		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
October 2013 | Vol. 56 No.3

Title:	DETECTING MOTION BY COMBINING THE STRUCTURE-TEXTURE IMAGE DECOMPOSITION AND SPACE-TIME INTEREST POINTS
Author:	I.BELLAMINE, H.TAIRI
Abstract:	Among all the features which can be extracted from videos, we propose to use Space-Time Interest Points (STIP), these ones are particularly interesting because they are simple and robust. They allow a good characterization of a set of regions of interest corresponding to moving objects in a three-dimensional observed scene. In this paper, we show how the resulting features often reflect interesting events that can be used for a compact representation of video data as well as for tracking. For a good detection of moving objects, we propose to apply the algorithm of the detection of spatiotemporal interest points on both components of the decomposition which is based on a partial differential equation (PDE): a geometric structure component and a texture component. Proposed results are obtained from very different types of videos, namely sport videos and animation movies.
Keywords:	Space-Time Interest Points; Structure-Texture Image Decomposition; Motion Detection
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	PROBABILISTIC QUEUING SCHEME FOR SERVICING E-MAILS USING MARKOV CHAINS
Author:	OMAR SAID, ALAA ELNASHAR
Abstract:	Recently, huge number of e-mails is sent and received. These e-mails are classified into spam and non spam ones which are processed with the same priority. To guarantee a higher priority service to non-spam e-mails than that is provided to spam e-mails, a two-priority queue scheme was proposed. There are some drawbacks in the two-priority queue scheme such as it fails to provide a Quality of Service (QoS) in case of network bottlenecks. In this paper, an algorithm for servicing non-spam e-mails with high probability is proposed. Markov chain is used to analyze the servicing probability of e-mails in case of two and three priority queue schemes. Results proved that the three-queue scheme provides a higher probability service to the most important non spam e-mails than that is provided to the same class in case of the two-queue scheme.
Keywords:	E-mail Systems; Internetworking; Markov Chain; Queuing Theory.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	SORTING DATES FRUIT BUNCHES BASED ON THEIR MATURITY USING CAMERA SENSOR SYSTEM
Author:	ABDELLAHHALIMI, AHMED ROUKHE, BOUZID ABDENABI, NOUREDDINE EL BARBRI
Abstract:	This paper presents the development and application of image analysis and computer vision system in quality and maturity evaluation of products in the agricultural field. Computer vision is a rapid, consistent and objective inspection technique, which has been expanded to varied industries. Monitoring and controlling ripeness is becoming a very important issue in fruit management since ripeness is perceived by customers as main quality indicator [1]. In this paper, we present a method for automatic evaluation of date fruits maturity based on computer vision. The method was implemented, and tested on a sample of dates fruit images with different levels of maturity. Segmentation is one of the basic techniques in computer vision [2][5]. Color is often thought as a property of an individual object and the color of this object comes from the visible light that reflects off the object surface. In this experiment we have implemented a method to quantify the standard color of fruit in HSV(Hue, Saturation and Value) color spaces in order to achieve fruit image segmentation. For this reason, a machine vision system was trained to distinguish between good or mature and yellow or green date fruits. HSV system is suggested as the best color space for quantification in date fruit quality and maturity. In addition, our approach has the benefits of being insensitive to rotation, scaling, and translation. Moreover, the system can be applied to several types of maturity fruit evaluation. In this article we shall give the results of the experiments we have carried out; these results demonstrate the feasibility of our proposed method in color segmentation for date fruit evaluation.
Keywords:	Image Processing; Image Segmentation And Binarisation; Computer Vision, Quality Control, HSV And RGB Color Space
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	OPINION ANALYSIS FOR TWITTER AND ARABIC TWEETS: A SYSTEMATIC LITERATURE REVIEW
Author:	MNAHEL AHMED IBRAHIM, NAOMIE SALIM
Abstract:	The objective of this paper is to present the current evidence relative to twitter opinion mining in general and also the current state of Arabic tweets’ opinion mining. The researcher performed a systematic literature review (SLR) to investigate features and methods used for twitter opinion mining and if those features and methods have been used for Arabic tweets opinion mining. Sixty five papers were used in our synthesis of evidences. Results showed that n-grams features are the most features used for twitter sentiments analysis and also for Arabic tweets. The most common methods used for twitter sentiments analysis is the Lexical based classification using Naive Bayes (NB) and Support Vector Machines (SVM), which are also used for Arabic tweets. In addition, evidence related to subjectivity and opinion target for twitter are highlighted. The results of this SLR show gaps in the research field: first, the lack of studies focusing on multilingual twitter sentiments analysis. Second, the lack of studies that investigate Arabic tweet opinion target. The third is the lack of studies investigating Arabic tweet subjectivity.
Keywords:	Opinion Analysis, Arabic Opinion Mining, Twitter, Systematic Review.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	RETROFITTING OF COLUMNS WITH RC JACKETTING AN EXPERIMENTAL BEHAVIOR
Author:	K.SENGOTTIAN, DR.K.JAGADEESAN
Abstract:	Columns are important structural elements in a multi storey building since it transmitting the entire loads to the foundation. If the columns are subjected to lateral loading due to wind/ earthquake, the load carrying capacity of the column member is substantially reduced. Hence the load carrying capacity of the compression member has to be increased. One way of increasing the load carrying capacity is by the way of confining the columns. There are a lot of confinement materials that are used for strengthening of concrete structures. Ferrocement, glass fiber, aramid fiber, carbon fiber, etc. are some of the few materials that are used in the confinement of concrete columns. Section enlargement is one of the methods used in retrofitting column concrete members. Enlargement is the placement of reinforced concrete jacket around the existing structural member to achieve the desired sectional properties and performance. This experimental study aims in assessing the behavior of such reinforced concrete columns confined with external Reinforced Concrete jacketing technique. This would enable in arriving at the effectiveness of the confinement in concrete columns in seismic regions. In this study we have tried with helical ties and vertical rods to improve the strength of column.
Keywords:	Multi Story Building Columns, Confinement Of Concrete, Section Enlargement, Effectiveness Of The Confinement In Concrete Columns
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	A NOVEL DIFFERENTIAL EVOLUTION BASED ALGORITHM FOR HIGHER ORDER NEURAL NETWORK TRAINING
Author:	Y. KARALI, SIBARAMA PANIGRAHI, H. S. BEHERA
Abstract:	In this paper, an application of an adaptive differential evolution (DE) algorithm for training higher order neural networks (HONNs), especially the Pi-Sigma Network (PSN) has been introduced. The proposed algorithm is a variant of DE/rand/2/bin and possesses two modifications to avoid the shortcomings of DE/rand/2/bin. The base vector for perturbation is the best vector out of the three randomly selected individuals for mutation, which actually assists intensification keeping the diversification property of DE/rand/2/bin; and novel mutation and crossover strategies are followed considering both exploration and exploitation. The performance of the proposed algorithm for HONN training is evaluated through a well-known neural network training benchmark i.e. to classify the parity-p problems. The results obtained from the proposed algorithm to train HONN have been compared with solutions from the following algorithms: the basic CRO algorithm, CRO-HONNT and the two most popular variants of the differential evolution algorithm (DE/Rand/1/bin and DE/best/1/bin). It is observed that the application of the proposed algorithm to HONN training (DE-HONNT) performs statistically better than that of other algorithms.
Keywords:	Artificial Neural Network, Higher Order Neural Network, Pi-Sigma Neural Network, Differential Evolution, Chemical Reaction Optimization.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	CONTINUOUS HOPFIELD NETWORK AND QUADRATIC PROGRAMMING FOR SOLVING THE BINARY CONSTRAINT SATISFACTION PROBLEMS
Author:	KHALID HADDOUCH, MOHAMED ETTAOUIL, CHAKIR LOQMAN
Abstract:	Many important computational problems may be formulated as constraint satisfaction problems (CSP). In this paper, we propose a new approach to solve the binary CSP problems using the continuous Hopfield networks (CHN). This approach is divided into three steps: the first concerns reducing the size of the CSP problems using arc consistency technique AC3. The second step involves modeling the filtered constraint satisfaction problems as 0-1 quadratic programming subject to linear constraints. The last step concerns applying the continuous Hopfield networks to solve the obtained 0-1 optimization model. Therefore, the mapping procedure and an appropriate parameter setting procedure about CSP problems are given in detail. Finally, some computational experiments solving the CSP problems are shown.
Keywords:	Constraint Satisfaction Problems, Filtering Algorithms, Quadratic 0-1 Programming, Continuous Hopfield Networks, Energy Function.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	A TECHNIQUE FOR WEB PAGE RECOMMENDATION USING MARKOV MODEL ASSOCIATED WITH QUALITY AND TIME BASED FP MINING
Author:	R. SUGUNA, Dr. D. SHARMILA
Abstract:	The aim of the web page recommendation is to predict the navigation of the users using web usage mining technique. In recent days, the researchers are exploring to develop an algorithm for web page recommendation using pattern mining model. Here, the data are prepared from the web log file and identify the users based on the ip address. Boid algorithm is used to cluster the logs and the quality and time based frequent pattern growth algorithm is used to mine the frequent patterns. Markov model is applied to generate the recommendation. The frequent pattern tree is formed by calculating the total support values of each web page based on the quality and time duration of the web pages and this frequent pattern tree is used to recommend the web page using Markov model. The artificial dataset is generated for experimentation to compare the performance of proposed technique with the existing technique.
Keywords:	Web Page Recommendation, FP-Growth Algorithm, Markov model, clustering
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	AN EFFICIENT SEMANTIC WEB SERVICES SELECTION MODEL USING CLUSTERING
Author:	SHYNU P.G.
Abstract:	Web Services are one of the fastest growing areas of information technology in recent years, also being a main motivating factor for internet computations in which, one of the services being, service discovery. Web service discovery is the process of finding appropriate services for the user defined tasks.Web Service clustering is a technique for efficiently facilitating service discovery. Most Web Service clustering approaches are based on suitable semantic similarity distance measure and a threshold. Threshold selection is essentially difficult and often leads to unsatisfactory accuracy. In this paper, a self-organizing based clustering algorithm called Taxonomy based clustering for taxonomically organizing semantic Web Service advertisements. A query matching method is also applied on these clusters to get more accurate and relevant results based for user requests. The system is tested and observed promising results both in terms of accuracy and performance.
Keywords:	Web Services Discovery, Composition, Ontology, Semantic Similarity, Clustering
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	A NEW DATABASE INTEGRATION MODEL USING AN ONTOLOGY-DRIVEN MEDIATED WAREHOUSING APPROACH
Author:	HAFIZULLAH AMIN HASHIM, ALI AHMED, NAOMIE SALIM, 4OH YU SHENG, AHMAD OSMAN, ALEX SIM, ARYATI BAKRI, NOR HAWANIAH ZAKARIA, ROLIANA IBRAHIM, SHAHIR SHAMSIR OMAR
Abstract:	Database integration technology has been developed for more than 20 years. The difficulties of database integration are the integration of heterogeneous data sources, with respect to the schemas and their data, as well as the query processing time that can take longer than expected. In this study, we present a semantic database integration framework using an integrated mediated and data warehouse approach to search for query words or sentences in a database and determine the accuracy of the search results. This method exploits semantic annotation, which overcomes some of the traditional database integration problems such as syntactic heterogeneity, structural or schematic heterogeneity and semantic heterogeneity. In this approach, semantic annotation is extracted from two types of ontologies, local and global ontology. The former is used to provide semantic annotation of data sources, and the latter is used to provide the shared vocabulary of a particular domain. With the help of domain ontology, the searching process will be more meaningful as it caters for the semantic aspects of a search query. This approach can enhance the efficiency and effectiveness of the search for the desired information.
Keywords:	Semantic, Database Integration, Local Ontology, Global Ontology, WordNet, SPARQL Query, Warehouse, Mediated
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	BRAIN STROKE CLASSIFICATION BASED ON MULTI-LAYER PERCEPTRON USING WATERSHED SEGMENTATION AND GABOR FILTER
Author:	C. AMUTHA DEVI, Dr. S. P. RAJAGOPALAN
Abstract:	Stroke is a cardiovascular disease that occurs whenever blood supply to the brain is stopped. For the diagnosis of the brain strokes, characterization of the progress of the disease and monitoring the treatment therapies, neuro-imaging techniques in the form of Magnetic Resonance Images (MRI) are widely used. Accurate segmentation and classification of stroke affected regions are essential for correct detection and diagnosis. Image classification is a critical step for high-level processing of automatic brain stroke classification. In this paper, a method is proposed for classifying the MRI images into stroke and non-stroke images. Features are extracted using Watershed segmentation and Gabor filter. The extracted features are classified using Multilayer Perceptron (MLP). Experiments have been conducted to evaluate the efficiency of the proposed method with varying number of features.
Keywords:	Infarction, Stroke Classification, Magnetic Resonance Imaging (MRI), Watershed, Gabor filter, Multilayer Perceptron (MLP)
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	MODIFIED REPUTATION-BASE TRUST (MRT) FOR WSN SECURITY
Author:	ABDULLAH SAID ALKALBANI, ABU OSMAN MD. TAP, TEDDY MANTORO
Abstract:	During the last years, Wireless Sensor Networks (WSNs) and its applications have obtained considerable momentum. However, security and power limits of WSNs are still important matters. Many existing approaches at most concentrate on cryptography to improve data authentication and integrity but this addresses only a part of the security problem without consideration for high energy consumption. Monitoring behavior of node neighbors using reputation and trust models improves the security of WSNs and maximizes the lifetime for it. However, a few of previous studies take into consideration security threats and energy consumption at the same time. Under these issues we propose a reputation and trust mechanism optimized for security strength. We apply two security threats (oscillating and collusion) during simulations of the proposed model in order to measure the accuracy, scalability, trustworthiness and energy consumption. As results, effects of collusion and oscillating are minimized and energy consumptions for dynamic networks reduced. Also simulation results show that the proposed model remains resilient to low or high percentages of pernicious servers when the percentage of client sensors are greater than or equal 60%. This result is quite promising; it shows that energy consumption generally is low, especially for dynamic networks.
Keywords:	Wireless Sensor Networks (WSNs), Collusion, Oscillating, Power Consumption, Trust and Reputation Models
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	IMPROVING THE PERFORMANCE OF K-MEANS ALGORITHM USING AN AUTOMATIC CHOICE OF SUITABLE CODE VECTORS AND OPTIMAL NUMBER OF CLUSTERS
Author:	MOHAMED ETTAOUIL, ESSAFI ABDELATIF, FIDAE HARCHLI
Abstract:	The automatic clustering is a useful tool for data-mining. It‘s a daily necessity for the searcher whatever his specialty. Indeed because of the huge amount of information available on the web-site, the access to relevant information in a suitable time is a difficult task. By grouping those informations in clusters this problem can be surmounted. Many clustering methods exist in the literature but the efficient ones suffer from some drawbacks. The main of them follows from the initialization phase which is performed randomly. Among these algorithms we find the k-means(deterministic and probabilistic version) and the clustering method based on Gaussian mixture. In these algorithms the initial parameters including the number of cluster are chosen randomly. Consequently an improper choice leads to poor clusters. In this paper we propose an approach attempting to overcome these problems. In this method the initial parameters are automatically and suitably identified. To this end, the structure of data is investigated in each iteration. To validate the proposed method a number of experiments are performed.
Keywords:	Clustering, K-Means, Evaluation Clustering
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	INFANT CRIES IDENTIFICATION BY USING CODEBOOK AS FEATURE MATCHING, AND MFCC AS FEATURE EXTRACTION
Author:	MEDHANITA DEWI RENANTI, AGUS BUONO, WISNU ANANTA KUSUMA
Abstract:	In this paper, we focused on automation of Dunstan Baby Language. This system uses MFCC as feature extraction and codebook as feature matching. The codebook of clusters is made from the proceeds of all the baby’s cries data, by using the k-means clustering. The data is taken from Dunstan Baby Language videos that has been processed. The data is divided into two, training data and testing data. There are 140 training data, each of which represents the 28 hungry infant cries, 28 sleepy infant cries, 28 wanted to burp infant cries, 28 in pain infant cries, and 28 uncomfortable infant cries (could be because his diaper is wet/too hot/cold air or anything else). The testing data is 35, respectively 7 infant cries for each type of infant cry. The research varying frame length: 25 ms/frame length = 275, 40 ms/frame length = 440, 60 ms/ frame length = 660, overlap frame: 0%, 25%, 40%, the number of codewords: 1 to 18, except for frame length 275 and overlap frame = 0 using 1 to 29 clusters. The identification of this type of infant cries uses the minimum distance of euclidean distance. Accuracy value is between 37% and 94%. Sound ‘eh’ is the most familiar, whereas sound ‘owh’ is always missunderstood and generally it is known as ‘neh’ and ‘eairh’. The weakness point of this research is the silent is only be cut at the beginning and at the end of speech signal. Hopefully, in the next research, the silent can be cut in the middle of sound so that it can produce more specific sound. It has impact on the bigger accuracy as well.
Keywords:	Codebook, Dunstan baby language, Infant cries, K-means clustering, MFCC
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text

Title:	SYBIL IDENTIFICATION IN SOCIAL NETWORKS USING SICT AND SICTF ALGORITHMS WITH IMPROVED KD-TREE
Author:	RENUGA DEVI. R, M. HEMALATHA
Abstract:	Most of the large scale social networking sites and small private social networks on the Internet are open to Sybil attacks. Lack in powerful user identity yields these systems at risk to Sybil attacks. A large number of methods have been proposed to solve this problem, but each method differs greatly from other based on the algorithms which they used, and network. In this paper we proposed two novel algorithms to identify the Sybil nodes in network community. We proposed SICT (Sybil identification using connectivity threshold) algorithm with Improved KD-Tree. Connections between the nodes are established, and connection threshold is compared with each node, if the connection establishment is exceeding the threshold then the node is identified as Sybil. We proposed SICTF (Sybil identification using connectivity threshold and frequency of visit or hitting the neighbors) algorithm, where the maximum variance of connectivity, length and frequency of a node can be calculated for a particular time interval and the maximum variance with respect to connectivity, length, and frequency is said to be Sybil. Both the algorithms are combined with previous Improved KD-Tree algorithm for community mining. Experimental results show that proposed SICTF algorithm performs well compared to the existing algorithm.
Keywords:	Social Networks, Sybil Node, Community Mining, Improved KD-Tree, SICT, SICTF
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 3 -- 2013
Full Text