		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 2014 | Vol. 70 No.3

Title:	ENSEMBLE OF CLUSTERING ALGORITHMS FOR ANOMALY INTRUSION DETECTION SYSTEM
Author:	SALIMA BENQDARA, MD ASRI NGADI, JOHAN MOHAMAD SHARIF, SAQIB ALI
Abstract:	Maximizing detection accuracy and minimizing the false alarm rate are two major challenges in the design of an anomaly Intrusion Detection System (IDS). These challenges can be handled by designing an ensemble classifier for detecting all classes of attacks. This is because, single classifier technique fails to achieve acceptable false alarm rate and detection accuracy for all classes of attacks. In ensemble classifier, the output of several algorithms used as predictors for a particular problem are combined to improve the detection accuracy and minimize false alarm rate of the overall system. Therefore, this paper has proposed a new ensemble classifier based on clustering method to address the intrusion detection problem in the network. The clustering techniques combined in the proposed ensemble classifier are KM-GSA, KM-PSO and Fuzzy C-Means (FCM). Experimental results showed an improvement in the detection accuracy for all classes of network traffic i.e., Normal, Probe, DoS, U2R and R2L. Hence, this validates the proposed ensemble classifier.
Keywords:	Intrusion Detection, Ensemble Learning, Voting Ensemble
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	NODE LOCATION ANALYSIS USING RSSI FOR AUTOMATIC POSITION REPORTING SYSTEM
Author:	S.V.Tresa Sangeetha, Dr.S.Ravi, Dr.Uma RajaRam, Dr.S.Radha Rammohan
Abstract:	This paper analyses various connectivity issues encountered when a mobile node identifies an access point with greater signal strength and find a proper node location in the network. Dynamic networks require adaptive policies for optimal performance and guaranteed QoS to support realtime environment. The network connectivity issues of different wireless protocols and standards are discussed with respect to bit rate and the number of users accessing the network. The study is demonstrated with an experimental set up of multiple wireless nodes performing push and pop functions in a common server through the network. The experimental work is extended to specific application like Automatic Position Reporting System (APRS) of remote data logging and a protocol implementation work of packet flow and data structure is presented.
Keywords:	Wireless Network, Access Point (AP), Self Learning Network, Fairness Policy
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	AUTOMATIC CLASSIFICATION OF AUDIO DATA USING GRADIENT DESCENT NEURAL NETWORK BASED ALGORITHM
Author:	LAKSHMI DEVASENA C, M HEMA LATHA
Abstract:	Audio mining is a technique by which the core of an audio signal can be automatically searched and analyzed. This research work addresses feature extraction from audio and audio similarity measures and proposes an algorithm to mine any type of audio data. This Hybrid Algorithm for Audio Mining (HAAM) consists of two different phases. The first phase named Training Phase, takes Training Audio data as input and then Sonogram, Spectrum Histogram, Periodicity Histogram and Fluctuation Pattern for the audio data are calculated. Then the features are extracted using Mel Frequency Cepstral Coefficient (MFCC) and the essential features are reduced from these for further processing. Then, classification is done by using a supervised classification technique. Then the features of the audio files are trained using Gradient Descent Adaptive Learning Back propagation Network. The second phase is the Testing Phase, which takes Testing Audio data as input and then preprocessing is done and the features are extracted. Then classification is done using the findings from the trained data by matching the features of the test audio with the equivalent or closest feature audio classes. The working prototype of this algorithm has been implemented and tested. During the experiments, Instrumental music data have been used as input and the system performed well and classified the input music in an accurate manner and presented the results obtained. The system is suitable for classifying the different types of audio data and can be used in many applications including speech recognition, audio classification in scientific research and engineering, audio data comparison and detection in audio surveillance applications.
Keywords:	Audio Mining, Gradient Descent Neural Network, K-Means Classifier, Mel Frequency Cepstrum Coefficient, Principal Component Analysis
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	A MIDDLEWARE AND POLICY-BASED ADAPTATION FRAMEWORK TO SIMPLIFY SOFTWARE EVOLUTION: AN IMPLEMENTATION ON UNIT TRUST ENTERPRISE SYSTEM
Author:	N.H AWANG, S. SHAHIBUDDIN, W.M.N WAN KADIR
Abstract:	Software evolution needs to be properly controlled to avoid huge problems during maintenance phase. Software needs to evolve to ensure it meets its development purpose. One of promising ways to address the issue of software evolution is via software adaptation. There are 4 main approaches to software adaptation i.e. architecture-based, component-based, agent-oriented and middleware-based. This research is adopting middleware-based approach to software adaptation. An adaptation framework called MiPAF, which uses middleware and policy-based concept is proposed to simplify software evolution. MiPAF comprises 6 components namely Service Manager, Adaptation Manager, Service Infrastructure, Device Controller, Policy Repository and Context Monitor. The use of MiPAF will affect 4 software development phases i.e. requirement, analysis, design, and development. MiPAF runtime is developed to enable adaptation of the device layer of a Unit Trust Enterprise System (UTES). A simple, XML-based policy language is developed to specify what action to be taken when certain condition happens. The adaptation requirements of this system is specified and an adaptation policy is developed according to the requirements. In this implementation, MiPAF runtime is developed using C language and it is installed on workstations together with UTES client. There are 2 adaptation requirements for this implementation. The first requirement is when a passbook printer fail, the system can proceed with printing using another passbook printer without interruption. The second requirement is that when the type of passbook printer is changed, the system should not be impacted. The evaluation is done against 6 evaluation criteria; scalability, context-awareness, performance, usability, heterogeneity, and dynamic-evolveability. MiPAF meets all the mentioned criteria.
Keywords:	Software Evolution, Software Adaptation, Middleware, Policy, Framework
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	AUTOMATED TEST CASE GENERATION USING UML USE CASE DIAGRAM AND ACTIVITY DIAGRAM
Author:	ARUP ABHINNA ACHARYA, PRATEEVA MAHALI, DURGA PRASAD MOHAPATRA
Abstract:	Testing plays a major role for improving the quality of a software product. Due to its iterative and incremental nature it needs special attention. Test case generation is one of the complex activities carried out during testing phase. Generating test cases in the early phases of development life cycle works like a catalyst for model based testing and at the same time efficiently manages time and resources. This paper describes a novel approach for test case generation from UML Activity Diagram (AD) and Use Case Diagram (UCD). At first UCD and AD are converted into Use Case Graph (UCG) and Activity Graph (AG) respectively. The AG and UCG are integrated to form a combined graph called Activity Use Case Graph (AUCG). The AUCG is further traversed to generate test cases. Test cases generated using the combined approach is capable of detecting more number of faults as compared to individual models while keeping intact the total coverage. The proposed approach also reveals faults like execution fault, operational fault and use case dependency fault.
Keywords:	Testing, AUCG, Test Case Generation, Dependency Fault, Operational Faults
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	INVESTIGATING BIOGEOGRAPHY-BASED OPTIMISATION FOR PATIENT ADMISSION SCHEDULING PROBLEMS
Author:	ABDELAZIZ I. HAMMOURI, BASEM ALRIFAI
Abstract:	This paper derives its work from an interest in the development of an automated approach to tackle highly constrained patient admission scheduling problems (PASP). It is concerned with an assignment of patients to bed in an appropriate department in such a way it can maximise medical treatment effectiveness and patients’ comfort. In this paper too, we have investigate a newly created meta-heuristic optimisation algorithm, called Biogeography Based Optimization (BBO) based on the idea of migration of species between different habitats. To evaluate the performance of the proposed method, six instances of PASP data sets were used. The performance of the BBO algorithm was compared with other approaches that in the literature. Experimental results show that, the BBO needs more investigation for improving the obtained results.
Keywords:	Meta-Heuristic. Evolutionary Algorithms. Biogeography-Based Optimization. Patient Admission scheduling. Healthcare.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	AUTOMATED ARABIC ANTONYM EXTRACTION USING A CORPUS ANALYSIS TOOL
Author:	LULUH ALDHUBAYI, MAHA ALYAHYA
Abstract:	The automatic extraction of semantic relations between words from textual corpora is an extremely challenging task. The increasing need for language resources supporting Natural language processing (NLP) applications has encouraged the development of automated methods for the extraction of semantic relations between words. The use of corpus statistical and similarity distribution methods can help in the task of semantic relation extraction between pairs of words. In this paper, we present a pattern-based bootstrapping approach using Arabic language corpora and a corpus analysis tool (Sketch Engine) to extract the semantic relations (antonyms) between word pairs. The algorithm uses LogDice and pattern co-occurrence to classify the extracted pairs into antonyms. Results of evaluation show that our approach is able to extract the antonym relations with a precision of 76%.
Keywords:	Antonym Extraction, Sketch Engine, Arabic Lexicon, Semantic Relation, Arabic NLP
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	EVALUATED REPUTATION-BASED TRUST 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 Modified Reputation-Based Trust model proposed and optimized for security strength. During evaluation of the model with well-known models two security threats (oscillating and collusion) were applied in order to measure the accuracy, scalability, trustworthiness and energy consumption. As a result, the effects of collusion and oscillating on proposed model are minimized and energy consumption for dynamic networks reduced. Also, simulation results show that MRT has better average accuracy and less average path length than other mechanisms, due to the security and energy aware.
Keywords:	Wireless Sensor Networks (WSNs), Collusion, Oscillating, Power Consumption, Trust and Reputation Models
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	VOICE ANALYSIS FOR DETECTING PERSONS WITH PARKINSON’S DISEASE USING PLP AND VQ
Author:	ACHRAF BENBA, ABDELILAH JILBAB, AHMED HAMMOUCH
Abstract:	In order to improve the assessment of speech disorders in the context of Parkinson's disease, we have used 34 voice recordings of sustained vowel / a /, from 34 subjects including 17 patients with Parkinson’s disease. We subsequently extracted from 1 to 20 coefficients of the Perceptual linear prediction (PLP) from each subject. The frames of the PLP were compressed using vector quantization, with six Codebook sizes. We used Leave One Subject Out validation scheme known as (LOSO) and the Support Vector Machines (SVM) classifier with its different types of kernels, (i.e.; RBF, Linear). After viewing the variety of obtained results, we proceeded to a bench of 100 trials. The best average result obtained was 75.79%, and the maximum result obtained was 91.17% using the codebook size of 1.
Keywords:	Voice analysis, Parkinson’s disease, Perceptual Linear Prediction, Vector quantization. Leave One Subject Out, Support Vector Machines.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	ERROR COMPENSATED FIXED WIDTH MODIFIED BOOTH MULTIPLIER FOR MULTIMEDIA APPLICATIONS
Author:	R. MOHAMED NIYAS, N. PRABHAKARAN, N. SATHYA, P. VAISHNAVI, B. MADHUSUDHANA REDDY
Abstract:	Many multimedia and digital signal processing systems are desirable to maintain a fixed format and to allow little accuracy loss to output data. The objective of this paper is to design a fixed width modified booth multiplier with high error performance. And the need to derive an effective error compensation function that makes the error distribution more symmetric and centralized in the error equalized to zero. The compensation circuit is mainly composed of simplified sorting network and this can achieve a tiny mean and mean square error as compared to the other circuits. The odd even sorting networks used for error compensation are composed of appropriately connected comparators. The simplified form of sorting network consist of neither NAND, NOR, AND-OR INVERTER (AOI) and OR-AND-INVERTER (OAI). In fixed width modified Booth multiplication, to reduce the number of partial products by a factor of two, modified booth encoding is used. The software used for the simulation of this circuit is Altera-Quartus II. The RTL code is generated using the above software. The implementation of the circuit is done using DE1 board.
Keywords:	Booth Multiplier, mean square error, partial products
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	MARKOV MODEL FOR DISCOVERING KNOWLEDGE IN TEXT DOCUMENTS
Author:	I.BERIN JEBA JINGLE, Dr. J.JEYA A.CELIN
Abstract:	The digital data knowledge discovery and data mining due to their immense growth have engrossed a great deal of deliberation in recent years. Numerous applications, such as market investigation and business society, can be promoted by use of the information and facts extracted from a bulky amount of data. Text mining is the skill that allows users to mine useful information from a large amount of digital text documents on the Web or databases.Text Mining is the discovery of unknown information, by automatically extracting information from different written resources. This paper deals with the patterns discovery in text documents using the hidden Markov model. In most existing pattern mining in text mining methods, all go through the problems of lack of accuracy and lack of performance. In the proposed system the first progression is pre-processing step which removes the “noise” word. The next development is the HMMs, which is used for pattern extraction and classification of input data. Hidden Markov Model calculates the possibility value between noticed events and unnoticed events. This method can improve the accuracy of evaluating term weights and also used to progress the performance for discovering patterns in text for large databases.
Keywords:	Data mining, HMM, Classification, stemming, Smoothing Technique
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	DETECTION AND TREATMENT OF THE SELF_CROSS IN THE SHRINK PROCESSES OF PARAMETRIC ACTIVE CONTOUR MODEL
Author:	LIU HONGSHEN, WANG NAN, RUAN YUE
Abstract:	The research object of this paper is the self_crosses of contour in parameter active contour model with shrink strategy (PACMS). For studying the object, parameter active contour model is improved to rapidly converge and reduce number of the self_crosses of contour. The concept of self_cross in PACMS is introduced and the influence of it on the evolution of PACMS is presented. With the improved model, the existence of self_cross in PACMS is shown. The treatments of self_cross on contours in the current literatures are analyzed. A model of describing the self_crosses is set up and an improved method of detecting and treating the self_crosses in PACMS is put forward. The experiment results of the new method are given and the comparison among the new method and other methods of detecting and treating the self_crosses are made. The result shows that the new method is more efficient than the other method of detecting self_crosses on contours.
Keywords:	Parametric Active Contour Model, Parameter Active Contour Model With Shrink Strategy, The Self_Cross Of Contour, Detection, Treatment
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	MEASUREMENT STUDY ON PACKET SIZE AND PACKET RATE EFFECTS OVER VEHICULAR AD HOC NETWORK PERFORMANCE
Author:	L. A. HASSNAWI, R.B. AHMAD, MUATAZ H. SALIH, M.N. MOHD WARIP, M. ELSHAIKH
Abstract:	A vehicular ad hoc network (VANET) is a type mobile ad hoc network which is developed to increase physical safety of vehicles’ derivers. Many parameters affect the performance of VANET. Packet size and packet rate are two important parameters that need to be considered when using VANET. Different values of these parameters provide different network performance. Using large packet size leads to reduce packet header overhead, but may leads to increase packet loss ratio due to packets collision. Therefore the values of these parameters must be chosen carefully. This paper presents an investigation and analysis of using different packet sizes and different packet rates on a VANET consists of wireless nodes distributed along a highway. The investigation and analysis were performed under varying network environments and for several different evaluation metrics. It is a conclusion of this study that using small packet size gives better network performance than using large packet size. Moreover, the slow packet rate can provide better network performance than using faster packet rate in highway VANET.
Keywords:	MANET, Packet Size, Packet Rate, Throughput, VANET
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	SIMULTANEOUS COORDINATED AND TUNING OF PSS FOR A MULTIMACHINE POWER SYSTEM USING A NEW HYBRIDIZATION (GA-GR) VIA A MULTI-OBJECTIVE FUNCTION
Author:	A. CHOUCHA, L. CHAIB1 , S. ARIF1, L. MOKRANI
Abstract:	This work presents a new coordinated and robust tuning procedures of power system stabilizer PSS using a novel hybridization technique to damp out power system oscillations. This hybridization is based a combination between stochastic Genetic algorithm (GA) methods and deterministic methods (gradient); it is called GA-GR, and even between themselves stochastic methods genetic algorithm and simulated annealing (GA-SA). The proposed approach is used for a multi-objective function based on the real part of eigenvalues and the damping factor, to search for optimal stabilizer parameters. To examine the effectiveness and robustness of this tuning approach in enhancing the stability of power systems, modal analysis and nonlinear simulations have been carried out on New England/New York interconnected network system 68-bus, 16-machine power system.
Keywords:	Genetic Algorithm (GA), Gradient Method, Modal Analysis, Power System Stabilizer, Multimachine Power System, Small Signal Stability.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	DATA PROCESSING METHODS IN MULTIMEDIA HOME PLATFORM APPLICATIONS FOR EARTHQUAKE EARLY WARNING OF POTENTIALLY TSUNAMI SERVICES BASED INTERACTIVE DIGITAL TELEVISION
Author:	SUHARTONO, ALI MAHMUDI
Abstract:	Earthquake early warning service for tsunami is important for the public. On one side the service cannot be easily accessed by the public especially television users. On another side the development of television technology, especially digital television, should be much easier to access. The purpose of this research is to make the method of processing data in Multimedia Home Platform (MHP) Applications for Earthquake Early Warning of Potentially Tsunami Services. Earthquake and weather data are taken from the web site Application Programming Interface (API) by The Meteorology, Climatology, and Geophysics (BMKG) in Indonesia. The research method is parsing techniques eXtensible Markup Language (XML) with the Document Object Model (DOM). The time interval for data collection from the Web site of BMKG uses the method of Systematic Sampling. Therefore, MHP applications can update Earthquakes and weather data in real-time in a specified interval. The results of XML parsing form of tsunami potential earthquake data are recorded by MHP applications into file storage. The findings show that MHP applications can display earthquake early warning of potentially Tsunami information to users of television accordance with BMKG website in real time.
Keywords:	MHP application, eXtensible Markup Language, Document Object Model, Systematic Sampling
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	GENERALIZED FREQUENCY DIVISION MULTIPLE ACCESS ALLOCATION SCHEME FOR LTE-A
Author:	MOHAMMED MELOOD A. ABDASED, MAHAMOD ISMAIL, ROSDIADEE NORDIN
Abstract:	Frequency Division Multiple Access (FDMA) is one of the important features of Long Term Evolution Advanced (LTE-A). For LTE-A downlink, Orthogonal FDMA (OFDMA) scheme is used to provide frequency orthogonality. Whereas, for uplink, Signal Carrier FDAM (SC-FDMA) is preferred since it provides improved PAPR performance over OFDMA. Interleaved FDMA (IFDMA) and Localized FDMA (LFDMA) are forms of SC-FDMA usually used in LTE-A. User subcarrier allocation method is the main distinction between IFDMA and LFDMA schemes. Users are allocated destributed frequency carriers in IFDMA while they are allocated localized carriers in LFDMA. Whereas IFDMA scheme provides better PAPR performance over LFDMA scheme, the latter has lower complexity requirements. In this paper a new user subcarrier allocation scheme is introduced. The proposed scheme provides a variable interleaved allocation of subcarriers in the bandwidth, hence it is named Generalized FDMA (GFDMA). This variable interleaved allocation scheme made the transition from IFDMA to LFDMA to be seamless. Theoritical derivation of the proposed scheme shows that both IFDMA and LFDMA are subclasses of GFDMA. Simulation results of the proposed GFDMA show that the signal PAPR calculated varies according to the interleave level selected. The simulation has been conducted for different QAM modulation schemes and bandwidths. In all the cases, GFDMA PAPR performance is in good match to the calculated IFDMA and LFDMA PAPR. Moreover, further enhancement in GFDMA PAPR is achieved as the number of users in a given bandwidth increased.
Keywords:	SC-FDMA, LTE-A, IFDMA, LFDMA, GFDMA
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	CURRENT STATE OF ANTI-PHISHING APPROACHES AND REVEALING COMPETENCIES
Author:	HIBA ZUHAIR ZEYDAN, ALI SELAMAT, MAZLEENA SALLEH
Abstract:	Phishing has become a substantial threat for internet users and a major cause of financial losses. In these attacks the cybercriminals carry out user credential information and users can fall victim. The current solution against phishing attacks are not sufficient to detect and work against novel phishes. This paper presents a systematic review of the previous and current research waves done on Internet phishing mitigation in different areas of expertise and highlighted phishing attacks types and some existing anti-phishing approaches. Further the discussion about novel phishes and identify the elements of issues highlighted. The review can be valuable source of information to find and identify recent gap and challenges to fulfill the security flaws.
Keywords:	Anti-phishing, detection, novel, credentials, client
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	A WEB SITE USABILITY MEASURE USING NAVIGABILITY MAP METRIC
Author:	SANDEEP KUMAR PANDA, SANTOSH KUMAR SWAIN, RAJIB MALL
Abstract:	We propose a website navigability map metrics suite. To evaluate a large scale website, use of website navigability map metrics opens up the potential of employing intelligent tools. We propose a set of four metrics associated with navigability rating based upon computing site navigability map complexity. To validate our proposed metrics we have evaluated the Cyclomatic complexity of 10 electronic commerce websites. We have conducted empirical studies to study the effectiveness of our proposed metrics.
Keywords:	Navigability Map Metrics, Cyclomatic Complexity, Intelligent Tool, Electronic Commerce
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	TRUST BASED AD HOC ON DEMAND DISTANCE VECTOR ROUTING PROTOCOL AGAINST WORMHOLE ATTACK
Author:	N SATHEESH, Dr. K. PRASADH
Abstract:	Mobile Ad hoc Networks (MANET) consists of mobile devices that communicate with each other without any predefined infrastructure/centralized administration. In network nodes can join or leave a network freely, MANETs are vulnerable to unauthorized data manipulation as it does not verify user identity before ensuring data access. Thus it is challenging to design security mechanisms that protect MANETs from routing attacks in the presence of malicious nodes. This study proposes a trust based Adhoc On-demand Distance Vector (AODV) protocol. Experiments were conducted in two scenarios and the results proved that the new method outperformed traditional AODV.
Keywords:	Mobile Adhoc Network (MANET), Adhoc On-demand Distance Vector (AODV), Routing, Trust, Wormhole attack
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	A NEW APPROACH FOR GENERATING EXERCISES BASED ONTOLOGIES: A CASE STUDY OF COURSES IN MATHEMATICAL ANALYSIS
Author:	IMANE LMATI, HABIB BENLAHMAR, NACEUR ACHTAICH
Abstract:	We present in this paper a methodology to generate an exercise model from the mathematical content of analysis taught in high school and university. The approach allows to a non-computer designer (teacher, educationalist ...) to set the parameters of a pedagogical object PO (Theorem, Definition ...) and to dynamically generate instances of the model by exploiting the semantic relations of PO with other pedagogical objects of mathematical corpus.
Keywords:	Automatic Generation Of Exercise, Evaluation, Ontology.
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	MODELING CREDIBILITY ASSESSMENT AND EXPLANATION FOR TWEETS BASED ON SENTIMENT ANALYSIS
Author:	DWI H. WIDYANTORO & YUDI WIBISONO
Abstract:	Credibility is one of the main issues when dealing with information obtained from Online Social Networks (OSNs). Although a significant number of prior works have addressed many issues in this topic, only a few that have worked on methods for automatic credibility measurement for OSN messages and almost none who has addressed a specific problem in explaining the credibility information. This paper proposes a new approach for modeling credibility of tweets and explaining it to users. We model tweet credibility based on other independent tweet contents that support and oppose the topic issue in question. We also consider the opinions of tweets’ followers who either confirm or deny, along with their reputations. This method is based on assumption that the more community is who agree with the claim, the more credible is the claim. Explanation of the credibility measure is based on the tweet content itself. We provide users with representative tweets that can be progressively zoomed-in for more detail explanation. To achieve this goal, all tweets are hierarchically structured and tweet representatives on each node are selected from the ones that are most similar to the centroid. Our evaluation results indicate the feasibility of the proposed methods.
Keywords:	Credibility Assesment, Credibility Explanation, Online Social Netwok, Tweet, Sentiment Analysis
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	AN EFFECTIVE SCHEDULING OF MULTIPLE SOURCE NODES IN MANET USING DEMPSTER-SHAFTER HYPOTHESIS
Author:	R.M.CHAMUNDEESWARI , DR P SUMATHI
Abstract:	A Mobile Ad-hoc network (MANET) is built without any central control point such as a base station. Partially observable Markov decision process (POMDP) multi-armed bandit problem solved continuous user authentication and intrusion detection systems (IDs) for large network with different nodes. But POMDP did not deal with higher number of nodes’ states for performing the scheduling process in MANET. Maximum-Residual Multicast Protocol (MRMP) based on the independent choice of transitional nodes provided loop-free tree and was theoretically optimal in minimizing the residual energy. However, multiple sources were not considered simultaneously for scheduling process using MRMP. To effectively schedule multiple source information in MANET, Distributed Scheduling Decision (DSD) scheme is proposed in this paper. In DSD scheme, the source node to be broadcasted is dynamically selected to handle higher level of security while transferring data packets with minimal residual energy consumption states. DSD Scheme uses the Dempster-Shafter Hypothesis for multiple source node scheduling process. The DSD scheme with Dempster-Shafter Hypothesis derives the rule for multiple sources, with the confidence value, thereby ignoring the contradictory values using the normalization factor. The normalization factor in DSD scheme detects the intruded nodes with the aid of contradictory values. The normalization factor improves the scheduling efficiency in the distributed mobile network and increases the decision accuracy in MANET. Simulation work is carried out on analyzing the DSD scheme performance on the factors such as false positive rate, time taken on scheduling the packets and decision control overhead.
Keywords:	Distributed Scheduling Decision, Confidence Value, Dempster-Shafter Hypothesis, Mobile Ad-Hoc Network, Normalization Factor, Residual Energy
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	A PIXEL INTERPOLATION TECHNIQUE FOR CURVED HAIR REMOVAL IN SKIN IMAGES TO SUPPORT MELANOMA DETECTION
Author:	T Y SATHEESHA D SATYANARAYANA M N GIRIPRASAD
Abstract:	Melanoma Insitu is one of the most earliest perilous forms of skin cancer. These cancerous growths develop when unrepaired DNA damage to skin cells (most often caused by ultraviolet radiation) triggers mutations (genetic defects) that lead the skin cells to multiply rapidly and form malignant tumors. As there is no effective treatment for advanced melanoma, recognizing the lesion at an early stage is crucial for successful treatment. This lead to the development of several computer-aided methods to assist dermatologists. While diagnosing, hair occlusion caused algorithms to fail to identify the correct lesion in skin, and caused errors in the results. Removing hairs without altering the lesion in skin images is important to effectively apply detection algorithms. The challenge is to develop fast, precise and robust algorithms for the removal of hairs without altering the lesion in skin images. Hence, it leads to the techniques of image processing by identifying hair pixels within a binary image mask using the Pixel Interpolation Technique. The Pixel Interpolation Technique was adapted to find a quadratic curve which detects curved hairs in the image mask for removal and replacement through pixel interpolation. MATLAB [12] gives the platform to perform tests rapidly on both simulated and actual images for implementing this. Overall the quadratic Radon formula for Pixel Interpolation works nicely in being able to detect curves in the image and ignore the majority of image spots which are considered noise.
Keywords:	Median filter, Pixel Interpolation Techniques, Melanocyte
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	THE OPTIMAL QUANTIZATION MATRICES FOR JPEG IMAGE COMPRESSION FROM PSYCHOVISUAL THRESHOLD
Author:	FERDA ERNAWAN , SITI HADIATI NUGRAINI
Abstract:	The JPEG image compression method has been widely implemented in digital camera devices. The quantization process plays a primary role in JPEG image compression. The quantization process is used to determine the visibility threshold of the human visual system. The quantization tables are generated from a series psychovisual experiments from several angle points of experimental views. This paper proposes psychovisual threshold through quantitative experiments for JPEG image compression. This experiment investigates the psychovisual threshold based on the contribution of DCT coefficients on each frequency order to the reconstruction error. The average reconstruction error from incrementing DCT coefficient is investigated to produce a primitive psychovisual threshold. The psychovisual threshold is designed to give an optimal balance between quality of image reconstruction and compression rates. A psychovisual threshold is obtained to generate new quantization tables for JPEG image compression. The performance of new quantization tables from the psychovisual threshold are analyzed and compared to the existing default JPEG quantization tables. The experimental results show that the new quantization tables from the psychovisual threshold produce higher quality of image reconstruction at lower average bit-length of Huffman code than default JPEG quantization tables.
Keywords:	JPEG compression, Psychovisual Error Threshold, Quantization Matrices Generation
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	WEB STRUCTURE MINING FOR USERS BASED ON A HYBRID GA/PSO APPROACH
Author:	B. RAJDEEPA , DR. P. SUMATHI
Abstract:	Web Mining is a demanding task that looks for Web access model, Web structures and the reliability and dynamics of the Web contents. It offers capable Web Personalization, System development, Site alteration, Business Intelligence and Usage Characterization. A latest approach is offered for the estimation of the web site hyperlink structure, where a web user advantage utility function is planned based on known assumptions. The aspire of this work is to propose and get better the Web Structure according to an effectiveness criterion. The frequencies of procedure and time division to click on a link are utilized for constructing the web user utility. Researching probabilistic behaviours have permitted quality development of the hyperlink structure, using a Hybrid GA/PSO. The planned methodology is tested on a real web site and the results are interpreted using the web user benefits by links.
Keywords:	Web mining, web structure mining, web content mining, Hybrid GA/PSO
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text

Title:	APPLICATION OF FEAST (FEATURE SELECTION TOOLBOX) IN IDS (INTRUSION DETECTION SYSTEMS)
Author:	MENDOZA PALECHOR FABIO, DE LA HOZ CORREA EDUARDO, DE LA HOZ MANOTAS ALEXIS
Abstract:	Security in computer networks has become a critical point for many organizations, but keeping data integrity demands time and large economic investments, in consequence there has been several solution approaches between hardware and software but sometimes these has become inefficient for attacks detection. This paper presents research results obtained implementing algorithms from FEAST, a Matlab Toolbox with the purpose of selecting the method with better precision results for different attacks detection using the least number of features. The Data Set NSL-KDD was taken as reference. The Relief method obtained the best precision levels for attack detection: 86.20 %( NORMAL), 85.71% (DOS), 88.42% (PROBE), 93.11 %( U2R), 90.07(R2L), which makes it a promising technique for features selection in data network intrusions.
Keywords:	Feature Selection Toolbox (FEAST), Data-Set, Security, Attacks, Networks
Source:	Journal of Theoretical and Applied Information Technology 31^st December 2014 -- Vol. 70. No. 3 -- 2014
Full Text