		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
February 2018 | Vol. 96 No.3

Title:	AN ITERATIVE GENETIC ALGORITHM BASED SOURCE CODE PLAGIARISM DETECTION APPROACH USING NCRR SIMILARITY MEASURE
Author:	M. BHAVANI, DR.K.THAMMI REDDY, DR.P.SURESH VARMA
Abstract:	With the advent of WWW and improvements in globally accessible software warehouses attained that source code is enthusiastically reachable to software designers. Even though, reusing of source code has its individual benefits, precaution is to be taken to guarantee that patented software [19] does not invade any authorizations. In this Context, Plagiarism Detection plays a very significant role. Although several existing detection approaches has been introduced, most of the approaches work on one to many similarity measures. However, this might not be very much helpful in case large number of datasets where many-to-many relationship exist. In this paper, an intelligent detection model is purposed by employing the iterative genetic algorithm with two different fitness evaluation functions. Prior to the detection model, the source code is preprocessed to remove noise and dimensionality reduction techniques are employed. The experimental results for the proposed approach are carried out using two different data sets. From the experimental results, it is found that the proposed model has good performance compared to the other existing approaches such as fuzzy clustering based Detection system and Incremental Genetic Algorithm.
Keywords:	Source Code, Plagiarism detection, Genetic Algorithm, Singular Vector Decomposition, Similarity Measure, Normalized Cumulative Reciprocal Rank, Euclidean Distance
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	IMPROVED C4.5 : AN AGENT-BASED SUPPLY CHAIN MANAGEMENT SYSTEM
Author:	C.P.BALASUBRAMANIAM, Dr.R.GUNASUNDARI
Abstract:	The supply chain management is an interesting and focused process at present. It has a lot of scope in the literature on SCM and there are a wide of models describing the Supply chain from different approach. The Supply Chain management system is the lowest possible cost and also meets the customer’s expectations on services like delivery precision and lead-time. In this paper, efficient decision based technique C4.5 is improved for the classification. The correlation coefficient of Kendall is used to improve supply chain management system. The accuracy of system is calculated by the sensitivity and specificity for the proposed and existing technique for the lowest textile dataset here. The result of system was proved by the proposed technique’s efficiency.
Keywords:	Supply chain management, C4.5 Algorithm, Mascot, Agent Based Modelling
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	QURAN ONTOLOGY: REVIEW ON RECENT DEVELOPMENT AND OPEN RESEARCH ISSUES
Author:	NANNA SURYANA, FANDY SETYO UTOMO, MOHD SANUSI AZMI
Abstract:	Quran is the holy book of Muslims that contains the commandment of words of Allah. Quran provides instructions and guidance to humankind in achieving happiness in life in the world and the hereafter. As a holy book, Quran contains rich knowledge and scientific facts. However, humans have difficulty in understanding the Quran content. It is caused by the fact that the meaning of the searched message content depends on the interpretation. Ontology able to store the knowledge representation of Holy Quran. This paper studies recent ontology on Holy Quran research. We investigate the current trends and technology being applied. This investigation cover on several aspects, such as outcomes of previous studies, language which used on ontology development, coverage area of Quran ontology, datasets, tools to perform ontology development ontology population techniques, approaches used to integrate the knowledge of Quran and other resources into ontology, ontology testing techniques, and limitations on previous research. This review has identified four major issues involved in Quran ontology, i.e. availability of Quran ontology in various translation, ontology resources, automated process of Meronymy relationship extraction, and Instances Classification. The review of existing studies will allow future researchers to have a broad and useful background knowledge on primary and essential aspects of this research field.
Keywords:	Information Retrieval, Ontology, Quran Ontology, Ontology Extraction, Ontology Population
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	A METHOD FOR MATCHING MODELS IN UML-B
Author:	MUHAMMED BASHEER JASSER, MAR YAH SAID, ABDUL AZIM ABDUL GHANI, PATHIAH ABDUL SAMAT
Abstract:	UML-B is a graphical front-end formal modelling language of the formal method Event-B. UML-B models semantics are given by the corresponding generated Event-B. Identifying similarities between models has several benefits such as model comparison, integration and evolution. Several matching and comparison methods have been done in the context of model driven software engineering. However, matching models via a systematic method is not supported yet in UML-B. In this work, we propose a matching method for UML-B elements based on their semantics. This method includes variable-based matching, event-based matching and state-machine matching. The variable-based matching provides rules for matching UML-B classes, attributes, states and variables. The event-based matching provides rules and cases for matching UML-B transitions and class-events. The state-machine matching provides rules for matching UML-B state-machines based on the state and transition matching rules. The matching rules are formalized by means of the generated corresponding Event-B specifications. The correctness of the rules is justified via preserving the compatibility of the matched state-variables and corresponding modifying events including their matched guards and actions. These rules are illustrated via a communication-based case study to show their applicability.
Keywords:	Visual modeling languages, Formal specification, Event-B, UML-B, Model Matching
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	AN ELM PREDICTIVE MODEL FOR RISK ASSESSMENTS OF CVD IN IMPAIRED GLUCOSE TOLERANCE (IGT) PATIENTS VIA GENPCNN AND SLFNS ALGORITHM
Author:	S.RAJESWARI, DR.M.S.JOSEPHINE, DR.V.JEYABALARAJA
Abstract:	Medical diagnosis systems play a vital role in medical practice and are used for diagnosis and treatment by several medical practitioners. Diagnosing the risk factors of pre-diabetic (IGT) cases is quite difficult. There is a big challenge to improve the diagnosis system to recognize the risks factors of impaired glucose tolerance regarding to cardiac vascular disease. In this paper, ELM classifier is combined with the hybrid of genetic algorithm and pulse coupled neural network (GENPCNN). Especially, a Single-hidden layer feed forward neural networks are suitable for solving the complex classification problem. The datasets we collected from health care centre having 270 instances of pre-diabetic, Diabetic and non-diabetic data each was having 28 attributes. A combination of genetic algorithm based neural networks to select the features from the dataset. So, it will be reduced to 14 attributes. The best population of the GA will be passed as input for the PCNN. The features extracted from the GENPCNN are passed to ELM classifier SLFNs in which the hidden nodes are chosen randomly and logically determines the output weight. First, dataset is preprocessed in order to remove the noisy data, missing values or irrelevant values and also from ‘curse of dimensionality’ which have to make suitable for training. This algorithm tends to provide good generation performance and extremely fast learning speed. The classification accuracy obtained using this approach is 94%. The obtained results have shown very promising outcomes for the prediction of risk factors of CVD in impaired glucose tolerance and impaired fasting glucose.
Keywords:	Pulse Coupled Neural Network, Genetic Algorithm, Dysglycemia, ELM, Impaired Glucose Tolerance
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	TACIT KNOWLEDGE FOR BUSINESS INTELLIGENCE FRAMEWORK: A PART OF UNSTRUCTURED DATA?
Author:	HERISON SURBAKTI, AZMAN TAA
Abstract:	Idea to capture knowledge from different sources can be very beneficial to Business Intelligence (BI). Organizations need to collect data sources from type of structured and unstructured, including individuals' tacit knowledge in order to have the better output in data analysis. Therefore, the complexity of BI processes need to be explored in order to ensure the process will properly treat the tacit knowledge as a part of the data source in BI framework. Moreover, the linkage between unstructured data and tacit knowledge is generally consistent, for the reason that one of tacit knowledge characteristic is unstructured, which is difficult to capture, codify, estimate, investigate, formalize, write down, and communicate accurately. Cognitive approach is ideally suited for the capturing tacit knowledge as from among the massive data available these days. Typically, the organization must integrate multiple streams of data from several sources or other collaboration resources with the knowledge systems for making the decisions. This paper explores the possibility of tacit knowledge used in BI framework to perform data analysis for decision makers.
Keywords:	Business Intelligence, Cognitive Approach, Data Analytics, Tacit Knowledge, Unstructured Data
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	A NOVEL DENOISING TECHNIQUE FOR MIXED NOISE REMOVAL FROM GRAYSCALE AND COLOR IMAGES
Author:	K. CHITHRA, T.SANTHANAM
Abstract:	The real-time images acquired from cameras, CCTV, medical image scanners like Magnetic Resonance Imaging (MRI), Computerized Tomography (CT), Ultrasound (US) and X-ray etc., are often corrupted by noise. This noise may be a mixture of two or more noise types. In recent years, researchers concentrate on developing a denoising filter to suppress the mixed noises to improve the quality of the image. A novel algorithm that uses absolute difference, mean and median for the removal of mixed noise in image has been proposed in this article. The proposed filter is tested with the images induced by two types of noise mixed (Salt and Pepper and Gaussian noise) and three types of noise mixed (Gaussian, Salt and Pepper and Speckle noise) images. The performance of the proposed algorithm is compared with existing Fuzzy Based Filter (FBF), and Median Weiner Bilateral Filter (MWBF) algorithms. The test images used in this research work are Lena image, Iris eye images and medical images in grayscale Joint Photographic Experts Group (JPEG) format and also with the color images in four different image formats with mixed noise level ranging from 0.01 to 0.10. The experimented results show that the proposed algorithm yields better performance than the algorithms mentioned above. Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE) are the metrics used in this comparative analysis.
Keywords:	Image Denoising, Mixed noise removal, Mean, Median, Absolute Difference, PSNR, MSE
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	EFFICIENT APPROACH OF DETECTION AND VISUALIZATION OF THE DAMAGED TABLETS
Author:	RIHAB HAZIM QASIM , AND MUZHIR SHABAN. AL ANI
Abstract:	People affected by many diseases in their lives and this effect with the productivity of the individual in society and the lives of the entire person and most of these diseases can be cured by medicines. The problem in pharmaceutical industries, in the actual situation, existing a number of defects incorporated in tablets inadequate fines to granules ratio, inadequate moisture content and poor machine settings can be some of the reasons for those visual defects such as faults in a cover of tablet pill. In addition, the production of medicines and pharmaceutical factories are expanded so it is difficult to control the quality of the tablets after packaging. The aim of this paper is to upgrade this manual tablet-sorting machine into an automated system with the aim of improving the speed and accuracy of the sorting process. The hole in the cover plastic package is common defects that can be found in tablets. Therefore, this defect was considered for the purpose of this paper. Damage on the Cover plastic package can be produced during the production of the packaging and can be produced before packaging therefore; will design system inspection the cover plastic before packaging for less damage money as much as possible, also inspection the cover plastic after packaging because the damage on the cover plastic packaging causes damage in pills and capsules. The proposed system algorithm includes preprocessing and feature extraction using opponent local binary patterns &opponent coordinated clusters representation (its the contribution research) and finally the classification of tablets for damage or undamaged issue using an artificial neural network algorithm (ANN) and specifically feed forward back propagation learning.The neural network training with feature extraction from the data after it has been tested. The experimental results are acceptable, the performances of the check pill cover plastic system indicated the total accuracy of 94.4% for testing. Also, the approach using opponent features provides better recognition accuracy than other approaches. The system is evaluated using sensitivity, specificity, and accuracy. The programs are done using Matlab package.
Keywords:	Hole in the Covered Plastic, LBP, CCR, Packaging, Texture
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	AN ALTERNATIVE SOLUTION TO HANDLE DDOS ATTACKS
Author:	AHMAD SANMORINO, RENDRA GUSTRIANSYAH
Abstract:	Through this article, we try to offer alternative solutions to handle DDoS attacks. The discussion begins with a study of literature on DDoS attacks that include the mechanism of DDoS attack detection proposed by several researchers. The discussion then proceeded to propose alternative solutions to deal with DDoS attacks. The proposed alternative solution continues the research we have done before, using the SOM algorithm with added packet per flow feature for classifying incoming packet data. By doing the classification, can distinguish a normal data packet and abnormal one. Through the discussion in this article, we expected to contribute in the world of research, especially those related to system security issues.
Keywords:	DDoS, Packet, Flow, Classification
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	DEVELOPMENT OF MEDIA-BASED LEARNING USING ANDROID MOBILE LEARNING
Author:	KHAERUDDIN SAID, ADE KURNIAWAN, OEY ANTON
Abstract:	Today, more than 80% in 104 countries of the youth population are online using Mobile Smartphone. The percentage growth of smartphones in the world is 3%. In Indonesia, the increase amount reaches 6 million per year with the number of smartphones worldwide reaches 7.5 billion in Q3 of 2016. Moreover according to Forbes Magazine, Operation System (OS) of Android controls 65% of the worldwide smartphone market shares beat IOS, Blackberry, and others. The landscape of educational problems especially at Vocational Senior Secondary School (SMK) level in Indonesia is lack of qualified teachers, digital learning media devices such as computers which are still expensive, unclean financial governance and media for learning are not attractive to learners. Learning media is used by teachers to stimulate learners interest to learn should be interesting and interactive in teaching and learning process. In this paper we develop Media-Based Learning using Android Applications as a medium of learning to SMK Learners for the competence operation of electronic control system. The results of the assessment of media experts, teachers, and learners are assessed based on 3 aspects, namely aspects of teaching media, CAI media aspects and material relevance aspects which conclude that media-based learning using android mobile learning is very feasible. Contribution of Media-Based Learning research using android apps are concluded to increase learners interest, easy to be carried everywhere, cheap, and worthy of use as a medium of teaching and learning media after performing functionality test included: ease of navigation, application performance, and ease of operation.
Keywords:	Media Learning, Android, Senior Vocational Education, Smartphone, Teaching
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	AN INTEGRATED MODEL OF KNOWLEDGE MANAGEMENT ENABLERS AND ORGANIZATIONAL CREATIVITY: THE MEDIATING ROLE OF KNOWLEDGE MANAGEMENT PROCESSES IN SOCIAL SECURITY CORPORATION IN JORDAN
Author:	MAHA ALKHAFFAF, MONIRA MUFLIH, MAHMOUD AL-DALAHMEH
Abstract:	This paper intends to make a contribution to the overall understanding of the relationship of organizational creativity to the enablers of knowledge management, including culture, structure, people and information technology, through examining the role of knowledge management processes, comprising the creating, sharing and codification of knowledge, as a mediating factor in this relationship. This research Integrated three well known models in KM area; Lawson’s model (2003) for identifying one of the knowledge management enablers; Organizational Culture, Lee & Choi Model (2003) for measuring the other enablers; Structure, People, Information Technology and the Allameh Model (2011) in order to measure knowledge management process as a mediating factor. The study aims to find out the impact of these factors in Organizational creativity, An empirical survey study has been adopted in this research paper by distributing questionnaires amongst social security corporation employees in Jordan. A total of 572 questionnaires were collected and analyzed using the smart Partial Least Square (PLS) technique. The main findings derived showed that knowledge management enablers, namely people and structure support, affect organizational creativity better with the mediate factor (KM process), whilst other enablers, namely culture and IT support, do not impact organizational creativity without a mediating role (KM Process). This paper might be valuable for academic people who are considered with understanding the linkage between organizational creativity and knowledge management enablers, furthermore, the paper might be helpful for scholars to discover additional mediating factors in this relationship; consequently, these new mediators possibly raise the organizational creativity.
Keywords:	Creativity, Knowledge Management Enablers, Knowledge Management Process
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	GIS-BASED DECISION SUPPORT SYSTEM FOR CASH WAQF DISTRIBUTION
Author:	KUSRINI KUSRINI, KUSUMA CHANDRA KIRANA, MUHAMAD IDRIS PURWANTO, ARIF DWI LAKSITO
Abstract:	Gunung Kidul Regency of Indonesia has a problem with a massive number of former Migrant Women Workers (MWW) who live in poverty. Meanwhile, Indonesian people who are Muslim in majority have a huge potential to do cash waqf (a form of donation worship in Islam). The fund collected can be utilized for community empowerment, specifically former MWW to reach their financial independence. It needs a model to do cash waqf distribution so the fund can be right on target and by the needs of the community. A decision support system approach utilizing knowledge representation in an expert system is proposed in this research. The model built is implemented in the application with GIS-shaped visualization. The model and applications have been tested and were accepted by potential users, but further development is still required to be implemented.
Keywords:	DSS, GIS, Knowledge Representation, Cash Waqf
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	A STUDY ON CONSTRUCTION OF ANALYSIS MODEL FOR BUILDING VIEW ENVIRONMENT USING UAV
Author:	SEUNGCHAN BAEK, WONHWA HONG, YEOL CHOI, SEUNGWOO LEE, MYUNGSUP CHUNG, HYUNDEOK KIM
Abstract:	View environment has become a new index for evaluating the economic value of buildings. Therefore, demand for environmental analysis is increasing. The current method used for analyzing a view environment involves conducting a field survey or the use of a simulation method based on actual survey data as well as satellite and aerial survey data. However, the analysis of the view environment through a field survey has limitations in the planning or design of buildings. Simulation methods using actual survey or satellite and aerial survey have an economical limitation in that they require considerable manpower and time. Recently, ICT(Information and Communication Technologies) and UAV(Unmanned Aerial Vehicle) technologies have rapidly increased, and it possible to acquire high resolution spatial information and 3D modeling. In this study, a small UAV was used to analyze the view environment of buildings and construct a model. In order to achieve the purpose of this study, an aerial photograph was taken using a UAV for urban areas, and spatial information (orthophoto and Digital Elevation Model) of the urban areas was constructed. Virtual buildings were modeled using BIM and a view environment analysis model was constructed for buildings by combining the virtual buildings with the constructed spatial information. Finally, this study established the framework of the construction of the view environment. This study proposed a methodology for constructing a view environment model for buildings using UAV. It is expected that the results of this study will be useful in the future planning and design of building view environment. Furthermore, this study provides a preliminary demonstration of view environment analysis modeling based on actual background; it is expected that various applications will be developed using future IoT(Internet of Things) and VR(Virtual Reality) technologies.
Keywords:	View Environment, UAV, Spatial information, Building, Analysis Model
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	AN ANALYSIS OF PARALLELIZATION IN MAMDANI- AND SUGENO-TYPE QUALITY OF WEB SERVICE FUZZY MONITORING MODELS
Author:	MOHD HILMI HASAN, EMELIA AKASHAH PATAH AKHIR, NORSHAKIRAH A AZIZ, IZZATDIN ABDUL AZIZ, JAFREEZAL JAAFAR
Abstract:	Quality of web service (QoWS) monitoring is an important component in web service as it evaluates web service delivery performance and detects problems. Our previous work proposed a fuzzy model for QoWS monitoring due to uncertain nature of web service environment. However, fuzzy models are computationally costly. In this work, we propose a parallelization implementation of the models. The objective of this paper is to compare the performance between Mamdani- and Sugeno-based fuzzy inference systems (FIS) when they are applied to the QoWS monitoring models. The results suggested that Sugeno models produced less processing time than that of Mamdani models. However, Mamdani models benefited from parallelization more than that of Sugeno models by recoding higher percentage of improvement in terms of average processing time. This work will be expanded to investigate the implementation of the models in cluster computers and using a higher type of fuzzy logic, namely interval type-2 fuzzy.
Keywords:	Fuzzy Inference System, Fuzzy Parallelization, Sugeno, Mamdani, Web Service Monitoring
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	ENERGY AWARE FAULT TOLERANCE TOPOLOGY CONTROL ALGORITHM
Author:	ALI ABDULJABBAR ALI, KHAIRUL AZMI ABU BAKAR
Abstract:	Wireless sensors network (WSN) has emerged as one of the most common and widely spread wireless networks and is widely deployed in different fields and environments. Topology control algorithms aim to conserve energy and improve network capacity by choosing the right transmission power and neighbors so that the network is connected and has the desired properties. In WSN, topology nodes located away from sink node send the data of their messages over different long paths, which require higher amounts of energy than the near sink nodes. On the other hand, if any parent node in the topology fails due to technical error or energy depletion, nodes that send data over this failed node consume more energy and there is higher data loss due to selecting higher cost paths or failing to find an alternative one. In this paper, an energy-aware and fault tolerance topology control has been proposed which can built topology to minimize energy consumption and rebuild the affected parts of network topology in the case of parent nodes failure. WSN topology was built to minimize the maximum load of each topology node which can minimize power consumption and maximize the network lifetime. On the other hand, in the fault tolerance phase, the proposed mechanism monitored WSN nodes and in the case of node failure, the affected part of network topology was rebuilt and it can resume data collection immediately. Results showed that the proposed mechanism reduced the maximum load up to 35% compared to the AODV scenario. However, Packet delivery ratio and network throughput were increased up to 44% compared to energy based without the failure tolerance topology control mechanism in the case of node failure.
Keywords:	WSN, Topology control, fault tolerance, controlled sink.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	FREQUENT ITEMSET MINING ALGORITHMS: A SURVEY
Author:	Sireesha Moturi, Dr.S.N.TirumalaRao, Dr. Srikanth Vemuru
Abstract:	Task of extracting fruitful knowledge from huge datasets is called data mining. It has several aspects like predictive modeling or classification, cluster analysis, association analysis, anomaly detection and regression etc. Among all association rule mining is one of the major tasks for data mining. Association analysis is mainly used to discover patterns, which describes strongly associated features in the data. Market basket data is one of the major applications of association rule mining. Other applications include bioinformatics, medical diagnosis, scientific data analysis, web mining, finding the relationships between different elements of earth climate system etc. Various algorithms have been proposed by researchers to improve the performance of frequent pattern mining such as Apriori, Frequent Pattern (FP)-growth etc. We are providing a brief description of some of the techniques in detail in the later section of this paper.
Keywords:	Association Rule Mining, Support, Confidence, Frequent Itemset
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	SECURING MAPREDUCE PROGRAMMING PARADIGM IN HADOOP, CLOUD AND BIG DATA ECO-SYSTEM
Author:	DR. ANITHA PATIL
Abstract:	In the wake of technologies like cloud computing, virtualization and big data, MapReduce is the new programming paradigm used for processing voluminous data known as big data. MapReduce computations take place in thousands of commodity computers associated with cloud. Thus it can exploits Graphics Processing Units (GPUs) associated with cloud with its parallel processing abilities. Enterprises in the real world are shifting from traditional computing to cloud computing and traditional data mining to big data analytics. The rationale behind this is the exponential growth of data. Storing and processing such data needs big data eco-system associated with cloud computing. In this context, MapReduce programming model is supported by distributed programming frameworks like Hadoop. However, it is very challenging to secure MapReduce computations from malicious attacks. In the literature many secure cloud storage mechanisms are found. However, securing MapReduce programming paradigm in Hadoop and big data eco-system is still to be explored. In this paper, we proposed an algorithm based on differential privacy to protect big data from malicious Mapper and Reducer. We built a prototype application to demonstrate proof of the concept. The result showed the utility of the proposed approach.
Keywords:	Big Data, Mapreduce Programming, Hadoop, HDFS
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	CLASSIFICATION OF HUMAN MEMBRANE PROTEIN TYPES USING OPTIMAL LOCAL DISCRIMINANT BASES FEATURE EXTRACTION METHOD
Author:	NOR ASHIKIN MOHAMAD KAMAL, AZURALIZA ABU BAKAR, SUHAILA ZAINUDIN
Abstract:	This paper presents a method of membrane protein feature extraction using a combination of the local discriminant bases (LDB) and three different classifiers. This method has adopted two dissimilarity measures of normalized energy difference and relative entropy to identify a set of orthogonal subspaces in optimal wavelet packets. The energy will be derived from the calculation of the two dissimilarity measures that have overlapping subspaces. This feature, in turn, serves as an input to support vector machine (SVM), decision tree and naïve Bayes classifiers. The proposed model yields the highest accuracy of 78.6%, 76.25%, 76.72% for dataset S1, S2, and S3 respectively by using SVM. This technique outperformed other feature extraction method for membrane protein type classification for dataset S2 and S3.
Keywords:	Membrane Proteins, Feature Extraction, Local Discriminant Bases, Wavelet, SVM
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	PERFORMANCE ANALYSIS OF MULTI OBJECTIVE HYBRID SELF ORGANIZED PSO-DGSA BASED ROUTING IN WIRELESS MESH NETWORKS
Author:	CHITRALEKHA.T, RAMAMOORTHY.P
Abstract:	Wireless Mesh Networks (WMNs), is a type of Wireless Sensor network with topology various from simple star network to multi-hop wireless mesh networks. Connectivity, Stability and Quality of Service (QoS) are the important parameters to be consider in forming the network. In this work, a novel hybrid self-organized Particle Swarm Optimization– Differential Gravitational Search Algorithm is developed to determine an optimal route in WMN. The optimization problem is formulated using bi-objective optimization for the mesh router nodes placement, measuring network connectivity and that of user coverage. Computational results are discussed for the Hybrid SOPSO method, it is optimizing the packet delivery ratio, throughput and delay for effective routing and the results proves it is an effective search method.
Keywords:	Mesh, Optimization, Routing, Gravitational Search, Self Organized.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	LIGHTWEIGHT IDENTITY BASED SIGNATURE FOR MOBILE OBJECT AUTHENTICATION IN THE INTERNET OF THINGS
Author:	MAHA SAADEH, AZZAM SLEIT, KHAIR EDDIN SABRI, WESAM ALMOBAIDEEN
Abstract:	Trusted communication is crucial for data sharing and resource access in the context of the Internet of Things (IoT). This paper presents a lightweight hierarchical authentication protocol, using identity based signature, to serve IoT mobile objects. The proposed protocol has three entities; Private Key Generator (PKG), sub_PKG, and mobile objects. A comparison with other related protocols according to the key generation method, key distribution method, and the security attack model is presented. BAN logic is used for formal verification of the proposed protocol. Moreover, the performance is evaluated based on a quantitative measure of performance metrics such as number of scalar multiplication and modular inverse operations. The evaluation shows that the proposed protocol has a lower total computation cost since it does not use expensive hash to point, modular inverse, and bilinear pairing operations. This makes it more efficient and suitable in supporting IoT constrained mobile objects.
Keywords:	Internet of Things, Hierarchical Architecture, Object Authentication, Identity Based Signature, Object Mobility.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	HVS BASED NEAR REVERSIBLE DATA HIDING SCHEME USING DCT
Author:	T. BHASKAR, D. VASUMATHI
Abstract:	In this research, a certain level of modifications to the original content can be acceptable. These schemes are called near-reversible. In this embedded content is allowed to be manipulated and the content can be restored almost to the original content. It has emerged application in remote sensing. In remote sensing application the image is captured while monitoring the damaged regions in the natural disasters such as tsunami, volcanic eruption, etc. proposed scheme have less pixel alterations or coefficients as an alternate to more alterations. In reversible data embedding shows the evidence of low embedding capacity and complexity. Already exist a few near reversible hiding schemes, deals with capacity, robustness and visual quality metrics. when the data is hidden in the image which is unclear, for accessing that image best quality metrics we need to use, generally the conventional mertric PSNR is not sufficient. Therefore, we present an HVS based metrics like PSNR_HVS, PSNR_HVS_M, MSSIM. Using frequency domain transform that evaluates the overall image quality. Hence, the new knowledge on this research paper is design of near-reversible scheme which has wider applications in remote sensing.
Keywords:	HVS (Human Visuval System), Frequency Domain Transform, PSNR_HVS, PSNR_HVS_M And MSSIM
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	SCHEDULING ALGORITHMS FOR MULTICORE SYSTEMS BASED ON APPLICATION CHARACTERISTICS
Author:	JUNG KYU PARK, JAEHO KIM, HEUNG SEOK JEON
Abstract:	In this paper, we research how an application effects on other applications when they are executed in the same processor. And we take advantage of PMU (Performance Monitoring Unit) to examine that shared resource has the strongest relation with the influence. Based on the analysis, we design a novel user-level scheduling scheme that monitors applications characteristics on-line utilizing PMU and allocates applications into cores so that it can reduce the contention of shared resources. The key idea of this scheme is separating high-influential applications into different processors.
Keywords:	CPU, LLC, NUMA, Performance Monitoring Unit
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	BEHAVIOR CLUSTERING SYSTEM BASED ON LOCATION DATA FOR LABORATORY SAFETY MANAGEMENT
Author:	Hyun-Seong Lee, Seong-hyun Lee, Jae-gwang Lee, Jae-kwang Lee
Abstract:	The laboratory safety management system that can predict the risk situation and monitor the safety status. In order to predict and inform the researchers about the risk situation of the laboratory, it is necessary to classify the location area where the risk factor exists and the status information of the researcher according to the real time position. Based on the classification results of the location history data for the previous risk situation, classification algorithms such as K-Means or density-based spatial clustering of applications with noise (DBSCAN) are used to classify the real-time location. However, since the classification algorithm requires a large amount of computation, there is a problem that a high-grade processor must be used in order to process many position record data. To solve this problem, we use Apache Spark, which has recently become a big data processing framework. Since Apache Spark processes in memory and is suitable for iterative operation of large-scale data, it can perform classification operation of large amount of position data more quickly. In addition, Apache Spark supports RDD-based Matrix storage method to process location data type, enabling faster location data processing. In this paper, we design and implement a classification algorithm for location data stored in the Apache Spark environment. The classification algorithm uses the existing K-means algorithm and the DBSCAN algorithm more suitable for position data. Based on the classified result data, the classification speed of position data is compared and analyzed.
Keywords:	Laboratory Safety, Apache Spark, Big Data, Clustering Algorithm, DBSCAN
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	CLASSIFICATION OF CONCURRENT ANOMALIES FOR IOT SOFTWARE BASED SUPPORT VECTOR MACHINE
Author:	ZHIQIANG WU, ASAD ABBAS, XIN CHEN, SCOTT UK-JIN LEE
Abstract:	Internet of Thing (IoT) can connect anyone with anything at any point in any place. Currently, growing number of IoT devices have become a major role of daily life owing to their convenience. The IoT devices usually controlled by Web applications and mobile applications, which will process lots of events from user’s controller to devices. Hence, such software is a kind of concurrent program in IoT environment because the software is unable to simultaneously process these events, which may cause the concurrent issue. There is event-drive model in either Web application or mobile applications, which is unable to easily detect the concurrent anomaly by existing approaches due to the non-determined of execution and hardly reproduced by the same sequence. The previous techniques of concurrent detection are excessive limitations that only used for one of concurrent anomaly with the large number of false positive. In this paper, we describe a novel methodology to dynamically classify two types of concurrent anomalies for IoT software. According to the executable sequence graph, we generate the training and test examples for classification. The vectorization features are classified by Support Vector Machine (SVM) with Gaussian kernel. The SVM will predict the concurrent state of current executable example. As a result, the optimal true positive of simulation is 80% in our experiment which is a higher accuracy than others.
Keywords:	Concurrency Anomalies, Machine Learning, IoT Software, Support Vector Machine, Classification
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text

Title:	A STUDY ON THE DETECTION OF MALFUNCTION OF GAS SENSOR IN INDOOR USING REGRESSION ANALYSIS
Author:	KI-SU YOON, SEOUNG-HYEON LEE, JAE-PIL LEE, JAE-KWANG LEE
Abstract:	As the industry enters the modern world, the chemical industry is growing in scale. As a result, the handling of chemicals is increasing and the risks are increasing. In particular, there is always the problem of the occurrence of chemical accidents due to the failure of control or management. To prevent this, a disaster detection system using sensors is actively under study. However, the gas sensor among the disaster detection sensors is malfunction due to the influence of the temperature and the humidity. Therefore, in this paper, we analyze the data of temperature sensor, humidity sensor data, and gas sensor data collected in indoor to prevent this. After confirming the correlation between the data, we calculate the regression equation that can express the sample data by calculating the coefficient of determination through regression analysis. Based on this, we propose a method to detect the malfunction by constructing an environment that can compare and analyze the data of the actual gas sensor with the data through the regression equation.
Keywords:	Gas Sensor, Bigdata, Regression analysis, Correlation
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2018 -- Vol. 96. No. 3 -- 2018
Full Text