		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.1

Title:	ON MODELING TRACES IN A COMPUTING ENVIRONMENT FOR HUMAN LEARNING BASED INDICATORS
Author:	Hassan ELKISS, Faddoul KHOUKHI, Abdelkrim BEKKHOUCHA
Abstract:	In classical teaching, the teacher can supervise his learners through their writings, dialogues and their behaviors. He has the possibility to evaluate them from their productions during the activities and can adapt or modify parts of the course, if it is necessary to start new chapters. The adaptation of educational contents to the learner's profile in a Computing Environment for Human Learning (ILE) is one of the most complex problems to solve. Indeed, the different profiles of learners and their heterogeneity and their different learning styles, returns the development and evolution of such systems difficult. The current goal of several studies is to follow and understand the behavior of the learner uses an ILE during a learning session through its traces. Several virtual learning environments presented on the web, exploiting traces to provide learners with individualized learning space. Unfortunately, these environments do not always offer the possibility to adapt courses to the profile of the learner. In a learning situation, we cannot predict with certainty the plan of a learner or the goal that he seeks to accomplish more during his navigation, we cannot directly observe what a learner knows or does not know, but only to estimate it in a very imperfectly way through their actions and interactions with the system. These traces of the Action types are analyzed and exploited in order to provide indications about his behavior during the learning process. The objective of our work is to propose a representation model which traces to determine indicators Cognitive, Activity and Motivation of the learner during the learning process. The exploitation of these indicators will allow us to propose a hybrid adaptive strategy (automatic or manual) to the learner profile.
Keywords:	Traces, Indicator, Learner, profile, CAM model
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	USAGE OF FIREFLY ALGORITHM IN VIGNERE CIPHER TO REDUCE VARIABLE LENGTH KEY SEARCH TIME
Author:	V.RAJENDRAN, DR.T.PURUSOTHAMAN
Abstract:	Various cryptographic methods rely on optimization techniques to find the key of a given cipher text. A fitness function is defined based on frequency analysis or any other known information. Vignere cipher was crypt analyzed using GA, PSO and other optimization techniques. Firefly algorithm is an optimization algorithm based on the brightness and attraction among fireflies. A fitness function is defined based on frequency of occurrence monograms and bigrams in English. Firefly algorithm is tried on 1 KB of Vignere cipher and it was seen that keyword length ranging from 5 to 20 were found without error and also with less time complexity than GA and PSO.
Keywords:	Cryptology, Vignere cipher, Network Security, PSO, Firefly Algorithm
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	WIND SPEED FORECASTING USING REPTREE AND BAGGING METHODS IN KIRKLARELI TURKEY
Author:	METIN ZONTUL, FATIH AYDIN, GOKHAN DOGAN, SELCUK SENER, OGUZ KAYNAR
Abstract:	In this study, an analysis was performed by examining the wind power potential of Kırklareli province which is in the west of Turkey. Statistical data between 2001 and 2007 was used in this study. The data was obtained from Kırklareli branch of State Meteorological Service. In Kırklareli region, wind speed forecasts regarding the year 2013 were made for windpower plants that are supposed to be built. WEKA tool was used for the performed analyzes. Algorithm which was used for forecasting is REPTree which is decision tree algorithm. There are two basic reasons to use REPTree algorithm. First, it produces better results compared to other machine learning methods, and secondly, the model produced with REPTree has a clear content. For this reason, new information can be gathered by using the tree model. This advantage of REPTree algorithm is combined with Bagging method and average model is generated by using the models produced by new training sets that are derived from the original training set. In this way, the model that will provide the highest accuracy rate is produced. The correlation coefficient value between the real and estimated values is obtained as 0,8154 by applying cross-validation method on the training set. This shows that REPTree can be used along with Bagging method for the wind speed forecasting of the year 2013.
Keywords:	Wind Speed Forecast, Machine Learning, Bagging, REPTree, Time Series Analysis
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	REPRESENTING TEXT DOCUMENTS IN TRAINING DOCUMENT SPACES: A NOVEL MODEL FOR DOCUMENT REPRESENTATION
Author:	ASMAA MOUNTASSIR, HOUDA BENBRAHIM, ILHAM BERRADA
Abstract:	In this paper, we propose a novel model for Document Representation in an attempt to address the problem of huge dimensionality and vector sparseness that are commonly faced in Text Classification tasks. The proposed model consists of representing text documents in the space of training documents at a first stage. Afterward, the generated vectors are projected in a new space where the number of dimensions corresponds to the number of categories. To evaluate the effectiveness of our model, we focus on a problem of binary classification. We conduct our experiments on Arabic and English data sets of Opinion Mining. We use as classifiers Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN) which are known by their effectiveness in classical Text Classification tasks. We compare the performance of our model with that of the classical Vector Space Model (VSM) by the consideration of three evaluative criteria, namely dimensionality of the generated vectors, time (of learning and testing) taken by the classifiers, and classification results in terms of accuracy. Our experiments show that the effectiveness of our model (in comparison with the classical VSM) depends on the used classifier. Results yielded by k-NN when applying our model are better or as those obtained when applying the classical VSM. For SVM, results yielded when applying our model are in general, slightly lower than those obtained when using VSM. However, the gain in terms of time and dimensionality reduction is so promising since they are dramatically decreased by the application of our model.
Keywords:	Document Representation, Text Classification, Opinion Mining, Machine Learning, Natural Language Processing
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	VLSI ARCHITECTURE FOR LIFTING BASED DISCRETE WAVELET TRANSFORM
Author:	DHANABAL R, BHARATHI V , HYMA SOMAN , SAIRA SALIM
Abstract:	A lifting based 2D DWT with efficient folded architecture and parallel scanning is being proposed. The architecture results in lesser hardware complexity and memory requirement due to multiplexing of 2 stages of lifting architecture. The 2D DWT architecture is realized by cascading two 2D processing elements. The coefficients for the lifting stage were chosen according with 9/7 filter. The 1D processing element has a column filter, transposing buffer and a row filter in it. The use of parallel scanning reduces the size of transposing buffer. Combining the intermediate results of row and column, the number of pipelining stages and registers are also reduced. The throughput obtained are 2 input and 2 output per cycle. The critical path for proposed architecture is one Tm.
Keywords:	DWT, VLSI, Wavelet Transform, Architecture
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	MEDICAL IMAGE COMPRESSION BASED ON SET PARTITIONING IN HIERARCHICAL TREES USING QUANTIZED COEFFICIENTS OF SELF ORGANIZING FEATURE MAP FOR MR IMAGES
Author:	S. SRIDEVI1, V.R.VIJAYAKUMAR, V.SUTHA JEBAKUMARI
Abstract:	Medical imaging plays a vital role in medical diagnosis. These medical images available in hospitals and medical organizations occupy a lot of space. The massive use of digitized images has led to the compression allowing economical storage and fast data transfer. Over the years, JPEG compression schemes based on Discrete Cosine Transform have been proposed and standardized. The input image has to be blocked which results in blocking artifacts. In recent years wavelet transform has gained widespread acceptance in image compression. Many compression algorithms using wavelets like EZW, SPIHT and SPECK have been proposed and they can be used for lossy or lossless compression. SPIHT is an efficient compression algorithm which has better performance over the others. In this paper, SPIHT based medical image compression algorithm using the quantized coefficients of Self Organizing Feature Map (SOFM) was brought in and proved to have better performance over existing methods.
Keywords:	SPIHT, SOFM, DWT, Image Compression, PSNR, CR
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	PERFORMANCE ANALYSIS OF MSK MODULATION AND CODING IN ENERGY EFFICIENT SENSOR NETWORK PROTOCOL
Author:	M. SHEIK DAWOOD, R.AISWARYALAKSHMI, G.ATHISHA
Abstract:	A wireless sensor network (WSN) consists of several physically separated sensors to monitor and control physical or environmental conditions. In this paper the role of minimum shift keying modulation scheme along with channel coding is analyzed in energy efficient clustered sensor architecture .The performance comparison of MSK with other modulation is also discussed to increase the energy efficiency at their transceiver and improve the lifetime of sensor nodes. The simulation and mathematical results show the appropriate combination modulation and channel coding to improve the lifetime of energy efficient clustered WSN.
Keywords:	Sensor Network, Energy Efficiency, Lifetime, MSK, Modulation, Error control code, clustering.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	LOW POWER HIGH SPEED CNTFET BASED DIFFERENTIAL ANALOG VITERBI DECODER ARCHITECTURE
Author:	SUJATHA CYRIL, DHARMISTAN K. VARUGHEESE
Abstract:	Differential Analog Viterbi Decoding (DAVD) for Forward-Error-Correction (FEC) is used in channel coding for digital communications. The use of analog circuits to reduce the size and power consumption of channel decoders such as Viterbi decoders has been an active area of research over the recent years. In this paper, differential analog Viterbi decoder architecture is proposed and implemented using 32 nm Carbon Nano Tube FET (CNTFET) transistors. CNTFETs can handle large currents, hence higher driving capacity and faster speed, the current mode architecture using CNTFETs further reduces number of transistors. The major computation blocks like Branch Metric Computation (BMC) and Add-Compare-Select (ACS) are implemented using CNTFET based current mirrors which reduce power and area as well as computing complexity. The differential logic operates at a maximum data rate of 500 Mbps and consumes power 65 times less than the analog Viterbi decoder. The designed decoder is suitable for low power applications.
Keywords:	CNTFET, Viterbi Decoder, Low Power Circuits, Current Mode Circuits, Error Correction
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	THE PREDICTION OF GROUNDWATER LEVEL ON TIDAL LOWLANDS RECLAMATION USING EXTREME LEARNING MACHINE
Author:	NURHAYATI, INDRATMO SOEKARNO, IWAN K. HADIHARDAJA, M. CAHYONO
Abstract:	Groundwater level in the tidal lowlands fluctuates according to space and time. It is influenced by local rainfall or tidal. Tidal lowlands development for agriculture particularly food crops requires proper water management strategies so that the productivity of land and the production of food crops can be optimized. Proper water management must be supported by an accurate prediction system. This research aims to apply extreme learning machine (ELM) which can be used to make a prediction system of groundwater level in tidal lowlands. ELM is a feed forward artificial neural network with a single hidden layer or commonly referred to as single hidden layer feed forward neural networks (SLFNs). ELM has the advantage in learning speed. The result of the ground water level prediction using ELM was better than that using BPANN. Based on these results, the ELM can be used to predict the ground water level in order to assist decision makers in determining water management strategies and the determination of appropriate cropping patterns in the tidal lowlands reclamation.
Keywords:	Prediction, Ground Water Level, Back Propagation, Artificial Neural Network, Extreme Learning Machine
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	AN EFFICIENT LOCATION AND DETECTION (ELD) BASED MOBILE AD-HOC IMPLEMENTATION WITH EMBEDDED SYSTEMS
Author:	RAJARAM.M, Dr.V.SUMATHY
Abstract:	A Mobile Ad-hoc Network (MANET) is a temporary wireless network composed of mobile nodes, in which an infrastructure is absent. If two mobile nodes are within each other’s transmission range, they can communicate with each other directly; otherwise, the nodes in between have to forward the packets for them. Several routing protocols have already been proposed for ad hoc networks. This paper suggests an approach to utilize location information obtained by using DLRDPF (Dynamic located Routing and Detection Protocol Far), if the destination is Remote and DLRPL (Dynamic located Routing and detection Protocol Local), if the destination is local. in this routing scheme affected various attacks. In MANETs, it is difficult to identify malicious attacks as the topology of the network dynamically changes. In this Progress we proposed new efficient dynamic detection scheme for attacks also . Using location information to help routing is often proposed as a means to achieve scalability benefits like Packet delivery ratio, Average delay ,packet loss and Qos in large mobile ad-hoc networks. and detect the attacks . We use the network simulator 2 (ns-2) system to conduct the MANET simulations and consider scenarios for location and detection. and on the Tiny based Real time operating systems.
Keywords:	Adhoc networks, Location, Detection attacks, Scalability benefits, Tiny 2.OS
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	DEVELOPMENT AND VALIDATION OF A QUESTIONNAIRE TO MEASURE GAME INTERFACE PREFERENCES BASED ON CULTURAL VALUES
Author:	RATNA ZUARNI RAMLI, NOR AZAN MAT ZIN, NORAIDAH SAHARI @ASHAARI, SALYANI OSMAN
Abstract:	Culture is a mental model that governs how people act and believe. Individuals with different cultures may have different perceptions about the same object. A general or standard design does not address different perceptions of different players when it comes to the design of a game interface and this may compromise the game intuitiveness or its natural feel. Hence, to address this issue, a model for a game interface with cultural values is proposed, based on past studies. The model consists of space and layout, menu buttons and dialogue or language, and three cultural elements – IDV, UAI and context. To verify the model, a valid and reliable instrument was developed. This paper discusses the development and validation of the instrument which is a questionnaire, to validate the proposed game interface with cultural values model. To validate the questionnaire, a structured interview involving four panels of experts in culture and human computer interaction (HCI) was conducted. Some changes to the questionnaire were subsequently made based on comments from the panels. Face and content validation was done using a focus group consisting of five avid game players. Finally, a pilot study using purposive sampling of 52 respondents was carried out. The calculated reliability value, α = 0.955.The final version of the questionnaire was then validated by all panel members and thus deemed suitable for model verification.
Keywords:	Game Interface; Questionnaire Validation; VSM94; High Context
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	ENSURING DATA CONFIDENTIALITY IN MANET BY COMBINING EMPHATIC CRYPTOGRAPHY TECHNIQUE WITH PSO
Author:	SANDHYA P, DR. JULIA PUNITHA MALAR DHAS
Abstract:	MANET is a dynamically varying network of wireless nodes that may move randomly independent of each other. Security, a serious crisis in MANET has innovative challenges such as data confidentiality and integrity. Malicious nodes or data hackers make packet dropping or interference in the routing messages in the network. To overcome these problems this paper proposes a secure optimized routing system with data confidentiality. Multipath route is optimized by selecting the best path using PSO (Particle Swarm Optimization) algorithm. Malicious nodes are identified by selecting the monitoring nodes derived from the network parameters: throughput bandwidth, and energy. Key management scheme with MD5 hash encryption is proposed to improve the secure data communication. The intent of MD5 algorithm is to generate the hash value for transmitting the data securely through the optimized route path. By simulation results, we show that the proficient of the proposed technique in terms of data confidentiality.
Keywords:	MANET, Data Confidentiality, Encryption, PSO (Particle Swarm Optimization), Malicious Node.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	RETAINING AND INCREASING CUSTOMER PROFITABILITY USING K-MEANS AND APRIORI ALGORITHM
Author:	SUPARTO DARUDIATO, ANINDITO
Abstract:	Appropriate strategy is an absolute must in the tight business competition of today. Many methods are used in business to predict and process data so that information and knowledge needs of the business can be obtained. Data mining is often used as a solution to this problem. Data mining is used to explore the hidden information in the data warehouse, and able to show a pattern of behavior of customers in their daily life associated with the company. K-Means and association rule are two techniques of the many techniques contained in the data mining algorithm that can be used as a basis for analysis to improve profitability.
Keywords:	Data Mining, CRM, K-Means, Association Rules
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	EFFICIENT CENTRIODS BASED CLUSTERING ALGORITHM WITH DATA INTELLIGENCE
Author:	D.JOHN ARAVINDER, DR.E.R.NAGANATHAN
Abstract:	Cluster analysis is important technique to find the similar and dissimilar group in data mining. From two decade of data mining process, most of technique extracts irrelevant knowledge to domain. This is the main aim of this paper. This paper proposes a new centroid based clustering algorithm. And also this paper includes some additional intelligence or measures with clustering process. This measure supported to find the relationship between data objects and clusters apart from distances. This algorithm tests with some synthetic datasets. Experimental results shows domain related clusters and needs to test with real time datasets.
Keywords:	Data Mining, Clustering, K-Means Algorithm, Actionable Clusters
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	BACKPROPOGATION NEURAL NETWORK FOR PREDICTION OF HEART DISEASE
Author:	NABEEL AL-MILLI
Abstract:	Recently, several software’s, tools and various algorithms have been proposed by the researchers for developing effective medical decision support systems. Moreover, new algorithms and new tools are continued to develop and represent day by day. Diagnosing of heart disease is one of the important issue and many researchers investigated to develop intelligent medical decision support systems to improve the ability of the physicians. Neural network is widely used tool for predicting heart disease diagnosis. In this research paper, a heart disease prediction system is developed using neural network. The proposed system used 13 medical attributes for heart disease predictions. The experiments conducted in this work have shown the good performance of the proposed algorithm compared to similar approaches of the state of the art.
Keywords:	Backpropagation, Heart Disease, Neural Network.
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	DEVELOPMENT AND MODELING OF UNMANNED UNDERWATER REMOTELY OPERATED VEHICLE USING SYSTEM IDENTIFICATION FOR DEPTH CONTROL
Author:	ARAS, M.S.M, ABDULLAH, S.S , RASHID, M.Z.A, RAHMAN, A. A, AZIZ, M.A.A
Abstract:	This paper presents the development and modeling of low cost underwater Remotely Operated Vehicle (ROV) for depth control using system identification technique. The ROV was developed by the Underwater Technology Research Group (UTeRG). For Unmanned Underwater Vehicle (UUV), the most crucial issue is the control system. It is needed for the ROV to perform several underwater applications and tasks. In this project, a prototype of the ROV will be developed first. The ROV will be tested on an open loop system to obtain measured input-output signals. Input and Output signals from the system are recorded and analyzed to infer a model. Then, system identification toolbox in MATLAB will be applied to generate a model of the ROV. The experimental testing of ROV only considered the vertical movement. The modeling obtained will be used to design the a suitable controller for depth control. The purpose of depth control is to ensure the ROV to remain stationary at a desired depth by utilizing the pressure sensor as feedback. The simulation studies have been carried out in order to obtain the controller of the ROV. This method is useful to obtain the model of the ROV to design the best controller for depth control. Conventional controller will be used in order to verify the modeling of ROV and gives acceptable performances of system response.
Keywords:	Remotely Operated Vehicle (ROV), System Identification, NI-DAQ card, Pressure Sensor
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text

Title:	USING ANSWER SET PROGRAMMING TO FIND MAXIMUM HEIGHT SPANNING TREES
Author:	MARCO MANNA
Abstract:	The max tree-height of an undirected graph is the longest possible length of a path among all spanning trees of the graph. A maximum height spanning tree of an undirected graph is a spanning tree that has a path of length equal to the max tree-height of the graph. Finding the max tree-height of a graph, or similarly some spanning tree of maximum height, is an NP-hard optimization problem for which efficient optimal procedures have been proposed only for special classes of graphs, and which is not polynomially approximable within any constant factor unless PTIME = NP. The paper presents an elegant yet efficient and succinct logic program in Answer Set Programming for the identification of both the max tree-height and the maximum height spanning trees of a graph.
Keywords:	Answer Set Programming, Declarative Problem Solving, Artificial Intelligence, Spanning Trees, Optimization Problems
Source:	Journal of Theoretical and Applied Information Technology October 2013 -- Vol. 56. No. 1 -- 2013
Full Text