		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
December 2016 | Vol. 94 No.1

Title:	SOFTWARE CONFIGURATION MANAGEMENT PRACTICE IN MALAYSIA
Author:	SYAHRUL FAHMY, AZIZ DERAMAN, JAMAIAH H. YAHAYA
Abstract:	This study investigates the practice of Software Configuration Management (SCM) in Malaysia. A survey was carried out involving three types of software organizations namely the Government, IT Companies and Institutes of Higher Learning to identify the approach for SCM implementation the aspects of: Process, People and Documentation. Results revealed that Malaysian organizations are adopting key SCM Process where versioning of artifacts and releasing of baselines are highly exercised; policy and procedures for change control exist; audits are carried out periodically; and software libraries are used in software projects. In terms of tools, commercial tools are dominantly used which include Serena Dimensions, Borland Calibre and Oracle Discoverer. Documentation efforts are carried out comprising of internal and external conformances; software quality factors; controlled artifacts; and audit results. Main project reports generated include software development, audits and change requests. Among the issues observed are the exclusion of some artifacts as controlled artifacts; the lack of effort to document software quality evaluation techniques; and little effort to include SCM and software quality documentations in software delivery.
Keywords:	Software Engineering, Software Configuration Management, Software Quality
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	INTEGRATION OF EFQM EXCELLENCE MODEL AND INFORMATION SYSTEMS CRITERION
Author:	ROSLI ISMAIL, MASRAH AZRIFAH AZMI MURAD, MARZANAH A. JABAR, ROZI NOR HAIZAN NOR, NORWATI MUSTAPHA
Abstract:	Higher Education Institutions (HEIs) have become key institutions in the knowledge-based economy. Over the past decade, the Malaysian government has placed greater emphasis on improved efficiency and productivity in the HEI as an engine for promoting quality human capital for a knowledge-based economy. Importantly, the government raised the share of research and development in GDP from 1.5% in the Eighth Malaysia Plan (2000–2005) to 4.9% in the Ninth Malaysia Plan (2006–2010) for HEIs. As a result, there is a need to monitor the quality performance of HEIs to see if the government’s objectives are being met. The European Foundation for Quality Management (EFQM) excellence model was introduced at the beginning of 1992 as the framework for assessing organizations for the European Quality Award. In fact, this model has been claimed to be the most widely used model of the national excellence awards in the European countries. However, it does not have Information Systems (IS) as a single criterion. The purpose of this paper is to evaluate the interrelationships between the EFQM excellence model and information systems criterion of Malcolm Baldrige National Quality Award (MBNQA) model in the HEIs of Malaysia. The paper identified ten (10) criteria from the research model: leadership; policy and strategy; people; partnership and resources; information systems; processes; people results; student results; society results and key performance results. We obtained 118 valid responses from person in charge of quality management in Malaysian HEIs. Structural equation model (SEM) is used to analyse the data and results indicate that the relationships among the research model followed the Information Systems-Quality Management theory and TQM theory.
Keywords:	EFQM, MBNQA, Quality model, Information systems
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	FEATURE SELECTION IN INTRUSION DETECTION, STATE OF THE ART: A REVIEW
Author:	HELMI B MD RAIS, TAHIR MEHMOOD
Abstract:	With the increase of internet usage the need of security for organizations network also increased. Network anomaly intrusion detection systems are designed to monitor abnormal activity in the network. These systems find the behavior that is deviated from the normal behavior. Network anomaly detection methods are implemented using different approaches including machine learning, data mining, and many more. However, intrusion detection systems highly depend on the features of the input data. These input features give information to the learning algorithms which used in intrusion detection system in the form of the detection method. With irrelevant and redundant features learning algorithm builds detection model with less accuracy rate. Also, ambiguous features increase the time complexity and consume other computational resources as well. By removing these irrelevant and redundant features accuracy of the learning algorithms can be increased. In this paper implementation of different feature selection techniques have been reviewed. Novel feature selection techniques have been developed due to its importance in network intrusion domain. We have discussed some of it in a technical aspect. These techniques are being discussed in detail. Moreover, features from these methods are also given and their results are being. We categorized these techniques according to their implementation. Different comparison of these techniques have been given and been discussed. Moreover, the benchmark dataset that is KDD99 widely used for anomaly detection is also discussed in this paper.
Keywords:	Intrusion Detection System, Intrusion Detection Methods, Feature Selection, KDD99
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	AN IMAGE STEGANOGRAPHY ALGORITHM BASED ON LOGICAL CONNECTIVE
Author:	SITI DHALILA MOHD SATAR, NAZIRAH ABD HAMID, FATIMAH GHAZALI, ROSLINDA MUDA, MOHAMAD AFENDEE MOHAMED
Abstract:	In cloud computing, steganography can be employed as one of the solutions that is mainly used to protect transmitted data from any security breaches. Most of the existing steganography algorithms cannot embed a high capacity of secret message. The aim of this study is to show that the proposed algorithm can embed a high capacity of secret message without noticeable distortion to the images. The proposed algorithm is used Logical Connective to calculate a new binary number of secret message. From the experiments that have been conducted, the largest numbers of characters that can be hidden into and retrieved from the image are 32,763 characters with 55.92 PSNR value. This PSNR value can be considered as a good value, which means that the proposed algorithm can hide a high capacity of secret messages underneath the image with near-zero distortion. Hence this new steganography algorithm is very efficient to hide secret messages inside an image.
Keywords:	Image Steganography, Least Significant Bit (LSB), Logical Connective Algorithm, Cloud Computing, Information Security
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	INTERNET OF THINGS: ISSUES AND CHALLENGES
Author:	YASEEN ABDULLAH ABDULRAHMAN, MASSILA KAMALRUDIN, SAFIAH SIDEK, MAHADI ABU HASSAN
Abstract:	Substantial research attention has been paid to the Internet of Things (hereafter abbreviated to IoT) since the dawn of the new millennium. IoT is very much perceived as being a major component of the Internet of the future. The composition of the Internet of the future will be billions of intelligent things that communicate through a variety of connected devices and it will become a means of enabling the realization of new capabilities of the ‘things’ that are connected. This paper presents a review of the related research relating to IoT. Further, issues associated with IoT particularly standardisation, security and privacy are also discussed. The discussion provides valuable information for future research in IoT.
Keywords:	Internet of Things, RFID, Security, Privacy, Data Protection
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	ARIMA METHOD WITH THE SOFTWARE MINITAB AND EVIEWS TO FORECAST INFLATION IN SEMARANG INDONESIA
Author:	WARDONO, ARIEF AGOESTANTO, SITI ROSIDAH
Abstract:	Inflation is one of the indicators to see the economic stability of a region. The value of inflation in Semarang district on January 2014 - April 2016 unstable. Inflation which unstable will impede the economic development in Semarang district, therefore need to be undertaken against the value of the modeling inflation in the future with a method of ARIMA. The purpose of this study is to find a model ARIMA which appropriate to forecasting inflation in Semarang district and to know the forecasting inflation in Semarang district on May 2016 - April 2017 using Minitab and Eviews software. Minitab and Eviews are two statistical packages programs that both can be used to analyze the time series data. The next, the authors wanted to know which of these programs is more accurate than the other in estimating the value of inflation. The methods used in this study is a literature method i.e. authors collect, select and analyze readings related to the issues examined and methods documentation i.e. the author collected data in inflation on January 2010 - April 2016 in Semarang district. Based on the research obtained, the model appropriate to forecasting inflation in Semarang district is a model ARMA(2,1) or ARIMA(2,0,1). The results of the forecasting inflation at Semarang district using Minitab and Eviews software on May 2016 – April 2017 is stable enough. The best model to foresee the next period is ARMA(2,1) or ARIMA(2,0,1) model with software Eviews namely with the following equation : Z_t=1,3551Z_(t-1)-0,5756Z_(t-2)+a_t-0,9789a_(t-1). The highest inflation occurred on September, October, and November 2016 and lowest Inflation occurred on May and June 2016.
Keywords:	ARIMA, Minitab, Eviews, Forecast, Inflation
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	HETEROGENEOUS FEATURE SELECTION FOR CLASSIFICATION OF CUSTOMER LOYALTY FAST MOVING CONSUMER GOODS (CASE STUDY: INSTANT NOODLE)
Author:	HENI SULISTIANI, ARIS TJAHYANTO
Abstract:	In the face of ASEAN open market, the actors (Fast Moving Consumer Goods industry) must increasingly explore patterns of business development because of tough competition and challenges in the market. One of strategy for surviving in high competition is retain the customer loyalty. The data were usually obtained from various sources and contains heterogeneous features, such as numerical and non-numerical features. The datasets with heterogeneous features can affect feature selection results that are not appropriate because of the difficulty of evaluating heterogeneous features concurrently. In this paper, we propose a method that combine the features transformation and subset selection based on mutual information to obtain feature subset that able to improve performance classification algorithm. Analysis comparative among before feature subset selection, dynamic mutual information (DMI) methods, p-value methods and researcher estimate were also done. Feature transformation (FT) is another way to handle the selection of heterogeneous features. The datasets were obtained from the survey of customers fast moving consumer goods, with a total of 386 respondents. By applying unsupervised feature transformation and dynamic mutual information methods, can be known the relevant features that affected the performance of decision tree algorithm. The accuracy and F-measure increased of the DMI- unsupervised-feature-transformation compared to all features (without features subset selection), p-value methods and manual features subset selection. The accuracy and F-measure for DMI-unsupervised-feature transformation are 76.68% and 73.5% respectively.
Keywords:	Classification, Customer Loyalty, Decision Tree, Feature Transformation, Mutual Information
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	DETECTION OF RING ARTIFACTS IN COMPUTED TOMOGRAPHIC IMAGES
Author:	MOHAMED ELOTMANI, ABDELMAJID ELMOUTAOUAKKIL, FRANCOISE PEYRIN, MUSTAPHA AGNAOU
Abstract:	In X-ray Computed Tomography, ring artifacts can be caused by imperfect elements in a detector or also by defects or impurities in the scintillator’s crystals. The artifacts appear on Computed Tomographic images as concentric rings superimposed on the images of the structures being scanned. The presence of such artifacts significantly complicates the post processing techniques such as noise reduction, binarization, or segmentation of image information. The efficacy of these techniques depends on the consistency of the method of classification and detection of ring artifacts. In this paper we present a simple, fast and efficient method to detect ring artifacts on Computed Tomographic images in the Polar domain.
Keywords:	Computed Tomography, Ring Artifact, Strip Artifact, Polar Coordinates, Post processing.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	ANALYSIS OF TWO DIMENSIONAL WAVELENGTH/TIME FCC-MDW CODE IN OPTICAL CDMA SYSTEM
Author:	NUI DIN KERAF, SYED ALWEE ALJUNID, PHAKLEN EHKAN, ANUAR MAT SAFAR
Abstract:	The performance of the incoherent OCDMA system is affected by the multiple access interference (MAI) as well as the phase induced intensity noise (PIIN). A new code structure of the two-dimensional (2-D) code family for OCDMA network system employs the wavelength/time (W/T) coding technique is proposed. By utilizing good cross-correlation properties from both one dimensional (1-D) Flexible Cross Correlation (FCC) and 1-D Modified Double Weight (MDW) codes, this new proposed hybrid code effectively suppresses the PIIN and eliminate MAI. The values of BER have been used to analyze and evaluate the performance of the system based on different data rates (1Gbps and 2.5Gbps). The analysis deliberates the influence of data rates over the number of simultaneous users and effective power. It was found that the increasing of data rates will degrade the quality of the decoded signal due to the rise of the MAI. The numerical results reveal that the performance of the proposed system can be enhanced and support much more simultaneous users compared to 2-D Perfect Difference (PD) and 2-D Diluted Perfect Difference (DPD) codes. In fact, the cardinality of the proposed code indicates the improvements of more than twice as compared to the 2-D PD code. Additionally, the code flexibility of this proposed system also been analyzed. It demonstrates the number of timing chip, N significantly plays a major role in the improvement of performance and the cardinality of the system. The results presented here reveals the importance of data rates and code flexibility in optimizing the system performance.
Keywords:	Optical Code Division Multiple Access, Modified Double Weight, Flexible Cross Correlation
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	LIBYAN VEHICLE PLATE RECOGNITION USING REGION-BASED FEATURES AND PROBABILISTIC NEURAL NETWORK
Author:	KHADIJA AHMAD JABAR MOHAMMAD FAIDZUL NASRUDIN
Abstract:	Automatic License Plate Recognition (ALPR) has wide range of commercial applications such as finding stolen cars, controlling access to car parks and gathering traffic flow statistics. Existing Libyan License Plate Recognition (LLPR) methods are not presented promising results due to their inefficient features for the extracted characters and numbers. In this work, an improved LLPR method is presented. The method is composed of five stages: pre-processing, license plate extraction, character and numbers segmentation, feature extraction and license plate recognition. In the pre-processing, undesired data, such as background noises are removed. Then, the license plate is extracted using few mathematical morphologies, Connected Component Analysis (CCA) and Region of Interest (ROI) extraction. After that, characters and numbers from the image regions of the license plate are extracted. A combination of geometrical features and Gabor features are considered to represent each of the character and word in the plates. Then, the recognition is done by using a template matching and a Probabilistic Neural Network (PNN) classification. The performance of the proposed method is evaluated and tested using 100 self-collected images of Libyan national license plates. The experimental results have shown that the proposed method has produced promising results and superior than other existing methods.
Keywords:	Automatic license plate recognition, Image processing, Feature extraction, Probabilistic Neural network.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	TH-HPG: THRESHOLD BASED HELLO PACKET GENERATION SCHEME FOR INTRA WIRELESS BODY AREA NETWORKS
Author:	BEENISH ABBAS , DR. KAMALRULNIZAM ABU BAKAR, DR. ISMAIL FAUZI ISNIN
Abstract:	Sensor Nodes (SNs) in Wireless Body Area Network (WBAN) sense and forward data towards Body Network Coordinator (BNC). Sensed data in WBAN contains information related to human physiological signals and vital signs. Other than sensed data, control packets are also forwarded among Senosr Nodes (SNs) and commonly known as Hello packets which announce the status of SN to its Neighbor Nodes (NNs) in the network. Updated Hello packets are required to forward latest information about SNs in the network. However, reduced number of Hello packets is the necessity as control packets generate overhead traffic in the network. The proposed, Threshold based Hello Packet Generation (TH-HPG) scheme produces reduced number of Hello packets and announces the availability of SN with updated status information. Performance analysis of TH-HPG scheme with state-of-the-art schemes demonstrate the better performance in terms of energy consumption and number of control packets generated (control overhead).
Keywords:	WBAN, Control packets, BNC, QoS, Congestion
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	ELECTRONIC WORD OF MOUTH (E-WOM): A PATH TO BUILD THE IMAGE OF UNIVERSITY
Author:	DAMAYANTI, APOL PRIBADI SUBRIADI
Abstract:	Globalization in higher education has a direct impact on competition among universities in Indonesia which become keener. The competition has not been only within universities in the country but also with universities from other countries. This keener competition has motivated each university to improve its quality continuously, so that they could survive and winning the competition. Furthermore, there was a universities ranking that standardized and recognized internationally, such as; Webometrics Ranking of World Universities, which was based in Spain. Webometric was a system that provided an assessment of all universities in the world through the university's website assessment. Meanwhile, the progressiveness of Internet Technology has made the spread of word of mouth (WOM) was not limited to directly face-to-face communication, but already in the form of electronic word of mouth (e-WOM). E-WOM has become a phenomenon that was essentially improving the image of organization especially in the context of Webometric measurement. This study aimed to identify and analyze the influence of someone’s motivation who engaged in e-WOM by using organization’s websites to enhance the image by exploiting the reputation and Webometric ranking.The research object was Sepuluh Nopember Institute of Technology (ITS), one of the largest University at Indonesia. Data was collected through the questionnaire to the academics community. This quantitative research engaging Partial Least Square (PLS) and enhancing with qualitative assessment. The results showed that there were significant correlation between factors of e-WOM towards improving the image of organization for reputation and webometric ranking.
Keywords:	Electronic Word of Mouth, Webometric, Image of Organization
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	MODEL OF SECURITY LEVEL CLASSIFICATION FOR DATA IN HYBRID CLOUD COMPUTING
Author:	MOHANAAD SHAKIR, ASMIDAR ABUBAKAR, YOUNUS YOUSOFF, MOHAMMED WASEEM, MOSTAFA AL-EMRAN
Abstract:	Organizations mainly rely on data and the mechanism of dealing with that data on cloud computing. Data in an organization has multi security levels, which is classified depending on nature of the data, and the impact of data on the organization. The security procedures which used for protecting data usually be complicated, and it had a direct and indirect influence on the usability level. This study aims to establish a model which has an ability to classify data dynamically according to the security form low till high levels. The security level classified it into five levels based on the policies and classification method. The purpose of classification is to apply a complex security procedure on data which has a high security level larger than data which has a low security level. It also has a potential to segregation an illegal data from the legal to support usability in system. Finally, several experiments have been conducted to evaluate the proposed approaches. Several experiments have been performed to empirically evaluate two feature selection methods (Chi-square (χ2), information gain (IG)) and five classification methods (decision tree classifier, Support Vector Machine (SVM), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) and meta-classifier combination) for Legal Documents Filtering The results show that all classifiers perform better with the information gain feature selection methods than their results with Chi-Square feature selection method. Results also show that Support Vector Machine (SVM) outperforms achieve the best results among all individual classifiers. However, the proposed meta-classifiers method achieves the best results among all classification approaches.
Keywords:	Information System Security, Classification Of Data, Big Data, Neural Language Processing
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	A NOVEL PHOTOPLETHYSMOGRAPH SENSOR PROBE DESIGN FOR MOTION ARTIFACT DETECTION: A COMPARISON STUDY WITH THREE AXIS ACCELEROMETER
Author:	MUHIDEEN ABBAS HASAN, FAHMI SAMSURI, KOK BENG GAN
Abstract:	Photoplethysmography (PPG) sensors have become widespread in most of the healthcare categories; its drawback is unreliable during non-stationary states. Adaptive noise cancellation is one of the several techniques have existed to address this issue. The problem of implementing this method still lacks for total detection of induced noise due to the motion. In this work, a new method was introduced for noise detection based on novel PPG sensor probe design by adding a covered photodetector (CPD) as a motion artifact reflector, in addition to the main photodetector (MPD). Experiments of several motion kinds were executed to the tied (CPD) with the accelerometer. Data analysis for the collected signals showed a lengthy convergence between the amplitude fluctuations in the time domain. The CPD precisely indicated all the fundamental frequencies of various induced noise, unlike the accelerometer. Using these photodetectors, the CPD as noise reflector and the MPD to track the contaminated PPG signal is more reliability than other approaches. Implementing this method ensures a high-level accuracy and reducing the cost of repeated false examinations. Furthermore, simple software computation and low power consumption. Practical application of this study will be presented in our next work.
Keywords:	Photoplethysmograph, Motion Artifacts, Accelerometer, CPD, MPD
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	PROCESS-ORIENTED BUSINESS ARCHITECTURE FOR A CONSCIOUS DECISION MAKING BASED ON USERS’ INTERESTS
Author:	RHIZLANE SELTANI, NOURA AKNIN, SOUAD AMJAD, KAMAL EDDINE EL KADIRI
Abstract:	Since the appearance of the web 2.0, several new concepts have emerged like social networks which generate big data, characterized by a difficult treatment using traditional administration tools. Though, they represent a rich resource of information that we can use as the basis for decisions to help managers which are always complaining about the time taken to get answers to questions in order to make decisions, and also about the quality of these decisions. In the decision-making task, the most important besides treating the data, especially big data, is to analyze and interpret the results of the treatment in a way to maximize the profit in terms of business management logic. So, we propose in this paper a process-oriented business architecture, founded on users’ interests, by analyzing tweets as an example of big data, for decision-making purposes, dealing with the practical functions of text mining. The business orientation of the analysis helps us to get conscious decisions which are more significant and closely adequate to the needs of the enterprise.
Keywords:	Decision Making, Big Data, Data Analysis, Process-oriented, Correlation
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	TEST SUITE MINIMIZATION AND EMPIRICAL ANALYSIS OF OPTIMIZATION ALGORITHMS
Author:	SRIVIDHYA. J, DR. R. GUNASUNDARI
Abstract:	Test suite minimization approaches attempt to minimize the huge number of test suites, time and cost. Some of the methods are additionally considered for reusing the test suites at the time of software maintenance which is done by avoiding the redundant test suites from available test suites. Main drawback of these methods are time consuming processes which directs to fault software testing process. The previous studies have presented that in sometime this test suite minimization process reduction is severe. This paper presents three different kinds of test suite minimization approaches such as Gravitational Bee Search Algorithm with Fuzzy Logic (GCSAFL), Non-dominated Sorting Genetic Algorithm (NSGAII) and Ant Colony Optimization (ACO) with Particle Swarm Optimization (PSO). These approaches initially investigate the minimization process and then shows the comparison results in terms of efficiency, time, cost, path coverage, and fault coverage. The experimental results show that a combination of algorithms presents the better results.
Keywords:	Test Suite Minimization, Gravitational Bee Search Algorithm with Fuzzy Logic (GCSAFL), Non-dominated Sorting Genetic Algorithm (NSGAII), Ant Colony Optimization (ACO) with Particle Swarm Optimization (PSO).
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	CONTENT BASED IMAGE RETRIEVAL USING MULTI REGION FEATURES
Author:	TALLURI. SUNIL KUMAR, T.V.RAJINIKANTH, B. ESWARA REDDY
Abstract:	In this paper an integrated method that brings together the image features form color, shape and texture is proposed for content based image retrieval (CBIR). The present paper converts the color image in to HSV color space and derives color histograms. The V color space of the image is divided into non over-lapping region of size 9x9. Each region is sub divided into nine non overlapped sub-regions and a feature vector is derived on each sub region. These feature vectors of each sub region compresses the 9x9 multi-region into 3x3. To derive shape feature, textons are computed on each 2x2 grid and the image is converted into “multi region texton matrix” (MRTM). The gray level co-occurrence matrix (GLCM) features are derived on MRTM and the image retrieval is performed on five categories of Wang database images by combining color histograms and the GLCM features of MRTM. The proposed method of CBIR is compared with GLCM and texton co-occurrence method (TCM) and results indicates the efficacy of the proposed method.
Keywords:	Texton, HSV, GLCM features, sub regions
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	RELEVANCE FEEDBACK BAYESIAN NETWORK IMAGE RETRIEVAL BASED ON SIFT- MODIFIED LBP BOF
Author:	B. SATISH, SUPREETHI K. P
Abstract:	The interest on content based image retrieval studies and researches has increased in the last decades as there is a need to maintain huge visual and multimedia databases in all computer applications. The retrieval of images from the datasets rely on the analysis of automatically- derived feature attributes such as color, texture and shape. Generally visual attributes of each feature data are smaller in size, it requires a descriptor for organizing and searching the relevant information or content from it. Scale Invariant Feature Transform (SIFT) and Local Binary Pattern (LBP) are the frequently used efficient visual descriptor helps in improving the retrieval of image even in case of noisy backgrounds. In this system, a Relevance Feedback Bayesian network is introduced in SIFT- modified LBP descriptor to improve the accuracy of image retrieval with the representation of neighbor pixel discrimination. It works on the basis of distribution of several viewpoints in the Bag of features (BoF) and provides better image retrieval.
Keywords:	Bag of features (BoF), Content-based image retrieval (CBIR), Local Binary Pattern (LBP), modified LBP (mLBP), Scale Invariant Feature Transform (SIFT).
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	TOPIC MODELING AND SENTIMENT ANALYSIS IN FACEBOOK TO ENHANCE STUDENTS’ LEARNING
Author:	TAOUFIQ ZARRA, RADDOUANE CHIHEB, RDOUAN FAIZI, ABDELLATIF EL AFIA
Abstract:	Information and communication technologies (ICT) have changed our daily lives and have particularly influenced the field of education, revolutionizing the means of teaching and learning. This article focuses mainly on the blended learning, whose on-site, lessons are devoted to the essential matter offered to the learners; and the ICT are used for a deep learning. We will use the collective intelligence that is shared on social websites such as Facebook in order to create learning groups. To make this objective possible, we will base our work on the generative probabilistic model of Latent Dirichlet Allocation. We will use this model on all the discussions shared between learners and between learners and teachers to classify students according to the topics and the difficulties that each one of them has expressed; in order to help the teachers build new knowledge on the degree of assimilation of students
Keywords:	Sentiment analysis, Latent Dirichlet Allocation, Learning, Facebook
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	MODELING FRAMEWORK FOR INTERMODAL DRY PORT BASED HINTERLAND LOGISTICS SYSTEM
Author:	LAAZIZ EL HASSAN
Abstract:	Intermodal transportation has known a great development during last decades as consequence to the development of container transportation services but also because of its sustainability advantages. The development of gateways infrastructures (ports, air ports) but also the extension of gateway concept to dry ports leads to the development of hinterland logistics networks that requires efforts and researches to optimize the design and the configuration of both their infrastructures and their services. The design, configuration and the service network design of a system(network) performing hinterland logistics, obeys to the same objectives as for a transportation and /or distribution network but could differ because of either its specific structure, cost function and/or specific constraints related to the actors points of view. To be cost effective and mitigate the negative environmental and human health effects of distribution operations of road mode, hinterland freight logistics systems should be intermodal by integrating more and more rail and land waterway traffic. The planning of these systems at tactical level, deserve more attention because a great deal of cost effectiveness could be reached at this level. The purpose of this paper is to address a modeling framework for service network design for a based dry ports hinterland logistics system. The models are based on a path fixed charged capacitated formulation and give as outcomes shipping frequencies by service class of each path and by the way the required capacity in gateways and the intermodal dry ports.
Keywords:	Hinterland, Dry port, Intermodal Transportation, consolidation, Service Network Design.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	COMMUNICATION PROTOCOL FOR CONSTRUCTIVE INTERFERENCE FLOODING IN WIRELESS SENSOR NETWORKS
Author:	HUDA ALHALABI, TAT-CHEE WAN
Abstract:	Wireless sensor networks (WSNs) are utilized to carry out sensor measurements under different conditions. In case of sparse topology, a multi-hop single path routing is usually used to pass information from a source node to a destination node. A problem with this approach is the loss of connectivity of nodes in the path between source and destination, which may lead to network partitioning. Constructive interference (CI) is used to increase the transmission range of the node and connect disconnected parts of a network to overcome the separation problem. CI- based flooding first presented by Glossy can realize millisecond network flooding latency and sub-microsecond time synchronization accuracy, adapt to topology changes and require no network state information. However, Glossy suffers the scalability problem. The packet reception performances of the forwarded nodes degrade significantly as the size or the density of the network increases. In addition, Glossy produces substantial unnecessary data forwarding, which significantly reduces the network lifetime. In this paper, we propose a multi-hop selective CI-based flooding (MSCIF) approach to improve the CI flooding scalability and reduce energy consumption. The proposed protocol works on a cluster-based network and build a virtual backbone from source to destination, consist of the best dominant nodes to perform the flooding. The dominant nodes are selected based on distances between hops and the residual energy in each node. The mathematical analysis shows that the proposed approach reduces the energy consumption and improves the packet reception ratio (PRR).
Keywords:	Wireless Sensor Networks, Constructive Interference; Cooperative Transmission; Clustering; Selection mechanism
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	DESIGN AND DEVELOPMENT OF AN EMBEDDED ACTIVE SOLAR TRACKING AND MANAGEMENT SYSTEM BASED SBC
Author:	NASEER SABRI, SAIFALLAH M. ABGENAH, M. S. SALIM, NOAMAN M. NOAMAN, HAMZA A. JUMA
Abstract:	Solar energy is gaining a rapid notoriety as an important source of renewable energy. Per se, it is vital for those who aim towards maximizing the total gain of its energy to utilize a method that will insure maximum energy gain by tracking the sun's position during its daily cycle. This research targets the means of collecting the utmost solar energy distributed by the sun by implementing an embedded tracking mechanism that will track the sun as it changes its position during its daily cycle. This embedded tracking system is developed based on an open source embedded single board computer (SBC) using an open source code that can be easily modified. The embedded tracking system is built on SBC type RaspberryPi as the main data collection and decision making unit for the system. This microcontroller is a part of an SBC developer's board that has a number of GPIOs to connect different peripherals to be used in the tracking system and controlled by the microcontroller. These peripherals consist of four LDR sensors to be used for sensing the sun's position by reading the light intake and sending the readings to the microcontroller to be processed, the LDR with the most light intensity readings will be the targeted position for the embedded tracking system to move the solar panel towards using two servo motors which will also be connected to the SBC via the GPIO pins, the two servo motors will have different tasks, one servo motor will be in charge of moving the solar panel vertically and the other servo will move the solar panel horizontally. The performance and characteristics of the solar tracker are experimentally analyzed to show the need and advantages of using this method of embedded tracking system. The results show that the designed embedded solar tracking system is efficiently tracking the sun and collecting more energy as compared to the static solar panels. In addition to the proposed embedded system has advantages over other system represented by real time tracking based on an active sun potion computing technique. The embedded solar tracking system offers cost effective and efficient solar tracking besides open source programming which allows for future enhancement and modification.
Keywords:	Embedded Systems, Open Source Technology, Solar Tracker, Sensing, Solar Panels, Renewable Energy
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	SEQUENTIAL AND PARALLEL COMPOSITION OF ROUND TRANS-FORMATIONS FOR CONSTRUCTION OF AN ITERATIVE ALGO-RITHM FOR STOCHASTIC DATA PROCESSING
Author:	IVANOV MIKHAIL, STARIKOVSKIY ANDREY, POPOV NIKOLAY, MAMAEV DMITRY, SKITEV ANDREY, KUTEPOV STANISLAV, BABALOVA IRINA
Abstract:	The trend of recent years has been the advent of algorithms based on the use of 2D and 3D stochastic transformations. This article proposes a new iterative cryptographic algorithm of 3D stochastic data transformation, which is basically aimed for information security solutions. The algorithm is characterized by the high degree of parallelism at the level of elementary operations. It is proposed to design an iterative transformation based on the consistent and parallel composition of the round operations. Such an approach to the design of the iterative cipher blocks has not previously been used. Its use in a software implementation of the cryptographic transformation became possible due to the advent of the heterogeneous supercomputer technologies. It became possible to perform within a round in parallel (without performance compromising) complex transformations of different trajectories and then at the output perform the parallel composition of the results. As a result, the task of the encryption function inverting becomes computationally unsolvable with fewer rounds of transformation.
Keywords:	Cryptographic Primitives, 3D Transformation, Cube Architecture, Iterative Stochastic Trans-Formation, Mixstate Transformation
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	AN ADAPTIVE CLUSTER BASED IMAGE SEARCH AND RETRIEVE FOR INTERACTIVE ROI TO MRI IMAGE FILTERING, SEGMENTATION, AND REGISTRATION
Author:	PADMAJA GRANDHE, 2DR. E. SREENIVASA REDDY, DR.D.VASUMATHI
Abstract:	Recently, there has been an enormous development in compilation of diverse image databases in the appearance of digital. The majority of the user establishes it hard to investigate and recover necessary images in huge collection. In organize to supply an effectual and well-organized explore engine tool, to smooth the progress of high point examination of checkup image information in investigate and clinical environment the scheme has been put into practice. In image retrieval system, there is no methodologies contain been careful in a straight line to get back the images from databases. That featured images only have be measured for the retrieval process in order to retrieve exact desired images from the databases. This paper also highlights an thought of newly developed image clustering technique and their real time application such as Clustering based image linearization in ROI, The purpose of this effort is a scalable, immediate, illustration search engine for medical images, Preprocessing, feature extraction, Classification and retrieval steps in arrange to build an well-organized recovery tool. The main characteristic of this tool is used of CBISR of the extract feel pattern of the image and clustering algorithm for image categorization in arrange to get better retrieval efficiency. The future image retrieval scheme consists of three stages i.e., segmentation, texture feature extraction and clustering procedure. In the segmentation development, preprocessing step to section the image into block is carried out. A decrease in an image area to be process is approved out in the surface feature removal procedure and lastly, the extract image is clustered using K-means algorithm
Keywords:	CBISR, MRI,K-Mean, Image Retrieval, Segmentation, Image Filter
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text

Title:	METHOD OF SIGNALS FORMING FOR HIGH-SPEED RADIO ACCESS SYSTEMS 5G
Author:	DMITRY IGOREVICH USHAKOV, IVAN ALEKSANDROVICH STAROVOIT
Abstract:	This article presents the results of the research of a new method of signal generation for advanced wireless access systems, including cognitive radio systems, which allows to increase the spectral efficiency of the system and data transfer speed as well. Communication systems built on the basis of the architecture of software-configurable radio with cognitive radio algorithms have good perspectives, especially in the age of 5G- systems development. However, the signals that are used in modern radio systems (the signals from the orthogonal frequency division multiplexing Ortogonal Frequency Division Multiplex (OFDM)) have a number of significant disadvantages, one of which is the high level of side lobes of certain subcarriers that does not allow to provide potential spectral efficiency of high-speed radio access systems. This article describes new method of signals formation which is based on application of the new baseline signal shaping functions, the main feature of which is the ability for adaptive change of the level of energy localization in frequency and time area of basis vector. The use of the given basis allows not only to generate signals with a low level of lateral lobes in a group signal spectrum, but also with the changing structure of the spectrum, which can adaptively adjust to the existing electromagnetic environment in the channel, thus formed, while the process of adaptation in empty areas of spectrum, there is low enough level of interference noise that cannot be achieved using signals with orthogonal frequency division multiplexing. The work states the results of the research conducted on the sustainability assessment to the effect of additive white Gaussian noise using computer modeling. Besides the assessment proposed in the article spectral efficiency was carried out.
Keywords:	Cognitive Radio Communication System, OFDM, Spectral Efficiency, Spectral Mask, Dynamic Spectrum, Subcarrier, Forming Function, Orthogonality, 5G.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2016 -- Vol. 94. No. 1 -- 2016
Full Text