		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 August 2012 | Vol. 42 No.1

Title:	POWER SYSTEM TRANSFORMER BOARD DEGRADATION DETECTION USING PROBABILISTIC NEURAL NETWORK
Author:	SERAP CEKLI , CENGIZ POLAT UZUNOGLU, MUKDEN UĞUR
Source:	Journal of Theoretical and Applied Information Technology pp 001 - 007 Vol. 42. No. 1 -- 2012
Abstract	The insulation condition monitoring of a power transformer has an important role for insulating materials which are subjected to extensive breakdown stress. In this study, a test setup has been constructed in order to simulate real world breakdown characteristics of transformerboards which are widely used as the insulating material. During the service life transformerboards may display undesired surface discharge damage due to increased rated voltages, which reduces the lifetime of transformerboards. The probabilistic neural network is used to detect the surface degradation of a transformerboard by analyzing electrical and ultrasound discharge data obtained from the test setup. The principle component analysis is employed to eliminate the messy matrix and vector calculations of the probabilistic neural network operations. Results of the classification procedure are given.
Keywords	Transformer board, Probabilistic Neural Network, Principle Component Analysis
Full Text

Title:	COOPERATIVE SWARM INTELLIGENCE BASED EVOLUTIONARY APPROACH TO FIND OPTIMAL CLUSTER CENTER IN CLUSTER ANALYSIS
Author:	BIGHNARAJ NAIK, SARITA MAHAPATRA
Source:	Journal of Theoretical and Applied Information Technology pp 008 - 017 Vol. 42. No. 1 -- 2012
Abstract	The Centroid-based clustering is an NP-hard optimization problem and the common approach is to search for cluster centers only for approximate solutions. In this paper we have proposed swarm intelligence based nature-inspired center-based clustering method using PSO optimization. Proposed PSO clustering method is capable to search best cluster with maximum fitness using social-only and cognition-only model, such that the square distances from the cluster are minimized. In this article, how PSO based clustering can be used to get N number of cluster specified by the user in a dataset is demonstrated. Our suggested method has been tested with artificial dataset and several datasets from UCI Machine learning repository. Effectiveness and usefulness of the proposed method is shown by comparing fitness of this method with K-means and Fuzzy c-means technique. For better comparative result, we have ended up with comparison of proposed clustering model with subtractive clustering (extension of the mountain clustering) to ensure proposed method computes optimal number of cluster in a dataset. Results shows that, this method is quite simple, effective and has much potential to search best cluster centers in multidimensional search space.
Keywords	Swarm intelligence (SI); Particle swarm optimization (PSO); Centroid-based clustering; Cluster Analysis; Fuzzy C-means clustering (FCM); K-Means clustering; Subtractive Clustering; Euclidean distance;
Full Text

Title:	DYNAMIC TTL BASED ALGORITHM FOR HIERARCHICAL RESOURCE DISCOVERY MODEL IN GRID
Author:	KAMRAN ZAMANIFAR, HOSSEIN ABOOTALEBIAN, LADAN MALAZIZI
Source:	Journal of Theoretical and Applied Information Technology pp 018 - 025 Vol. 42. No. 1 -- 2012
Abstract	Today, Grid is used as a powerful infrastructure for resource sharing. One of the main services in the Grid is the resource discovery service. Several models and methods have been proposed to manage and search of resources. The central model has problems such as single point of failure and heavy load. There are newer models in order to solve the mentioned problems, but there is also the problem of sending anomalous query messages among these models. In this paper, resource discovery tree which is constructed based on hierarchical model has been utilized. In the first place, by considering coefficients for each level in the tree, the managers are provided with information. Afterward, by using this information, time to live of discovery messages are dynamically determined. By doing so, the forwarding of these messages is limited so that the traffic imposed by resource discovery is alleviated and its performance is enhanced. Eventually, to evaluate, the simulation of the presented method through this paper and other methods were used. The results of the accomplished evaluation showed that although the proposed method uses small number of update messages and spends a little time to process the information of the resources, it significantly decreased the traffic resulted from the transferring of the messages for resource discovery and also increased speed.
Keywords	Grid, Hierarchical Model, Resource Discovery, Time to Live
Full Text

Title:	STUDY OF INCLINATION ANGLE OF REFLECTOR OBJECT IN SIMPLE WATER LEVEL INSTRUMENT USING 40 KHz ULTRASONIC TRANSDUCER
Author:	WARSITO, G. A. PAUZI, S. W. SUCIYATI, K. IMANIAR
Source:	Journal of Theoretical and Applied Information Technology pp 026 - 030 Vol. 42. No. 1 -- 2012
Abstract	The simple water level instrument has been designed by using ultrasonic transducer and the inclination angle of reflector object has been studied. The hardware system consists of ultrasonic transducer, 16bits Atmega8535 microcontroller and 2x16 Liquid Cristal Display (LCD) monitor. By using a 40 KHz ultrasonic transducer, and assuming the sound velocity in air is 344m/s, the maximum theoritical resolution possible is 19.2mm for the maximum water level measured is 3.182m. The experimental obtained resolution is about 29.7mm. The minimum angle of object inclination given by factory for which the sound will not be reflected back towards the receiver is starting from 450, the obtained exact value of inclination angle in this research is starting from 100. The sensibility of system in digital bits number for the object inclination angle of 00 is 5143bits/m.
Keywords	Non Destructif Method, Water Level, Ultrasonic Transducer
Full Text

Title:	ON THE DIVERSITY RECEPTION WITH CORRELATED RAYLEIGH-FADING SIGNALS
Author:	Amira El Atar, Mona Shokair , Salah Khamis , Mohamed E. Nasr
Source:	Journal of Theoretical and Applied Information Technology pp 031 - 034 Vol. 42. No. 1 -- 2012
Abstract	In this paper, the diversity reception with correlated Rayleigh fading signals will be investigated . Results will be evaluated by converting two correlated Rayleigh fading signals into another two independent Rayleigh fading signals using transformation matrix. These results show that Optimum transformation matrix F=1 is better than F = which is the elements of the optimum transformation matrix which convert two correlated Rayleigh fading signals into another two independent Rayleigh fading signals. Analysis of the system over Rayleigh fading will be made further, the BER performance will be investigated under BPSK modulation.
Keywords	DS-CDMA, The Diversity Technique . Diversity Reception, Fading Signals, Rayleigh Fading
Full Text

Title:	INCORPORATING FUZZY INFORMATION FOR THE EVALUATION OF CONFIDENCE MEASURE IN DETECTION OF PUTATIVE ERRORS AND OOV WORDS IN ASR SYSTEM
Author:	Dr.C.P. SUMATHI, V. MEENAKSHI, Dr.T. SANTHANAM
Source:	Journal of Theoretical and Applied Information Technology pp 035 - 041 Vol. 42. No. 1 -- 2012
Abstract	Confidence Measure (CM) in Speech Recognition System (SRS) provides the information about how much confident the recognizer in recognizing the word. Accurate recognition of Automatic Speech Recognition (ASR) is one of the most difficult problems in speech recognition today. When speech is produced in a carefully planned manner, ASR systems are successful at accurate recognition and transcription. In this work, Fuzzy Reasoning Scheme is proposed to perform the information compilation step that includes recognition related features that combines through a compilation mechanism, into a more effective way to distinguish between correct and incorrect recognition results. A novel method is described to combine different knowledge sources and estimate the confidence in a word hypothesis via Fuzzy Inference System (FIS) and measure the joint performance of recognition and confidence systems. Here the HCM (Hybrid Confidence Measure) which is a combination of Acoustic CM and Phone Duration based CM and Likelihood Score Ratio (LSR) are incorporated with Fuzzy if-then rules to add up recognition information into CM. Definitions and Algorithms are illustrated with results on the HUB4_trigram corpus. Experimental result shows higher performance of this approach compared against standard compilation methods in rejection of putative errors and detection of Out-Of-Vocabulary (OOV) words. Fuzzy Inference Systems (FIS) represent a natural way to increase the performance of Confidence Measure (CM). This approach treats the uncertainty of recognition hypotheses in terms of “possibility” contrasted to the “probability” notion of previous works. Different features are incorporated with FIS that produces better results of recognition.
Keywords	Confidence Measures (CM), Out-Of-Vocabulary (OOV) words, Fuzzy Inference System (FIS), Hybrid Confidence Measure (HCM), Likelihood Score Ratio (LSR)
Full Text

Title:	OPTIMAL SETTING GAIN OF PSS-AVR BASED ON PARTICLE SWARM OPTIMIZATION FOR POWER SYSTEM STABILITY IMPROVEMENT
Author:	MUHAMAD HADDIN, SOEBAGIO, ADI SOEPRIJANTO, MAURIDHI HERY PURNOMO
Source:	Journal of Theoretical and Applied Information Technology pp 042 - 048 Vol. 42. No. 1 -- 2012
Abstract	This paper presents the settings of automatic voltage regulator (AVR) and power system stabilizer (PSS) on a single machine infinite bus (SMIB) to improve the dynamic stability of the power system. This setting is done by determining the fitness function of AVR (KA) and PSS (KPSS) gain using Particle Swarm Optimization (PSO) algorithm. The main purpose of this setting is to minimize the oscillation frequency so that it would improve the stability of electric power. Simulations are conducted by inputting step function with 5% load fluctuations as a representation of dynamic load. Simulation results show that the proposed method is very effective for improving the damping of electromechanical oscillations of the power system. The proposed method shows that the power system produces a reduced rate of 11% overshoot and settling time 40%.
Keywords	Setting Gain of PSS-AVR, Dynamic Stability, Modified PSO
Full Text

Title:	VLSI ARCHITECTURE FOR LOW POWER MINIMUM SIGNED DIGIT MULTIPLIER FOR FIR FILTER AND ITS SIGNAL PROCESSING APPLICATIONS
Author:	K.N.VIJEYAKUMAR, Dr.V.SUMATHY, E.J.AISHWARYA, S.SARAVANAKUMAR, M.GAYATHRI DEVI
Source:	Journal of Theoretical and Applied Information Technology pp 050 - 058 Vol. 42. No. 1 -- 2012
Abstract	Most of the Digital Signal Processing applications (DSP) involve multiplication and accumulation operation. As multiplier decide the critical computation time and power dissipation of a signal processing architecture, design of high throughput and power efficient multiplier is a major challenge. In this paper, we proposed a new architecture for high speed multiplication based on shifting and adding inputs based on bit values of filter coefficients. Minimum Signed Digit (MSD) representation of constants with Common Sub expression (CS) algorithms has been used to reduce the number of addition operations in filters for reducing dynamic power consumption. The proposed architecture has been designed using VHDL and simulated in ALTERA Quartus II 8.1. Experimental results demonstrates that the dynamic power dissipation of our MSD-CS multiplier is better compared to the previous designs and shows a delay reduction up to 17.2% compared to standard design. Design implementation of proposed multiplier in an18 tap FIR filter is done to verify its functionality.
Keywords	Common Sub-Expression Elimination (CSE), Shift And Add, Canonic Signed Digit(CSD) Representation, Finite Impulse Response (FIR),Infinite Impulse Response(IIR)
Full Text

Title:	DESIGNING AN ADAPTIVE QOS-ORIENTED AND SECURE FRAMEWORK FOR WIRELESS SENSOR NETWORKS IN EMERGENCY SITUATION
Author:	RACHID HAJI, MOHAMED GHALLALI, ABDERRAHIM HASBI, BOUABID EL OUAHIDI
Source:	Journal of Theoretical and Applied Information Technology pp 059 - 069 Vol. 42. No. 1 -- 2012
Abstract	The most important factor characterizing an emergency situation is the lack of information or the difficult access to it. The use of wireless sensor networks (WSN) in this type of applications allows having an almost real-time status of the supervised area by collecting relevant information and thus assisting in the process of rapid response to the disaster. In such cases, the information availability, reliability, security and delay of its delivery are critical to the success of rescue operations. In this paper we design a new Framework Ad-M-QoS-DS (Adaptive Management of QoS in different situations) that permits an adaptive management according to the QoS requirements of each situation in the supervised area by grouping multiple modules and parameters. Next, we have proposed a Sensor Security Module (SSM) for our Framework to dispute sensor security challenges and describe the role of its components. At the end of the paper, we implement the proposed Module within the Base Station (BS).
Keywords	Emergency situations; Wireless Sensor Networks; QoS; Sensor security; Energy; Mobility
Full Text

Title:	A NEW OPTIMAL QUADRATIC PREDICTOR OF A RESIDUAL LINEAR MODEL IN A FINITE POPULATION
Author:	MOHAMMED EL HAJ TIRARI, ABDELLATIF EL AFIA, RDOUAN FAIZI
Source:	Journal of Theoretical and Applied Information Technology pp 070 - 074 Vol. 42. No. 1 -- 2012
Abstract	In this paper, we deal with the problem related to the prediction of a residual quadratic form of a super-population model in the case of a finite population. We propose a new optimal quadratic predictor of this quadratic form for a linear Gaussian model . The main result of this paper is used to derive an optimal quadratic predictor of the residual sum of squares of a linear Gaussian model.
Keywords	Survey Sampling, Finite Population, Super-Population Model, Quadratic Prediction
Full Text

Title:	REVIEW AND FUTURE DIRECTIONS OF THE AUTOMATED VALIDATION IN SOFTWARE PRODUCT LINE ENGINEERING
Author:	ABDELRAHMAN OSMAN ELFAKI, OMAR AMER ABOUABDALLA, SIM LIEW FONG, MD GAPAR MD JOHAR, KEVIN LOO TEOW AIK, RUZI BACHOK
Source:	Journal of Theoretical and Applied Information Technology pp 075 - 093 Vol. 42. No. 1 -- 2012
Abstract	Context: Software Product Line Engineering (SPLE) has emerged as a thriving approach for software products constructions. In SPLE, a triumphant software product is highly reliant on the validity of an SPLE. Hence, validation is a significant process within SPLE. Objective: In this paper, we reviewed the related works in the area of automated validation of SPLE to bring to light the pros and cons of the related works and suggest the future directions in this research area. Method: We started by defining the validation operations followed by classification of the related works in eight groups based on the technique or method that is used. The general attributes of each class are highlighted and the main strengths and weaknesses of each class related to the validation of SPLE are thrashed out. Subsequently, we analyzed each work to find out which validation operations are achieved and how they are satisfied. Finally, we abridged the current situation and recommended how the validation of SPLE can be enhanced in each operation. Results: The research gap in the area of validation of SPLE has been clarified by recommending the future directions. Conclusion: It is concluded that some works cannot gratify all the validation operations because the technique or method used has its weaknesses that prevented the completion of the validation process. Moreover, we conclude that this area of research has room for improvement by validating the domain-engineering directly instead of validating software products during the configuration process.
Keywords	Software Product Line, Domain-Engineering, Configuration, Automated Analysis
Full Text

Title:	QUALITATIVE DIAGNOSTIC CRITERIA INTO OBJECTIVE QUANTITATIVE SIGNAL FEATURE CLASSIFICATION
Author:	B.SUGUNA NANTHINI, B.SANTHI
Source:	Journal of Theoretical and Applied Information Technology pp 094 - 099 Vol. 42. No. 1 -- 2012
Abstract	Predicting the epileptic seizure is challenging biomedical problem. EEG signal includes enormous information. Few relevant parameters are expected in the field of recognition and diagnostic purposes. Seizure detection and classification system has been designed and developed. The system uses computer based procedures to detect seizure and classified normal and abnormal subjects. Intelligent compact support property of GLCM is used for extracting essential features from the EEG signal. Selected features are classified using neural network model. The 70 samples would be divided into 50 training samples and 20 testing samples. The back propagation algorithm tested on these samples showed expected classification. The main objective of this study is to predict the epileptic seizure using GLCM feature extraction method and neural network model.
Keywords	Seizure, EEG Signal, GLCM, Neural Network, Accuracy
Full Text

Title:	PROVIDER RECOMMENDATION IN E-SERVICE PORTALS USING GROUP PROFILING
Author:	HEBAH ELGIBREEN, ABDULRAHMAN MIRZA
Source:	Journal of Theoretical and Applied Information Technology pp 100 - 112 Vol. 42. No. 1 -- 2012
Abstract	Nowadays, most of e-service portals focus on individual users rather than considering shared characteristics that could be useful when searching a portal. Service providers searching activities involve different types of common user behaviors and preferences that should be considered. Thus, group profiling can be used to group customers with similar interests together and recommend service providers based on their common characteristics. Accordingly, this paper proposes a new approach that recommends service providers, based on group profiling and ranking, to be used by e-service portals. Such an approach is unsupervised and is carried-out in two steps. First, group profiles are generated. Second, whenever a user tries to search for a service provider, a different result may be returned based on the data collected about that specific user. Thus, customers would most likely find the most suitable service provider more accurately and in less time. This approach focuses on group profiling and group users based on the Ant Colony Clustering (ACC) method, which is a new type of clustering that is based on an Artificial Intelligence algorithm called Ant Colony Optimization. In addition, this approach has been tested and three measures have been recorded including speed, aggregation precision, and result accuracy. Such test has shown that this approach is promising and produces high quality results.
Keywords	Group Profiling, Search Recommender, E-Service Portal, Evolutionary Algorithm
Full Text

Title:	NOISE ABATEMENT IN THE ARABIC IRS RESULTS BY APPLYING A SENTENCES MORPHOSEMANTIC FILTER (GENE FILTER METHOD)
Author:	Adil ENAANAI, ABDELAZIZ DOUKKALI, BOUBKER REGRAGUI
Source:	Journal of Theoretical and Applied Information Technology pp 113 - 121 Vol. 42. No. 1 -- 2012
Abstract	In this paper, we introduce a new approach to facilitate the calculation of relevance and noise abatement in information research systems in Arabic language. Our method is to remove morphosemantic ambiguity due to agglutination and lack of vocalization of the Arabic words. To do, we have proposed to transform words to semantic gene. The latter represent an accurate determination of the word meaning. They contain the type, context, definition and vocalized shape of all possible cases may be taken in the Arabic word. In our approach we consider all possible meanings of the terms by applying a morphosemantic variation based on a recursive algorithm. Obtained variants are filtering by using of the sentence context, user profile and the Arabic phrase synthesis rules. The result is a semantically coherent text ready to be used by an information search system.
Keywords	Semantic Gene; Arabic Disambiguation; TALN; Information Research.
Full Text

Title:	AN IMPROVEMENT METHOD OF SUBJECTIVE PICTURE QUALITY WITHIN CONCERNED REGIONS FOR H.264 VIDEO CODING
Author:	KE LI, YALIN WU, SHUYING YANG
Source:	Journal of Theoretical and Applied Information Technology pp 122 - 131 Vol. 42. No. 1 -- 2012
Abstract	Video compression is very crucial method which is used to reduce the quantity of data used to represent digital video pictures. However, most video compression is loss when the video pictures data is quantized. So a quantizer is key factors for adjusting the bitrate and controlling the picture quality. Importantly, if the concerned region of video sequence takes on high level picture quality, the subjective picture quality could be improved. First, on the basis of the subjectively concerned region which can be determined using motion vectors within a video sequence, a classification method is suggested. Furthermore, we propose a method that allocation a relatively small quantization step-size for the concerned region compared with the other regions within a video sequence and thus improves picture quality. The measurement of the objective PSNR and the subjective image quality of result presented that subjective picture quality can be improved by proposed method.
Keywords	Quantization Step-Size, Subjective Picture Quality, Concerned Region, DSCQS
Full Text

Title:	INTELLIGENT SAFETY REGULATION AND WARNING METHOD FOR FISHING BOAT SECURITY
Author:	WEI HE, ENJUN WANG, JINYU LEI
Source:	Journal of Theoretical and Applied Information Technology pp 132 - 136 Vol. 42. No. 1 -- 2012
Abstract	The data mining is carried out for the historical data to investigate and analyze crucial factors related to the causes of accidents of fishing boats. The vital factors, especially shipping time, weather and manipulation, etc. are extracted as the input variables of a BP neural network to establish a safety warning model for fishing boats. In addition, the Particle Swarm Optimization (PSO) is employed to develop the generalization ability of neural network and optimize the parameters of safety warning model. Experiments using the historical data have showed high efficiency of the proposed intelligent safety warning model. Hence, it is feasible for the design of waterborne traffic safety and warning system.
Keywords	Fishing Boats, Safety Regulation and Warning, Neural Network
Full Text

Title:	A RECONSTRUCTION ALGORITHM WITH ADAPTIVE WEIGHTED FUSION IN COMPRESSED SENSING
Author:	YANJUN HU, ZHONGYU LIU, JIE XIANG, XINDE CAO, ENJIE DING
Source:	Journal of Theoretical and Applied Information Technology pp 137 - 141 Vol. 42. No. 1 -- 2012
Abstract	An efficient energy-saving method is proposed by taking the advantages of lightweight encoder and high compression efficiency of Compressed Sensing, which is extremely suitable for image nodes in Wireless Multi-media Sensor Networks. However, the Orthogonal Matching Pursuit (OMP) reconstruction algorithms in CS can not balance the reconstruction image quality and processing time. A novel reconstruction algorithm is proposed in this paper. This algorithm fuses images which reconstructed by OMP according to the row vectors column vectors and diagonal vectors of sample data. And the fusion weights are adjusted by calculating the PSNR values among RIRV (Reconstructed Image by Row Vectors), RICV (Reconstructed Image by Column Vectors) and RIDV (Reconstructed Image by Diagonal Vectors). Experiments show this algorithm is workable, and it reduces the stripe noise. Also, it has a better performance of balancing the reconstruction image quality and processing time than traditional OMP and CoSamp algorithms.
Keywords	Compressed Sensing, Image Fusion, Orthogonal Matching Pursuit, Adaptive Weighted Fusion
Full Text

Title:	FAST OBJECT DETECTION WITH DEFORMABLE PART MODELS BASED ON HIERARCHICAL MODEL
Author:	LIU MENG , QINGXUAN JIA
Source:	Journal of Theoretical and Applied Information Technology pp 142 - 149 Vol. 42. No. 1 -- 2012
Abstract	We propose a deformable parts model attached the coarse to fine detection methods to improve the detection speed. General when we meet the complex target structure, image changes, background interference problems, contour information of the target problems are often difficult to accurately describe. In order to solve the problem, we propose a hierarchical model: first we introduce the Conditional Random Fields (CRF) in the low-layer to fuse sorts of features which can obtain the target candidate region for high-layer that auxiliary to provide the appearance feature; in high-level we molding the contour features of the model and deformable parts model as the underlying detector, the model training and testing use of coarse to fine inference, so it will not only improve the detection speed but also improve the accuracy rate .The experiments on the PASCAL 2007 dataset show that the model flexibility, the universal recognition results are accurate and stable.
Keywords	Deformable Parts Model, Coarse to Fine Detection, Conditional Random Fields
Full Text

Title:	EXPERIMENTAL STUDY OF ON-LINE ARC FAULT DETECTION SYSTEM BASED ON LABWINDOWS/CVI
Author:	QIONGFANG YU, DEZHONG ZHENG, YI YANG, AIHUA DONG
Source:	Journal of Theoretical and Applied Information Technology pp 150 - 155 Vol. 42. No. 1 -- 2012
Abstract	Arc fault is one of the primary reasons that cause electrical fire. In power supply line, if arc fault occurs, the currents can not make protective equipments act, the arc fault can not be found easily, so electrical fire comes into being. Based on Lab Windows/CVI, experimental studied the on-line arc fault detection system. AT89S51 Single Chip Microcomputer is used as lower computer, based on Lab Windows/CVI, the upper computer program uses multithreading technology to detect and analyze the current signal. By arc fault detection algorithm, the system judges whether there has arc fault . The algorithm judges whether there has arc fault through detect if there has periodicity singularity points. The experiments show that this detection method of arc fault can detect arc fault in power supply circuits exactly and efficaciously.
Keywords	Arc Fault, Lab Windows/CVI, On-line Detection; Multithreads, Periodicity Singularity Point
Full Text