		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

September 2017 | Vol. 95 No.17

Title:	TEXTURE PATTERN IN ABNORMAL MAMMOGRAMS CLASSIFICATION USING SUPERVISED MACHINE LEARNING TECHNIQUES
Author:	YOUSSEF BEN YOUSSEF, ELHASSANE ABDELMOUNIM, ABDELAZIZ BELAGUID, MOHAMMED NAJIB BOUJIDA
Abstract:	The purpose of the present study is to extract pattern texture from regions of interest (ROI) on mammograms and to use texture descriptors to classify the ROI into benign or malignant mammograms. Supervised Machine Learning (SML) algorithms like Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) are used to classify the ROI. Two types of texture descriptors (GLCM and GRLM) are extracted after cropping and resizing the ROI. The goal is to find the best texture descriptors which give best accuracy in the classification of mammogrames. Our proposed method is proved to be a highly efficient method for the diagnostic of breast cancer with high accuracy using SVM. This study proves that SVM is a consistent classifier for two mammogram databases use.
Keywords:	Breast cancer, Computer Aide Diagnosis (CAD), Classification, Supervised Machine Learning(SML), Texture Pattern
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	INTERNET OF THINGS (IoT) MOBILITY SUPPORT BASED ON DISTRIBUTED SENSOR PROXY MIPV6
Author:	JABIRY M.MOHAMMED, BI-LYNN ONG, R. BADLISHAH AHMAD, MOHAMMED HAKAWATI
Abstract:	It is expected that the footprint of the Internet of Things (IoT) will increase in the future. In order for this increase to occur, a network architecture which is flexible and capable of handling multiple flows with varying requirements as well as dynamically meeting the current demands. A new era of dynamic entities (nodes) within an environment like smart hospitals and cities is being empowered by IoT. The Sensor Proxy Mobile IPv6 (SPMIPv6) has been specifically determined for IP-based wireless sensor network (WSN) mobility with the aim of potentially reducing the consumption of energy by means of preserving the mobile nodes from being part of the handoff process. The majority of the shortcomings of the Proxy Mobile IPv6 (PMIPv6) such as non-optimized communication path, long handoff latency, and bottleneck issues were inherited by SPMIPV6. An improved SPMIPv6 architecture called Distributed SPMIPv6 (DSPMIPv6) is presented in this work with the aim of addressing the aforementioned problems. The solution proffered in the present architecture includes de-coupling the entities that are part of the control and data planes; the Dynamic Mobility Access Gateway (MAG) located close to the edge of the network distributes and manages the data plane, while the control plane, is dependent on a central entity called Sensor Local Mobility Anchor (SLMA). The introduced design is evaluated analytically, and the numerical results show that the performance of the DSPMIPv6 design is better than that of both SPMIPv6 and PMIPv6 protocols in terms of Local Mobility Anchor (LMA) load, and transmission cost performance metrics.
Keywords:	Distributed mobility management, Mobility management, IP-WSN, Handover mechanism, PMIPv6, Serving DMAG (S-DMAG), Previous DMAG (P-DMAG)
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	ADVANCED AND SELF IMPROVED META HEURISTIC ALGORITHMS FOR FREQUENCY TRACKING IN OFDM SYSTEMS
Author:	DR.G.ARUL DALTON, DR.T.S.ARULANANTH, MRS. A. BAMILA VIRGIN LOUIS
Abstract:	The primary objective of this Paper is to enhance the OFDM system, the proposal has been channelized to introduce advancements in the Meta heuristic procedures for blind Carrier Frequency Offset (CFO) estimate, the purpose of this paper is defined as follows. To improve the quality of service by enhancing the OFDM systems, address the challenges reside on frequency tracking and so the impact of interference on OFDM systems. Also review various principles CFO estimation and algorithms and categorize them based on various criteria. In order to experimentally investigate the performance of various state of the art Meta heuristic search algorithms on estimating the CFO and Adopting Grey-Wolf Optimization for estimating the CFO. To investigate the self adaptive mechanisms persist in the literature that is suitable for CFO estimate process. Introduced a novel based self-adaptive mechanism for Grey Wolf Optimization and hence to propose a blind and global CFO estimate procedure. Finally to conduct an extensive comparative study under various OFDM system and channel models to demonstrate the global compatibility feature and blind estimation characteristics of the proposed CFO estimation.
Keywords:	Carrier Frequency Offset (CFO) estimate, Orthogonal Frequency Division Multiplexing (OFDM), Inter Carrier Interference (ICI), Minimum Mean Square Error (MMSE), Cramer Rao Lower Bound (CRLB), Non Blind CFO estimation, Blind CFO estimation, Alternating Projection Frequency Estimation (APFE).
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	A NOVEL FRAMEWORK FOR SERIAL PROGRAM FULLY AUTO PARALLELIZATION BASED ON OPENACC
Author:	WANG XIAORUI, JIANG HUIFANG, CAI DA
Abstract:	On the basis of OpenACC programming standard (for open accelerators), a new framework was proposed, whose name is GENerate OpenACC, or GENACC for short. GENACC can automatically accelerate the serial code. The static program of the source code are analyzed aimed to recognize the hot snippets and analyze the computation property. And finally OpenACC directives are added to the source code in order to accelerate the serial code. According to the experiments on the NPB test set, the results show that GENACC can accurately produce compiler directive, and the source codes show fine performance on different amount of data.
Keywords:	OpenACC, Auto-Parallelization, LLVM translator, Inheritance code, NPB test set
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	AN INTELLIGENT APPROACH FOR PREDICTING SOCIAL MEDIA IMPACT ON BRAND BUILDING
Author:	ALTYEB ALTAHER, AHMED HAMZA OSMAN
Abstract:	Social media networks such as Twitter and Facebook plays important roles in many aspects of our lives and affects many of our decisions. This paper presents a data mining model consists of different five classification and regression algorithms to predict the significant performance metrics of posts announced in the Facebook pages of the brands. The algorithms utilized in the model include the Generalized Liner Regression (GLR), Normal Regression (NR), support Vector Machine, Neural Network, and CHAID decision tree classifier. Using a dataset contained a 790 published posts in the cosmetic brand, the Lifetime post consumers achieved the best posts performance metrics with an average accuracy of 0.82 among all the algorithms in the proposed model, followed by the Lifetime post total reach performance metric with an average accuracy of 0.79. The findings of this research potentially help the manager's in making the right decisions regarding whether to publish a post.
Keywords:	Data Mining, Classification, Social Media, Brand Building, Performance Metrics
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	ANALYSIS EMAIL CONTENT WITH K-MEANS CLUSTERING FOR PROFILING ON POSTFIX SERVER
Author:	BAMBANG SUGIANTORO, MUSLIM HERI KISWANTO
Abstract:	Clustering email content is a way of categorization of email content based on specific criteria to obtain the category types of emails that can be used for content profiling email. There are several types and content of the email on a mail server that is not desired by the client so that if this occurs continuously will result in performance mail server will be disrupted. Email content profiling was conducted to determine patterns and behavior in the Postfix SMTP email delivery server using the K-means algorithm to know the type of email that can disrupt the performance of the mail server. The profiling process begins with taking the log file content stored on the Postfix Simple Mail Transfer Protocol (SMTP) email server and then analyze the log file using Clustering techniques with K-means algorithm for Profiling email content on Postfix-based mail server using three criteria, namely: message_id, access from and content. Email content analysis was conducted using K-Means Clustering until the 3rd iteration. The clustering results obtained from four categories of e-mail stored in the postfix mail server, that is a true email, fraud, advertising, and emails which do not have a clear purpose. The step profiling using the deductive method to the content of the email that will be obtained information about the type and characteristics of e-mail stored in the Postfix SMTP server. Using the deductive method for the profiling is the solution to assign profiles based on data obtained from the scene, in this case, is the content of the email on the SMTP Mail Server. There are 3 main things done in this deductive technique, namely: analysis of the operation mode refers to the clustering process, as a characteristic signature in email delivery and victimology identified as a victim in email delivery.
Keywords:	Profiling, Email, K-Means clustering, Postfix
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	ONLINE FAKE NEWS DETECTION ALGORITHM
Author:	SAKEENA M. SIRAJUDEEN, NUR FATIHAH A. AZMI, ADAMU I. ABUBAKAR
Abstract:	The widespread of online hoax news is increasing rapidly, especially with the vast number of Microblogging sites allowing disseminating distasteful content. This has become vigorous and nearly unstoppable now. Spreading online fake news has been identified as one of the major top concern of online abuse. Due to the difficulty in preventing and evaluating what does fake news contain prior to publishing it online, if an algorithm is known for detecting fake news, then spreading online fake news wouldn’t exist in the first place, lead this paper to presents an evaluation of the effectiveness of algorithm(s), able to detect and filter to reasonable degree of accuracy what constitute an online fake news. The proposed approach is a multi-layered evaluations technique to be built as an app, where all information read online is associated with a tag, given a description of the facts about the contain. A proof of concept is provided for better understanding of the proposed techniques. This has contributed in providing possible steps to be taken by some popular Microblogging sites to stop the widespread of fake news.
Keywords:	Online Fake News, Hoax News, Detection, Filtering
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	AN APPROACH TO THE EVOLUTION FROM AN OSPF NETWORK TO SDN
Author:	RUSLAN LEONIDOVICH SMELYANSKIY , RAMIL AIDAROVICH YANBULATOV
Abstract:	Increasing requirements to the quality of service and the dramatic growth of traffic are the main driving development factors of modern network technology. Traditional networks, such as TCP/IP networks, have a complex structure and it is difficult to control them. Thus, there is a need to shift to a higher-quality technology, such as SDN technology. With centralized network management and programmability of control units, the SDN architecture has the potential, which can reduce COPEX and OPEX, simplify the network administration and maintenance. However, replacement of the traditional networks by a new one is a long and spending process, which is also related to the lack of methodology. This paper discusses the methodology intended for the transition from a traditional OSPF/IS-IS network to a network based on SDN architecture. As a result, the authors developed greedy algorithm, which provides the stepped system for the transition from OSPF to software defined network.
Keywords:	SDN, OSPF, hybrid SDN, Incremental Deployment, Network Migration
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	A NEW APPROACH FOR MEASURING SEMANTIC SIMILARITY OF ONTOLOGY CONCEPTS USING DYNAMIC PROGRAMMING
Author:	ABDELHADI DAOUI, NOREDDINE GHERABI, ABDERRAHIM MARZOUK
Abstract:	Today, with the emergence of semantic web technologies and increasing of information quantity, searching for information based on the semantic web has become a fertile area of research. For this reason, a large number of studies are performed based on the measure of semantic similarity. Therefore, in this paper, we propose a new method of semantic similarity measuring which uses the dynamic programming to compute the semantic distance between any two concepts defined in the same hierarchy of ontology. Then, we base on this result to compute the semantic similarity. Finally, we present an experimental comparison between our method and other methods of similarity measuring. Where we will show the limits of these methods and how we avoid them with our method. This one bases on a function of weight allocation, which allows finding different rate of semantic similarity between a given concept and two other sibling concepts which is impossible using the other methods.
Keywords:	Semantic Web, Ontologies, Similarity Measuring, Dynamic Programming, Semantic Similarity, Semantic Distance.
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	AN ADVANCED REVENUE DISTRIBUTION MODEL FOR CLOUD MEDIA CONTENTS SALES WITH MULTI-DRM
Author:	YOUNGMO KIM, BYEONGCHAN PARK, EUNJI SEO, BYUNG-GI KIM, SEOK-YOON KIM
Abstract:	DRM technology to prevent illegal copying of digitized contents can control illegal copying by controlling usage of contents according to user's rights. However, options for revenue sharing were rather limited since DRM technology is dependent on the platform and uses only one technique applied by a content distributor. This problem is conspicuous in the case of contents used on multiple platforms, and inconveniences and additional costs arise due to the application of multiple DRMs.To slove this problem, this paper suggests a profit sharing model in cloud-based media service with application of multiple DRMs, in which contents providers can choose their favorate DRMs and get their share of profit after saling contents. The proposed model is more flexible than the existing models in that it can accept various profit sharing policies for each stake-holder’s interests.
Keywords:	Cloud Media Service, DRM, Copyright, Accounting Models
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	PERFORMANCE ANALYSIS OF VIDEO RETRIEVAL THROUGH IMAGE AND AUDIO FEATURE
Author:	IN-KYOUNG SHIN, HYOCHANG AHN
Abstract:	As growth of computer technology and multimedia information, not only texts but also various form of image information can be obtained and stored. Furthermore, growing hardware technology is capable to store and inquiry large size of multi data in rapid time. Traditional indexing technology was supervised by human supervisor by writing an appropriate keyword but this method is inefficient for processing large images through time factor and, indexing keyword is likely to be subjective which leads to the problem of wrong keyword. Thus the matter of context based image searching is being focused on extracting and indexing automatically from visual context of images. This paper propose a method of efficient context based image searching using a feature of face image and audio feature. Two feature vectors are extracted and weighted by similarity search method using fuzzy integration and merging techniques. Our method extracts two features, merges them, and uses similarity search as a weighting using fuzzy integral images. Objective performance accuracy and reproducibility are superior to conventional methods in experimental results with 1,000 color images.
Keywords:	Image Feature, Audio Feature, Video Retrieval, Image Retrieval, Multimedia Information
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	EFFECTIVE PAGE REPLACEMENT ALGORITHM OF HYBRIDE MEMORY
Author:	BOSUNG JUNG, SEUNGMIN LEE, JUNGHOON LEE
Abstract:	The main objective of this paper is to implement high-performance next-generation main memory by pro-posing an effective page replacement algorithm for the hybrid structure of DRAM and PCM. To replace conventional DRAM, a DRAM&PCM hybrid memory is one of the effective structures because it can uti-lize an advantage of DRAM and PCM. However, in order to use the characteristics of DRAM and PCM, pages should be replaced frequently. This is still a major problem in PCM that have write-limits. Therefore, it needs an effective page management method for exploiting each memory characteristics dynamically and adaptively. To reduce frequent page replacement, page replacement in the proposed hybrid memory is handled by two localities in PCM and recent write requests in DRAM. According to our simulation, the pro-posed algorithm for the DRAM&PCM hybrid can reduce the PCM write count by around 22% and the average access time by 31% given the same PCM size, compared with Clock-DWF algorithm
Keywords:	Hybrid Memory, Page Management, Temporal/Spatial Locality, Memory Characteristics
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	RENDERING SPEEDS OF DYNAMIC AND STATIC OBJECTS WITH TANGENT SPACE NORMAL MAPPING ON 3D GAMES
Author:	YOUNGSIK KIM
Abstract:	In 3D games, bump mapping is an efficient way to provide high-resolution bumpy lighting features in textures using only low-resolution meshes during runtime. This paper developed two 3D games based on Unity3D and Direct3D using normal mapping, which is a typical one among bump mapping methods. In particular, dynamic objects in 3D games require tangent space normal mapping, which requires much computation per vertex. The performance of dynamic and static objects with or without normal mapping in 3D games is analyzed using various screen resolutions as well as eight simulation models in terms of the rendering speed like frames per second (FPS). The rendering speeds of the models Gu and Gd on Unity3D and Direct3D based games, where using normal mapping to all objects among the eight simulation models, can be improved by up to 79.7% and 19.2%, respectively, compared with the models Bu and Bd without normal mapping. The tangent space normal mapping on both dynamic and static objects in 3D games has a large effect on rendering speed.
Keywords:	Bump Mapping, Tangent Space Normal Mapping, Rendering Speed, Frames Per Second (FPS), Direct3D, Unity3D
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	A STUDY ON BIG DATA APPLICATIONS FOR THE KOREAN DRANA INDUSTRY AT EACH STAGE OF THE VALUE CHAIN
Author:	Jun-Ho LEE, Seung-Hyeok BAEK
Abstract:	This paper aimed to explore the use of Big Data in the Korean drama industry. The paper examined the strategy of using big data for the development of the Korean drama industry. The purpose of this study was to examine exemplary cases of advanced countries in which big data is being used actively and draw conclusions on the applicability in Korea. Compared with the growth and development of Big Data, its utilization in the Korean contents industry was insufficient, and its application in the drama industry has been limited in particular. While Big Data has been hailed for its wide applicability, there have been few studies on the utilization of big data to promote the culture industry (Yoon, 2013). In foreign countries, there have already been many successful cases of using Big Data in the field of video industry, and although a few Korean cases existed, there was not a comprehensive and systematic linkage and utilization as a whole. Therefore, this paper proposed an integrated model of using big data in the contents industry by presenting integrated method of using big data centered on value chain of Korean drama industry, and proposed future development direction of Korean drama industry with big data .
Keywords:	Big Data, Drama Industry, Value Chain
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	CLASSIFICATION MODEL BASED ON URL AND CONTENT FEATURE APPROACH FOR DETECTION PHISHING WEBSITE IN INDONESIA
Author:	FEBRY EKA PURWIANTONO, ARIS TJAHYANTO
Abstract:	This research proposed a classification model that can be used to detect phishing website accurately. This study takes a case study from Indonesia because data used are sites using Bahasa Indonesia, hosted in Indonesia and frequently accessed by Internet users from Indonesia. Dataset used in this research consisted of approximately 102 authentic websites and 364 phishing websites. The proposed detection technique based on website analysis using the URL and content feature based approach. This classification model combines several heterogeneous features from previous research and proposes new URL and content feature based approach that are expected to improve detection performance when compared with previous research. Moreover, in the proposed classification model created a web crawler to extract feature vectors in this research. This research uses four different algorithms such as Sequential Minimal Optimization (SMO), Naive Bayes, Bagging and Multilayer Perceptron. The result, SMO, Naive Bayes, Bagging and Multilayer Perceptron have accuracy of approximately 89.27%, 93.78%, 95.49% and 92.70%. Algorithm has the best accuracy is Bagging, it will be used in this classification model to compare with classification model in previous research using same dataset. The result, accuracy of classification model in this research outperformed accuracy of classification model in previous research. The classification model in this research outperform 5.79% against classification model in previous research which only yielded 89.70% accuracy.
Keywords:	Classification Model, Detection, Phishing Website, Indonesia, Feature
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	SIMULTANEOUS COORDINATED TUNINGOF CES AND PSS FOR SINGLE-MACHINE USING GENETIC ALGORITHM
Author:	ENDRO WAHJONO, ONYASRARULQUDSI, DIAH SEPTI YANARATRI
Abstract:	This paper presents a new coordinated design between Power System Stabilizer (PSS) and Capacitive Energy Storage (CES) using Genetic Algorithm (GA). A GA will determines optimal parameters for PSS and CES by tuning parameters PSS and CES simultaneously. The optimization results can change the value of PSS and CES parameters which can also cause oscillation on the system. This problem is formulated as an objective function with limits consisting of damping ratio and damping factor. The approach is succesfully tested on single-machines generator models. The optimization results show that this method is effective enough to damp the oscillation, so as to give an idea of the dynamic stability of the single-machine system.
Keywords:	CES, PSS, Single-Machine, Genetic Algorithms
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	ACCURATE SEGMENTATION OF PSORIASIS DISEASES IMAGES USING K-MEANS ALGORITHM BASED ON CIELAB (LAB) COLOR SPACE
Author:	TANYA SHAKIR JARAD, ALI J. DAWOOD
Abstract:	Context: Psoriasis turned out to be one of the debilitating and enduring inflammatory skin diseases. Often misinterpreted as a casual skin disease, it is estimated that approximately 125 million people worldwide suffers due to this infection. The case is made worse when there is no known cure in the status quo. The communal category of psoriasis has been considered as abruptly demarcated scaly and erythematous plaque at patient’s skin. This disease could ensue anywhere on the human body. Problem: Diagnosis of psoriasis requires an experienced specialist in the field of dermatology because of the presence of other skin diseases similar to a large extent which lead to majority cases of an error in diagnostic. As doctors are still mere human and depends on factors such as eye and physical touch that is not error free. In addition, the drugs for psoriasis disease contain quantities of Chemical materials dangerous to other body organs that may put the functionality of critical organs such as the liver and spleen in jeopardy. Meanwhile, over-treatment leads to loss of life of the patient so it must be re-diagnosis multiple times until the confirmation of a high proportion of the dangerous disease. Time is not the greatest threat for this disease rather the accuracy of diagnosis is much crucial and the accuracy of diagnostic plays a pivotal role in combating this atrocious disease. Regular re-diagnosis is considered a must in order to ensure the survivability of patients from the threat it poses. However, re-diagnosis often consumed a great amount of financial expenditure just to ensure that it is indeed a disease of psoriasis and that the appropriate treatment is given may only lead to another issue which is a financial deficiency. Approach: In this paper, the researcher is interested in separating the image and concentrate on the lesion region and extricating disease district. The process itself is an enormous challenge in light of the fact that there is no discovery of this minute segmentation algorithms division executes and all in all dataset. The proposed strategy is based on K-Means clustering as initial segmentation and gets a divided region, including areas of diseased and the proposed K-Means based on CIE Lab Lab color spaces instead of using Red, Green and Blue (RGB) color space. Post segmentation based on color feature will be filtered out as non-interesting objects. Finding: The findings from this study have shown that: Firstly the method is depending on the Lab color spaces instead of using RGB color spaces, secondly, the method is based on color feature to select disease region of psoriasis or the correct object. The results of this research confirmed that this method works effectively where we have been implementing this method on a database containing 80 medical images of RGB psoriasis diseases image and shows the accuracy of this method was at 95% when we did a comparison between our method and other ways to find that the proposed strategy gives more effective results in the segmentation. The researcher compared accurate segmentation of K-Means cluster formation with color spaces Lab on medical imaging and K-Means cluster formation with color spaces RGB on the same images.
Keywords:	Color image segmentation, Psoriasis disease diagnosis, K-Means algorithm.
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	OPINION CLASSIFICATION OF ONLINE REVIEWS USING THE PROBABILISTIC NEURAL NETWORK AND PRINCIPAL COMPONENT ANALYSIS
Author:	A. SHANTHINI, G. VINODHINI, RM. CHANDRASEKARAN
Abstract:	Sentiment analysis of product reviews is an attracting and increasing interest in the area of natural language processing and web text mining. Objective is to analyze the effect of ANN based method for opinion classification. In the research that has done so far on sentiment analysis, ANNs have been considered rarely. In this work, the probabilistic neural network (PNN) has been examined in sentiment classification. This work also examines neural network based sentiment classification methods for feature level sentiment classification on various levels of word granularity are used as features. Product reviews collected from the Amazon reviews website are used as dataset for evaluation. Our objective is to classify the product reviews into three classes: positive, negative and neutral. The results are empirically compared with SVM using various quality measures. The superiority of PNN with Principal Component Analysis (PCA) is also shown in terms of training time. PNN is found to perform better and yields higher accuracy in prediction. In general, statistical based approaches do not perform well as that of neural network based approaches. Compared with traditional techniques, the ANN based approach shows the performance improvement in quality measures and in training time. Through the experimental results it will be show that shortening of training time and increasing the classification accuracy can be achieved by hybrid combination of PNN with PCA.
Keywords:	Opinion Mining, Classification, Principal Component Analysis, Neural Networks, Sentiment Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	CONDITIONAL INCLUSION DEPENDENCIES FOR IMPROVING XML DATA CONSISTENCY
Author:	MOHAMMED HAKAWATI, YASMIN YACOB, RAFIKHA ALIANA A. RAOF, AMIZA AMIR, JABIRY M.MOHAMMED, EYAD SAIF AL-HODIANI
Abstract:	Without any doubt, XML data model considered the most dominant document type over the web with more than 60% of the total; nevertheless, their quality is not as expected. XML integrity constraint just as its relational counterpart played an important role to keep XML dataset as consistent as possible, but their ability to solve data quality issues is still intangible. The main reason is old-fashioned data dependencies introduced mainly to keep schema consistent rather than data consistent. In this paper, a conditional version of XML inclusion dependencies (XCIND) is proposed for data quality issues and justify the ability to use inclusion dependencies for data quality issues. XCIND Notations will extend XIND and shift its mission from schema design to data quality by providing pattern tableaus. Moreover, a set of minimal XCIND dependencies will be discovered and learned using a set of mining algorithms. Finally, the ability to use XCIND to detect data inconsistencies will be inspected using denial quires between mined rules and XML tree.
Keywords:	XML, Data Quality, Data Cleaning, Integrity Constraints
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	EFFECTIVE APPROACH FOR INTRUSION DETECTION USING KSVM AND R
Author:	M. NAGA SURYA LAKSHMI, DR Y RADHIKA
Abstract:	Nowadays there is an incredible escalation of the usage of computers over various networks and application domains, which in turn increases the security threats in terms of intrusions. An intrusion may happen either internally or externally and the traditional approaches used in intrusion detection are unable to meet the requirements of preventing and detecting an intrusion. For the detection of different attacks, intrusion detection occupied important work for the maintaining of privacy and reliability in network resource. In this paper, the methodologies of Data Mining has been used for increasing the performance in the IDS, and to handle Some of the problems like data Preparation, pre-processing of the data, data classification and Intrusion detection are being solved using different techniques like Dynamic Data Preparation (DDP), Hybrid Rule-based Pre-processing, Efficient Kernel Based Support Vector Machine (EKBSVM) and Decisive Neural net using R (DNR) respectively. The proposed techniques have produced better accuracy, specification and minimized the false alarm rate (FAR).
Keywords:	Anomaly Detection, Classification, DDoS, Intrusion Detection, Misuse Detection
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	ARC FLASH IDENTIFICATION FOR SELECTION OF PERSONAL PROTECTION EQUIPMENT IN THE REAL INDUSTRIAL POWER SYSTEM USING LEVENBERG MARQUARDT BACKPROPAGATION
Author:	MARGO PUJIANTARA, ANDIKTA DWI HIRLANDA, DIMAS OKKY ANGGRIAWAN, ANANG TJAHJONO, ARDYONO PRIYADI
Abstract:	Arc flash hazard is an important concern for who works on an industrial electrical system. Arc flash hazard incident energy can lead damage to equipment and injury to workers. Therefore, arc flash identification required to determine category of personal protective equipment (PPE) based on NPFA 70E. Calculations of Arc flash hazard incident energy using numerical techniques based on IEEE std. 1584. However, the calculations just determine value of arc flash incident energy. Therefore, in this paper, proposes Levenberg Marquardt Backpropagation (LMBP) for identification of Arc flash. The proposed method applied in HESS Indonesia Corporation. In the simulation result demonstrates that the proposed method presents high accuracy in identification of arc flash for selection of PPE.
Keywords:	Arc Flash, personal protective equipment, NPFA 70E, Identification, Levenberg Marquardt Backpropagation
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	EVALUATION AND ANALYSIS OF PID AND FUZZY CONTROL FOR AUV-YAW CONTROL
Author:	MOHD SHAHRIEEL MOHD ARAS, BOON PEI TEOW, AI KEE TEOH, PEI KEE LEE, ANUAR MOHAMED KASSIM, MOHAMAD HANIFF HARUN, MOHD KHAIRI MOHD ZAMBRI, 5ALIAS KHAMIS
Abstract:	This paper presents the comparison and performances analysis between Proportional Integral Derivative (PID) Controller and Fuzzy Logic Controller (FLC) designs for yaw control of an Autonomous Underwater Vehicles (AUVs). PID controller is easy to be implemented as PID parameter can be obtained based on the software used and it’s can be achieved, precisely. Moreover, the PID parameter can be acquired based on tracking error and treats the system to be “blackbox” if the system parameter is unknown. However, the designed PID controller may not resist the uncertainties and disturbances. Hence, FLC design had been implemented to improve the performances of AUV-yaw control using heuristic approach until the satisfactory results are obtained. It is necessary to tuning the rules and the range of membership functions in order to get the desired output and improve the system response. The aim of this work is to analysis the performances between PID and FLC for AUV yaw control. Simulation are done in MATLAB/Simulink, using Fuzzy Logic Toolbox and Simulink block. The differences tuning process of PID and FLC are demonstrated and analyzed. The results of simulation shows the implementation of FLC improved the performance of the system response in terms of overshoot and rise time.
Keywords:	Proportional Integral Derivative; Fuzzy Logic Controller; Autonomous Underwater Vehicle; Yaw control
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	THE USER ACCEPTANCE FACTORS OF E-FILING SYSTEM IN PONTIANAK
Author:	FARAH DEVI ANDRIANI, TOGAR ALAM NAPITUPULU, SRI HARYANINGSIH
Abstract:	The application of information technology (IT) within an organization is necessity of globalization. Nowadays, governments try to develop public service system based on e-commerce called e-government. One of e-government which is currently being introduced to the public is e-Filing system for filing tax report. However, until now we do not know why a lot of people still do not adopt the e-Filing system. The purpose of writing this research study is to analyze factors that influence user acceptance of the e-Filing system. This is done by evaluating user acceptance based on human behavior theory towards the use of information systems. The research is based on a combination of UTAUT and IS Success Model. The data collected was from distributing questionnaires to 394 respondents of e-Filing users in Pontianak. All data were analyzed using Structural Equation Modeling (SEM) with SPSS AMOS 22. The test results of this research found that factors influence user acceptance of e-Filing system in Pontianak are Information Quality (IQ), Service Quality (SQ) and System Quality (SYQ), Use Behavior (UB), User Satisfaction (US) and Behavior Intention.
Keywords:	User Acceptance, e-Filing, Structural Equation Model
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	AN INTELLIGENT NETWORK INTRUSION DETCETION SYSTEM USING DATA MINING AND KNOWLEDGE BASED SYSTEM
Author:	ALEBACHEW CHICHE, MILLION MESHESHA
Abstract:	In this study, an intelligent network intrusion detection and prevention system is presented for detecting network attacks that incorporates a knowledge based system and data mining techniques. To extract hidden knowledge from KDDCup’99 dataset, hybrid data mining process is used. The intrusion dataset for the study is collected from MIT Lincon lab. A predictive model is constructed on total datasets of 63, 661 instances using JRip rule induction, Naïve Bayes,J48 decision tree and Multilayer Perceptron (MLP) Neural Network. During training 99.91% prediction accuracy is achieved by J48 decision tree. So, the J48 model is integrated with knowledge based system automatically for designing intelligent network intrusion detection and prevention system. In addition, knowledge is acquired, represented and organized in the knowledge based so as to suggest possible prevention for detected attacks. Evaluation results show that the proposed system registers 91.43% accuracy in network intrusion detection and 85% in user acceptance testing. This indicates that the performance of the proposed system is promising to design an intelligent network intrusion detection system that can effectively predict and provide a prevention mechanism. The system cannot update the knowledge of prevention techniques automatically which need further researches.
Keywords:	Network Intrusion Detection, Intrusion Prevention, Data Mining, Knowledge Based System
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	A RELIABLE IN-BAND CONTROL IN A SOFTWARE-DEFINED NETWORK
Author:	ANATOLY S. KHAKHALIN , EVGENY V. CHEMERITSKIY
Abstract:	The development of wireless communication technologies has made it so the number of people who use them has surpassed the number of users of landlines. This causes malfunctions in and slow operation of networks. Software-defined networks separate data-forwarding processes from networking and communication processes – such networks allow for a significant reduction in the number of protocols used to improve the controllability of the network. This research investigates a method for establishing a reliable network connection, which will maintain the operability of the network in the presence of at least one route between switches, regardless of the number of failures. This study describes two methods of failsafe route generation – Non-return routes and Return routes. The paper provides a flowchart that shows the conditions that allow maintaining a connection to the switch. The proposed algorithm supports the OpenFlow protocol. In addition, the study established the rules that the controller sets for each separate switch. This method improves the fail-safety of the network and ensures its uninterrupted operation.
Keywords:	Computer network, Forwarding plane, Network security, OpenFlow protocol
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	GREEN SD ADOPTION USING KNOWLEDGE MANGEMENT FACILITATION – A MOTIVATIONAL PERSPECTIVE
Author:	MCXIN TEE, RUSLI ABDULLAH, JAMILAH DIN, SALFARINA ABDULLAH, LIMING WU
Abstract:	Attention on green computing has been growing in this decade. Green computing is generally a large field of study which is concerning study of related environmental issues on information technology (IT) and computer science relevant systems, datacenters, hardware, networks, processes, software, and architectures. Several existing researcher papers have concentrated on studying motivating factors of green computing adoption. A few of them have discovered tools to facilitate the green computing adoption. However, green computing is still a broad discipline of study. There is a need for empirical research that narrows down this field of study. Thus, this paper empirically and specifically studies on motivating factors that influencing the Green Software Development (Green SD) adoption by using Knowledge Management (KM) as facilitation tool. Green SD is one of the in-depth research topics in the broad discipline of green computing. Drawing from existing literature and using data collected from a quantitative survey of 107 software practitioners, this paper analyzed five hypotheses. PLS-SEM method was used to validate the proposed framework of this research paper, by following standard two-steps approach for PLS-SEM analysis: measurement model analysis and structural model analysis. The result shows that only ethical motivation is the significant motivating factor influences Green SD adoption among software practitioners. This paper proves that intention of software practitioners to develop nature-friendly software products is driven by their environmental concerns, sense of care and responsibility to our natural environment. Outcomes of this paper will help in enhancing researchers’ understanding on Green SD adoption and will also be valuable for diverse stakeholders who are interested in encouraging Green SD adoption. SD organizations and top management need to properly utilize their workers’ morale and concern on ecological issues for identifying green innovation and green initiatives. Theoretical and practical contributions are discussed in this paper.
Keywords:	Green Software Development, Adoption, Motivating Factor, Intention, Ecological Sustainability
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	SPECTRAL ENERGY BASED VOICE ACTIVITY DETECTION FOR REAL-TIME VOICE INTERFACE
Author:	JEONG-SIK PARK, JUNG-SEOK YOON, YONG-HO SEO, GIL-JIN JANG
Abstract:	Voice activity detection (VAD) is a main process of speech recognition tasks in which every voice region is detected to extract acoustic feature parameters from the region. This paper proposes an efficient VAD approach for applying to real-time voice interface systems. Even though diverse VAD approaches have been successfully applied for speech applications, they may operate inefficiently according to environmental conditions. In this study, we attempt to enhance the conventional VAD method based on signal energy within time and spectral domain. In addition, an efficient end-point detection method is also proposed. We successfully verified the efficiency of the proposed approach via a set of VAD experiments, comparing with the performance of some conventional VAD methods including zero crossing rate.
Keywords:	Voice Activity Detection, End-point Detection, Voice Interface, Spectral Domain, Spectral Energy
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	COLOR DETECTION USING GAUSSIAN MIXTURE MODEL
Author:	DONG KEUN KIM
Abstract:	In this paper, we propose a method for color region detection in color images and videos. It is based on Gaussian mixture model (GMM) which is calculated by the expectation-maximization (EM) algorithm. We assume that we know the number of Gaussian components in the reference image, but we do not know it in input images. The proposed our approach is composed of two steps. We first estimate GMM parameters using EM algorithm over a reference image including colors regions of interest (ROI). To construct 2-dimensional GMM in the reference, we consider two chrominance features, CbCr-channel from YCbCr color model. The second step is to detect and segment the color regions by using GMM parameters in input images. We decide the color regions by the posterior probability which is Gaussian distributions calculated by GMM in the reference image. Our method can only detect and segment the colors ROI including the Gaussian components from the input image. The experimental results show that it is very effective to detect the predefined multi-colored regions in images and videos.
Keywords:	Gaussian mixture model (GMM), expectation maximization (EM), YCbCr color model, Color region detection, Segmentation
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	SEGMENTATION METHODS FOR A GROUP-HOUSED PIG MONITORING SYSTEM
Author:	MISO JU, YEONWOO CHUNG, HANSOL BAEK, YONGWHA CHUNG, DAIHEE PARK, BYUNGKWAN PARK
Abstract:	The analysis of individual pig behavior in group-housed pigs is important for pig management. In this study, we propose two low-level segmentation methods for group-housed pigs to facilitate the video-based high-level analysis of pig behavior. In a 24-hour pig room monitoring environment where no pig is allowed to enter/leave the room during the monitored period, the previous video frame has sufficient information for separating touching-pigs in the current video frame. In this paper, we propose two methods to separate touching-pigs using the information of the previous video frame and a hybrid method for combining the segmentation results of each method. According to experimental results with the Korean pig farm data, the proposed segmentation methods based on the labeled outline/region information can provide more accurate results than widely used methods.
Keywords:	Group-Housed Pigs, Pig Management, Video-based Pig Monitoring, Image Processing, Segmentation
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

Title:	THE EFFECTS OF THE COMPUTATIONAL THINKING-BASED PROGRAMMING CLASS ON THE COMPUTER LEARNING ATTITUDE OF NON-MAJOR STUDENTS IN THE TEACHER TRAINING COLLEGE
Author:	YONGJU JEON, TAEYOUNG KIM
Abstract:	In these days, the software-integrated education is considered very important in both K-12 and undergraduate education. However, negative attitudes about software learning, such as lack of confidence caused by insufficient educational opportunities about computational thinking-based programming experience, could be a barrier to try software-integrated education for the non-majors in college. Unfortunately, only ICT skill-based education is provided for undergraduate students of the teacher training college in Korea, and we cannot find courses on computational thinking-based programming education in the university curriculum of liberal arts. Thus in this study, we developed a computational thinking-based programming course applicable to the liberal arts of the non-major education. Then we performed our experiment to both a controlled group with the traditional ICT skill-based course and an experimental group with our computational thinking-based programming course, and the paired samples t-tests were carried out. As a statistical result, the mean score of the experimental group is significantly higher on the most area of computer learning attitude. Thus, we concluded that the computational thinking-based programming class is more significant to foster affective elements of computer learning attitude such as superiority, self-confidence, interest, sense of purpose, accomplishment motivation and knowledge application than those of the traditional ICT skill-based class.
Keywords:	Computational Thinking Education, Computer Learning Attitude, Software-Integrated Education
Source:	Journal of Theoretical and Applied Information Technology 15^th September 2017 -- Vol. 95. No. 17 -- 2017
Full Text

dew