) has provided an effective software development paradigm which allows selection of domain specific components from component repository and assemble them into a modular and scalable application. The reliability of software and its components depends on the amount of effective testing carried on it during its development life cycle. We cannot deny the fact that exhaustive testing is not possible. Selection of appropriate test suite is a combinatorial problem. Soft computing provides a promising solution for the same. Emergence of artificial intelligence over years has added fuel to nature inspired testing techniques. This paper is a comparative study of various soft computing approaches inspired by nature for reusable software components such as artificial neural network, genetic algorithm, fuzzy logic and other swarm based techniques. A comparative analysis is presented to discuss pros and cons of different soft computing techniques for software testing of reusable components along with their preferences in recent years. A future dimension is also proposed to develop hybrid techniques for optimization of testing techniques.
Keywords:	Soft computing, Test Case Prioritization, Testing, Reusable Components.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	KNOWLEDGE DISCOVERY OF THE STUDENTS ACADEMIC PERFORMANCE IN HIGHER EDUCATION USING INTUITIONISTIC FUZZY BASED CLUSTERING
Author:	T.PRABHA, Dr.D.SHANMUGA PRIYAA
Abstract:	This study observes the aspects associated with the evaluation of Students performance. To improve the performance of Students, their previous records have to be analyzed in order to determine their behavioral pattern in academic wise. This may help to assist the difficulty faced by the students to produce more marks in the semester exams and to enhance their co-curricular activities. This is done by clustering the students based on their performance. For performing the clustering process, this work utilized the fuzzy K-Mediods which takes the membership value of each student in account towards the particular cluster. The main contribution of this work is assisting to determine the level of performance of students and filtering the students who are in need of special attention by the staffs which results in improvising the quality of education.
Keywords:	Education mining, Student DataBase, Performance, Fuzzy K-Mediods, Academic
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	DISTRIBUTED AND PROGRESSIVE FEATURE SELECTION ALGORITHM FOR HIGH DIMENSIONAL DATA: A MAP-REDUCE APPROACH
Author:	CH. RAJA RAMESH, G. JENA3K RAGHAVA RAO
Abstract:	Dimensionality reduction or feature selection is an essential pre-processing step to apply machine learning algorithm further on any data set. But at for medium dimensional datasets it is optional or on-demand requirement. But it is mandatory in high dimensional datasets. Its significance is increased to get the accurate and relevant output from machine learning algorithm. Most of the existing methods are divided into 2 types one is Dimensionality reduction and the other one is feature selection. There is very narrow gap between these two methods. Dimensionality reduction is more mathematical analysis with transformations and may or may not have same subset of features from original features. Feature selection is application of feature engineering and requires domain knowledge. But any algorithm applicable for high dimensional data requires more processing time and storage resources. We considered the processing time as basis for our problem statement and implemented a distributed algorithm for Feature Selection and named as Distributed Progressive Feature selection algorithm with Knn+Relieff for high dimensional data. In this paper applied MapReduce concept to select final sub set of relevant features in progressive manner. Simulation results showthe feature with its weights for various parameters.
Keywords:	Feature Selection, Dimensionality Reduction, Mappers, Similarity Measures
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	APPLYING INTERPRETIVE HERMENEUTIC APPROACH TO INTERRELATE THE GAME ENVIRONMENT AND LEARNERS INTERACTION
Author:	MIFRAH AHMAD, LUKKMAN AB. RAHIM, NOREEN IZZA ARSHAD
Abstract:	In 21st century, one of the prominent learning tool in the education industry is highlighted as Educational games (EG). There are many ways in which the literature describes its importance in the current generation. In addition, the learning environment, the rules embedded in the game, the theoretical aspects on which the game is built, and the learners/subject-matter experts; all play a crucial role in EG. Hence, this requires a projecting need of understanding the relationships that allows an enhancement in the learning objectives for learners while interacting through the game environment. Although, relationships are vaguely dispersed in literature; understanding the need to interrelate other concepts of game environment with learners expectations, and how the elements of game environment interact throughout the play is essential. Therefore, this article highlights the proposed multi-domain framework for game developers to effectively map the game elements while extracting implicit vaguely supported relationships based on game environment domain and learners concepts through a systematic literature review. Consequently, this article explains on twelve (12) implicit relationships in perspective of game environment domain and learners. They are validated through qualitative interviews with eight (8) game-based learning experts. Subsequently, the results are interpreted in relevancy with all domains of proposed framework by applying interpretive hermeneutic approach, and using NViVO software to obtain the themes, sub-themes, and coding strategy was adopted to code the experts response with each relationship and its elements. The findings conclude twelve (12) explicit relationships between game environment domain and the learners relationships; for game developers to guide them through the development phase of EG.
Keywords:	Game Environment, Learners, Multi-Domain Framework, Hermeneutic, Interpretivism Paradigm, Coding Technique
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	A PROPOSED CONCEPTUAL MODEL FOR FLIPPED LEARNING
Author:	IRETI HOPE AJAYI, NOORMINSHAH A. IAHAD, NORASNITA AHMAD, AHMAD FADHIL YUSOF
Abstract:	This study developed and tested the efficacy of flipped model that is usable as a strategy for teaching and learning. The concept applied Perceived Ease of Use (PEOU), Perceived usefulness (PU), Teaching Method (TM), task Technology Fit (TTF), Behavioral Attitude (BA) as factors influencing the use of the system (flipped learning). The model made used of Technology Acceptance Model (TAM) and Task-Technology Fit (TTF) to develop some hypotheses and some connected determinants. The result of the survey conducted was tested using SmartPLS software package. The outcome of the investigation indicates that Teaching Method (TM) is the highest determinant factor followed by use intention, perceived usefulness, perceived ease of use, behavioural attitude and TTF. This confirmed that students belief about the manner through which they are been taught (Teaching method) has a great influence on their performance.
Keywords:	Learning, Flipped Learning, TAM, and TTF
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	EXPLORING THE USE OF COMPUTER ASSISTED AUDIT TECHNIQUES AND ITS IMPACT TO THE TRANSPARENCY AND ACCOUNTABILITY OF FINANCIAL STATEMENTS
Author:	RINDANG WIDURI, SYNTHIA A. SARI
Abstract:	The objective of this research is to explore the perception of internal auditor in public companies on the use of Generalized Audit Software (GAS) to improve the transparency and accountability of financial report. The qualitative approach was used by conducting face-to-face semi structured interview with the internal auditors from Indonesian listed companies. This research used Agency Theory and Technology Acceptance Model (TAM) as underpinning theories, therefore this research provides academic contribution not only in auditing area but also in information technology. The results indicated not all participants agreed that GAS is helping them in producing a transparent and accountable financial report. Also, this research found that companys internal condition and individual characteristics of internal auditor are the inhibiting factors in using GAS.
Keywords:	Internal auditor, Generalized Audit Software, Technology Acceptance Model, Good Corporate Governance, IDX
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text

Title:	HYBRID DATA DEDUPLICATION TECHNIQUE IN CLOUD COMPUTING FOR CLOUD STORAGE
Author:	HESHAM ABUSAIMEH, OMAR ISAID
Abstract:	This paper proposed a hybrid data deduplication technique in cloud computing, that combines different types of data deduplications for satisfying different demands and requirements. The hybrid data deduplication consists of two different hybrid subsystems, each hybrid subsystem contains a file level deduplication and chunk level deduplication. The file level deduplication shows better execution time for deduplication redundant files. And, chunk level deduplication for detecting duplicated chunks among files at the data. The subsystems are: hybrid file variable size chunk level deduplication (FVCD), and hybrid file fix size chunk level deduplication (FFCD). The FVCD satisfies the requirements of users and applications that required better effectivity in reducing the size of data. While, the FFCD provides lower execution time. And, it can be tuned by changing its chunks size. Where, increasing the chunks size reduces the execution time. But, it decreases the effectivity of reducing the size of data.
Keywords:	Data Deduplication, Cloud Computing, Cloud Storage
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2017 -- Vol. 95. No. 24 -- 2017
Full Text