		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
September 2014 | Vol. 67 No.1

Title:	A PROFICIENT LOW COMPLEXITY ALGORITHM FOR PREEMINENT TASK SCHEDULING INTENDED FOR HETEROGENEOUS ENVIRONMENT
Author:	D. I. GEORGE AMALARETHINAM, P. MUTHULAKSHMI
Abstract:	The major component of any computing system is the scheduling technique that coordinates the entire system. Heterogeneous environments like grid computing environment provide the accessibility to use wide range of resources that are located around the world. In such environment resource management becomes a complex issue due to various factors like high computational demand, diversity among the tasks, heterogeneity of resources, and heterogeneity of vendors who offer services, dynamic nature of resources. An effective scheduling may increase the efficiency of resource management systems. This paper addresses a grid scheduling algorithm. The algorithm is devised to schedule the tasks on available resources. The performance of the algorithm has been evaluated for arbitrary and regular graphs. The algorithm and the compared algorithms are implemented in Java. The algorithm begins by grouping the tasks. Then tasks from various groups are compared and prioritized for scheduling. The results show that the proposed algorithm outperforms the existing algorithms. The test results of the algorithm justify that the algorithm encourages maximum utilization of resources, minimized makespan and balanced load across resources.
Keywords:	Resource Finalizing Factor, Load Balancing, Schedule Length, Quick Finish Time, Prominent Parent, Promising Successor.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	MONEY LAUNDERING ANALYSIS BASED ON TIME VARIANT BEHAVIORAL TRANSACTION PATTERNS USING DATA MINING
Author:	G.KRISHNAPRIYA M.C.A., M.PHIL, Dr.M.PRABAKARAN
Abstract:	Money laundering a suspicious fund transfer between accounts without names which affects and threatens the stability of countries economy. The growth of internet technology and loosely coupled nature of fund transfer gateways helps the malicious user’s to perform money laundering. There are many approaches has been discussed earlier for the detection of money laundering and most of them suffers with identifying the root of money laundering. We propose a time variant approach using behavioral patterns to identify money laundering. In this approach, the transaction logs are split into various time window and for each account specific to the fund transfer the time value is split into different time windows and we generate the behavioral pattern of the user. The behavioral patterns specifies the method of transfer between accounts and the range of amounts and the frequency of destination accounts and etc.. Based on generated behavioral pattern , the malicious transfers and accounts are identified to detect the malicious root account. The proposed approach helps to identify more suspicious accounts and their group accounts to perform money laundering identification. The proposed approach has produced efficient results with less time complexity.
Keywords:	Money Laundering, Data Mining, Behavior Patterns.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	DETECTION OF OBJECTS USING FISHER SVM WITH MODIFIED ADABOOST CLASSIFICATION TECHNIQUE
Author:	P.SANTHI, V.MURALI BHASKARAN
Abstract:	The object detection is a very important technique in computer vision. This detection is mainly used in many applications like military, satellite image mining, medical and etc. This paper proposes the object detection based on data clustering methods in region based segmentation and shape feature. In existing, most of researchers are using the k-means and fuzzy k-means for clustering and it uses the SVM and Adaboost classifiers for object classification. Here each cluster needs the own centric and distance calculation for clustering. The main disadvantage of this technique is distance calculation between the pixels. This distance calculation technique does not produce the efficient result in clustering. In classification, SVM classifier needs more parameters for increasing the efficiency and adaboost is more noise sensitivity. To avoid these drawbacks, the region based segmentation using non Euclidean distance measure for clustering and combined Fisher SVM with modified adaboost algorithm is used for object classification. This result shows the region based segmentation and object classification of an image. Finally, the performance analysis graph shows the increased efficiency of proposed algorithm.
Keywords:	Detection, Clustering, Classification, Segmentation, Non-Euclidean Distance, Fisher SVM.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	A NOVEL HEURISTIC BASED CLUSTERING FOR MOBILE AD HOC NETWORKS
Author:	G.R.SREEKANTH, Dr. R.C. SUGANTHE
Abstract:	Mobile Ad hoc Network (MANET) is a set of mobile nodes that are infrastructure-less and capable of functioning without the existence of centralized co-ordination. MANETs are helpful in places that have no infrastructure for communications or when that infrastructure is destroyed. The constrained resources in the ad hoc networks have made designing of an efficient and reliable routing a very challenging problem. A smart routing is required to efficiently make use of these constrained resources and also adapting to the dynamic nature of the network. Clustering is one of the approaches for regulating the routing process. Partitioning the network into number of interconnected substructures is called clustering and those substructures are called clusters. The dynamic and unstable nature of the mobile nodes makes it difficult for the cluster formation and constrained resources restrict the determination of clusterheads for each cluster. A large number of approaches have been proposed for the election of clusterheads. In this paper, a new method has been proposed for clusterhead selection using geometric mean by considering multiple factors. The simulation results prove that the proposed method results stable clusters with lower clusterhead change rate and re-affiliation rate than other existing algorithms.
Keywords:	Ad hoc networks,Routing, Clusterhead, Weight Based Clustering
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	COMPLEX WAVELET TRANSFORM BASED DENOISING AND RESOLUTION ENHANCEMENT OF NOISY IMAGES
Author:	V.JAYARAJ, D.EBENEZER
Abstract:	A dual tree complex wavelet transform (DT -CWT)based directional interpolation scheme for denoising of noisy images is proposed . The problems of denoising and interpolation are modeled as to estimate the noiseless and missing samples under the same framework of optimal estimation. Initially, DT -CWT is used to decompose an input low-resolution noisy wage irito low and high frequency subbands. The high- frequency subband images are interpolated by linear minimum mean square estimation (LMMSE) based interpolation, which preserves the edges of the interpolated images. For each noisy LR image sample, we compute multiple estimates of it along different directions and then fuse those directional estimates for a more accurate denoised LR image. The estimation parameters calculated in the denoising processing can be readily used to interpolate the missing samples. The inverse DT-CWT is applied on the denoised input and interpolated high frequency subband images to obtain the high resolution image. Compared with the conventional schemes that perform denoising and interpolation in. tandem, the proposed DT -CWT based noisy image interpolation method can reduce many noise-caused interpolation artifacts and preserve well the image edge structures. The visual and quantitative results show that the proposed technique outperforms many of the existing denoising and interpolation methods.
Keywords:	Complex Wavelet Transform, LMMSE, Denoising
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	A FULL CUSTOM MAC USING DADDA TREE MULTIPLIER FOR DIGITAL HEARING AIDS
Author:	ANANDI. V , DR. RANGARAJAN . R
Abstract:	The ultra-low power requirements of emerging implantable and wearable biomedical devices, necessitates, novel power management schemes. In this paper, we focus our attention on large DSP data path operators such as multipliers and MAC circuits, where lowering the energy per operation is of greater importance. These form the heart of a majority of commercial DSP Processor data path units. We examine architectural choices for merged MAC circuits and formulate a high-speed/low-power MAC architecture.An efficient hardware architecture for Multiply Accumulate (MAC) unit based on a modified Dadda tree multiplier is proposed and validated in full custom environment in standard cell 180nm technology. The partial products reduction block is completely designed using the novel binary compressors and the addition module is implemented using a new less complex modified full adder based on XNOR. Feeding the bits of the accumulated operand into the summation tree before the final adder helps to increase the speed .The final adder is implemented using ripple carry adder. The resulting MAC is implemented and compared with the existing low power designs. The simulation results show that the proposed implementation is faster and consume less power than similar implementations making it a viable option for efficient designs. The 32x32 bit MAC unit designed using proposed full adder as the basic building block gave a power saving of 24.27% over 32 bit MAC designed using SERF full adder and 35.07% power savings over 32 bit MAC designed using conventional 28T full adder.
Keywords:	Wallace, Compressor, Low power, MAC, SERF full adder
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	CERTAIN ANALYSIS ON EEG FOR THE DETECTION OF EOG ARTIFACT USING SYMLET WAVELET
Author:	K.YASODA , DR.A.SHANMUGAM
Abstract:	This paper presents a statistical method for identification of ocular artifacts in the electroencephalogram (EEG) records. The occurrence of artifacts in EEG signals is due to various factors, like power line interference, EOG (electro-oculogram) and ECG (electrocardiogram). The identification of ocular artifact from scalp EEGs is mandatory for both the automated and visual analysis of underlying brainwave activity. These noise sources increase the difficulty in analyzing the EEG and obtaining clinical information. For this reason, it is necessary to design a procedure to decrease such artifacts in EEG records. Here for identification of ocular artifacts, the Stationary Wavelet Transform (SWT) with symlet as a basis function is used and without using the reference of EOG channel the artifacts has been identified. Using this statistical approach, the artifact ocular zones are very easily identified.
Keywords:	EEG, ARTIFACTS, EOG, SACCADES , SWT
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	METADATA BASED CLUSTERING MODEL FOR DATA MINING
Author:	T. NADANA RAVISHANKAR, R. SHRIRAM
Abstract:	As the information flooding onto worldwide web is growing fast, it is very difficult to find the hidden knowledge from huge data stored. In traditional clustering techniques, the task for clustering algorithm is to find the relevant data, describing relationships among the elements between two input datasets. During unsupervised learning process, metadata may play a significant role in the context of data retrieval. In this work, we proposed a methodology of metadata based clustering model (MBCM) for large datasets. The proposed model is validated with few standard datasets like IEEE, ACM and Cluto etc. Experimental results show that it is possible to achieve better cluster quality without significant overhead in terms of execution time. Finally, the performance of our proposed model is evaluated using F-measure and the performance of our method is compared with existing clustering models.
Keywords:	Metadata, clustering, data mining, dataset, K medoids.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	INTRUSION DETECTION SYSTEM: TIME PROBABILITY METHOD AND HYPERBOLIC HOPFIELD NEURAL NETWORK
Author:	JABEZ J, Dr.B.MUTHUKUMAR
Abstract:	Nowadays, high level security maintenance between the two companies is the significant issue when they are communicating between them. However, the goal of achieving complete secure communication between those companies communicating over the internet with various networks is still lacked by the following factors such as misuses and intrusions. Thus, the Intrusion Detection Systems are very important components to detect these types of attacks. There are various approaches being utilized to these intrusion detections, but any of the systems so far is not completely flawless. The proposed framework utilized novel methods such as time probability based pattern detection method and Hyperbolic Hopfield Neural Network for detect the intrusion from the real time network datasets. The experimental results shows our proposed framework is obtained better results rather than other frameworks.
Keywords:	Data Mining, Intrusion Detection Systems (IDS), Network Security, Anomaly Detection, Time probability Method, Hyperbolic Hopfield Neural Network (HHNN).
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	A NOVEL DIFFERENCE EQUATION REPRESENTATION FOR AUTOREGRESSIVE TIME SERIES
Author:	B.SELVARAJ, M.RAJU, M.THIYAGARAJAN
Abstract:	The major components of the time series are the long term trend, the short term trend, cyclic variation and irregular fluctuations. Various attempts have been made to give necessary conditions for processing the specific components. Here we take necessary conditions to predict the asymptotic behavior of the time series using second order difference of the combinations of observations obtained from a general time series. Specific illustrations are given to authenticate our claim.
Keywords:	Secular Trend, Time Series, Difference Equations, Second Order Forward Difference, Asymptotic Behavior, Numerical Data.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	EXPERIMENTAL STUDY ON HIGH PERFORMANCE SELF-COMPACTING CONCRETE USING RECYCLED AGGREGATE
Author:	M.SEETHAPATHI, S.R.R.SENTHILKUMAR, K.CHINNARAJU
Abstract:	In this article, attempt has been made to improve the performance of self compacting concrete using recycled coarse aggregate. Self compacting concrete has significant environmental advantages in compaction to the vibrated concrete. Absence of noise and vibrations during installing provides healthier working environment. In general, there is a scarcity of coarse aggregate throughout the world. Consumption of large amount of coarse aggregate affects the environment. For the purpose of reducing the consumption of coarse aggregate there is a need for an alternative coarse aggregate arises. Recycled aggregates are obtained from the demolition of buildings, culverts and also by-products from the industries. Hence, partial replacement of coarse aggregate by recycled aggregate is researched in this article, in view of consuming the ecological balance. The fresh and hardened properties of Self Compacting Concrete (SCC) using recycled concrete were evaluated. Four series of SCC mixtures were prepared with maximum of 30% of coarse recycled aggregates. The cement content was kept constant for all concrete mixtures. The SCC mixtures were prepared with 0, 10, 20 & 30% of recycled coarse aggregate. The strength test namely, Compressive Strength Test, Split Tensile Strength Test and Flexural Strength Test are carried out in this investigation. To test the characteristics of self compacting concrete, Slump cone test, J – ring test, L – box test were conducted to test the characteristic of SCC. There is an improvement in the strength of self compacting concrete by using recycled coarse aggregate, maximum of 30% is better than concrete with natural aggregates.
Keywords:	Self Compacting Concrete, Recycled Coarse Aggregate, Fresh Properties, Mechanical Strength
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	INDIAN RESEARCH OUTPUT ON MEMS LITERATURE USING SCOPUS DATABASE : A SCIENTOMERIC STUDY
Author:	AL.BATHRINARAYANAN, DR. M. TAMIZHCHELVAN
Abstract:	The study explores the research output of MEMS literature from 1970 to 2013, data collected from Scopus database. The total number of publications has been identified as 294573 records among Indian contribution were 8050 records. The Indian contribution has been analysed and tabulated in this paper, from the study, 2.73 % (8050 items) by Indian authors, growth of publications from 1970 to 2013, author collaboration is single authored 11.4%, remaining are collaboration in nature, the length of the articles was counted by pages which confirms that most of the articles are in range of 6 to 10 pages.
Keywords:	Bibliometrics, MEMS, Authorship Pattern, Scientometrics, Scopus database
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	IMAGE RETRIEVAL USING MULTI TEXTON CO-OCCURRENCE DESCRIPTOR
Author:	AGUS EKO MINARNO, NANIK SUCIATI
Abstract:	One of many method for image retrieval is Multi Texton Histogram (MTH) that incorporated feature extraction technique. Though the MTH is able to represent the image very well, it’s still has weaknesses. First, the MTH is only using local features to represent image. Second, in the process of pixel pair detection using texton, there is information missing that caused image representation may degrade. This study proposes a new method in order to extract image features for the image retrieval system. The proposed method is named Multi Texton Co-Occurrence Descriptor (MTCD). The MTCD is extracting color, texture and shape features simultaneously using texton, and then calculating image representation globally using Gray Level Co-occurrence Matrix (GLCM). This study used 300 Batik images and 15000 Corel images as datasets. Image similarity is calculated using Canberra and MTCD performance is measured using precision and recall. Our experiments show that by adding 2 new textons and GLCM, the precision rate is increased by 2.86% for Batik dataset, by 3.40%for Corel 5,000 and by 3.06% for Corel 10,000. We conclude that MTCD performance is superior than MTH.
Keywords:	Batik, Image retrival, Texton, Gray Level Co-occurrence Matrix
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	MULTICAST ENABLED VERTICAL HANDOVER TECHNIQUE FOR HETEROGENEOUS WIRELESS NETWORKS
Author:	A.PRITHIVIRAJ, K.KRISHNAMOORTHY, K.JAYA BHARATHY
Abstract:	In the subsequent generation of wireless networks, mobile nodes can move across heterogeneous networks and gets the best connectivity using multiple access interfaces. The network based protocol like Proxy Mobile IPv6 (PMIPv6) gives better performance when compared with the host based protocols since the serving network in PMIPv6 manages the mobility management on behalf of the mobile node (MN). The wireless Internet services are commonly accessible, when mobile nodes able to use different Internet services without any limitation. Though, if a mobile node uses different wireless networks, much limitation occurs, when they move a network different from each other. Many parameters such as packet loss, handover latency and delay affects the overall handover performance during the vertical handover process. However, there are many existing techniques to conquer, but still, it’s a challenging task. This paper enhances the functionality of PMIPv6 by introducing a multicast enabled handoff technique to improve the performance during handover with minimum delay by eliminating the false handover initiation and provide seamless handover among heterogeneous wireless networks. The obtained simulation results show a reduction in packet loss and handover latency which improves the handover performance. It also addresses the out of sequence packet problem.
Keywords:	PMIPv6, Heterogeneous networks, Multicast manager, Packet loss, Handover Latency.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	REDUCING DISTRIBUTED URLS CRAWLING TIME : A COMPARISON OF GUIDS AND IDS
Author:	I. SHAKIR, S. ABDUL SAMAD, H. BURAIRAH, G. PRAMUDYA ANANTA, S. SUHAILAN
Abstract:	Web crawler visits websites for the purpose of indexing. The dynamic nature of today’s web makes the crawling process harder than before as web contents are continuously updated. In addition, crawling speed is important considering tsunami of big data that need to be indexed among competitive search engines. This research project is aimed to provide survey of current problems in distributed web crawlers. It then investigate the best crawling speed between dynamic globally unique identifiers (GUIDs) and the traditional static identifiers (IDs). Experiment are done by implementing Arachnot.net web crawlers to index up to 20000 locally generated URLs using both techniques. The results shown that URLs crawling time can be reduced up to 7% by using GUIDs technique instead of using IDs.
Keywords:	Distributed systems, Web Crawler, GUID, Search Engine.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	DELAY SENSITIVE OPPORTUNISTIC AND HABITUAL ROUTING IN WIRELESS MULTIMEDIA SENSOR NETWORKS
Author:	G.VITHYA, B.VINAYAGASUNDARAM
Abstract:	Heterogeneous Wireless Multimedia Sensor Network (WMSN) is a delay prone network requires an energy entropy model to overcome delay during multimedia packet transmission. The core idea of this work is to avoid delay by determining the next hop of a node based on factors such as, residual energy, success ratio and time taken to deliver a packet. The proposed Transport Layer algorithm called Delay Sensitive Opportunistic and Habitual Routing Protocol (DSOHRP) provides an optimized path between the sender and receiver by using delay sensitive constraints in the holistic network. Another key factor that is satisfied with this approach is Load Balance. Load balance is achieved by transmitting packets on the path, based on the opportunistic routing feature exuded in the proposed algorithm. This work is an algorithmic approach to maximise the Network life time and minimize the delay by choosing two optimal paths for the transfer
Keywords:	QOS in WMSN, Delay sensitive WMSN, Habitual Routing in WMSN
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	INTELLIGENT SEGMENTATION OF MR BRAIN STRUCTURES USING SUPERVISED CONTEXTUAL CLUSTERING
Author:	S.P. RENJITH, DR. N. KESAVAN NAIR
Abstract:	Image segmentation plays a vital role in medical imaging applications. Developing a robust and efficient algorithm for medical image segmentation has been a demanding area of growing research of interest during the last two decades. Image processing techniques provide a good tool for improving the manual screening of samples of Brain. This study presents a novel intelligent approach for the segmentation of anatomical brain structures in Magnetic Resonance Images (MRI) using supervised contextual clustering method. Matlab software ‘region props’ function has been used as one of the criteria to show the performance of the proposed segmentation method. The CC segmentation shows more segmented regions with less discontinuity within the objects present in the Brain image. The segmented results are compared with the conventional algorithms
Keywords:	Image Segmentation, Medical Imaging, Brain Image, CC Segmentation, MRI
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	IMPLEMENTATION OF FUZZY LOGIC CONTROLLER FOR BUCK-BOOST CONVERTER COMBINING KY AND SYNCHRONOUS BUCK CONVERTER FOR BATTERY OPERATED PORTABLE DEVICES
Author:	R.ANAND , I.GNANAMBAL , N.POORNEMA
Abstract:	KY converter and buck converter, combined into a positive buck–boost converter is a recently proposed system by K. I. Hwuet. Al. This converter produces low output voltage ripple than the conventional DC-DC negative voltage boosting converters. In this manuscript a PI controller and Fuzzy controller is modelled to control the output voltage ripple to reduce the peak overshoot and settling time of the converter. The results of proposed PI and Fuzzy controlled negative output KY boost converter with the digital simulation by Matlab/Simulink shows reduction in voltage ripple for about 5milli Volts for PI controlled system to 2milli Volts by the proposed Fuzzy controlled combined buck and KY converter. Also the peak overshoot of the system and its settling time are reduced to a greater extent with the proposed system. The performance of the converter with traditional Proportional-Integral-Controller (PIC) and Fuzzy controller is compared at different working conditions in the MATLAB/Simulink. Experimental model using field programmable gate array (FPGA)were also done and the simulation results were verified.
Keywords:	Fuzzy Logic Controller (FCL), Proportional Integral Controller(PIC), Modified KY Buck Boost Converter, Output voltage ripple, DC-DC Converter
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	OPTIMIZED RADIAL BASIS FUNCTION CLASSIFIER WITH HYBRID BAT ALGORITHM FOR MULTI MODAL BIOMETRICS
Author:	ANAND VISWANATHAN, S.CHITRA
Abstract:	Biometrics is identifying a person using their physiological/behavioral features. Recently, vein pattern biometrics attracted interest from research communities. Finger-vein recognition is a new biometrical identification procedure using the idea that different persons have differing finger-vein patterns. Multimodal biometrics is based on fingerprint and finger vein. Gabor features are extracted from finger vein using Gabor filter with orientation of 0, 15, 45, 60 and 75 degrees. For fingerprint images, energy coefficients are got using wavelet packet tree. Both obtained features are normalized with min max normalization and fused with concatenation. Feature selection is through use of PCA and kernel PCA. Classification is by using RBF Classifier and Euclidean distance. It is suggested that RBF kernel be optimized using BAT algorithm and hybrid BAT with local search.
Keywords:	Multimodal Biometrics, Fingerprint, Finger vein, Radial Basis Function (RBF) classifier, BAT, Gravitational Search
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	NOVEL VIGILANT REAL TIME MONITORING AND SECURITY SYSTEM FOR ATM CENTRE
Author:	R.SENTHIL KUMAR, K.R.SUGAVANAM, D.GAJALAKSHMI, S.SRI KRISHNA KUMAR, V.ABIRAMI, 6R.MADHAVI
Abstract:	The increased threat encountered by customers and ATM machines, have drifted the ATM center to a danger zone. The present day monitoring system is much vulnerable which in turn encourages the fraudulent activities and crimes in ATM centers. This is high-time for banking sector and government to join hands to weed out this crisis in security system. So it becomes indispensable to strictly monitor the do’s and don’ts inside the ATM centers, very specifically the facial recognition is considered to authenticate the entry of any individual inside the ATM center, it is achieved by employing classifier technique. As an additional feature, a combinational biometry system is used to access the ATM machine. The entire security module is incorporated with an easy access panic button and a sound sensor-cum-alarm, which alerts the cops as well as the bank’s security wing, ensuring immediate rescue to the victims including physically challenged people. This overall system proves to be an autonomous, continuous and secured surveillance system.
Keywords:	ATM Centre, Security, Fraudulence, Face detection, Classifier.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	MULTI MODAL BIOMETRICS USING PALMPRINT AND PALMVEIN
Author:	V.USHARANI, S.V.SARAVANAN
Abstract:	Personal identification technology is applicable to various systems including area-access control, PC login and e-commerce. Biometrics is a statistical measurement of human physiological/behavioral traits. Biometric techniques for personal identification attracted attention as conventional means like keys, passwords or PIN numbers face problems regarding theft, loss, and reliance on user’s memory. A multimodal biometric system using palmvein and palmprint is proposed by this work. Wavelet based texture features extract features from palmprint while autoregressive model based texture features are extracted for palmvein. Obtained features are normalized using z score normalization and are fused using concatenation. Feature selection is achieved by Correlation based Feature Selection (CFS) and classification by using K NN and Naive Bayes for 50, 75 and 100 features.
Keywords:	Multimodal biometrics, Auto Regressive, Wavelet packet tree, k Nearest Neighbor (KNN), Naïve Bayes, Correlation based Feature Selection (CFS).
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	INTUITIONISTIC FUZZY SOFT MATRIX THEORY IN MEDICAL DIAGNOSIS USING MAX-MIN AVERAGE COMPOSITION METHOD
Author:	P. SHANMUGASUNDARAM , C.V. SESHAIAH , K.RATHI
Abstract:	In this paper a new technique named as Intuitionistic fuzzy max-min average composition method is proposed to construct the decision method for Medical Diagnosis using different types of Intuitionistic fuzzy soft matrices and its operations. Sanchez’s approach for decision making is studied and the concept is generalized by the application of Intuitionistic fuzzy soft set theory. Through a survey the relations between the symptoms and diseases are discussed and the proposed method is compared with the existing method.
Keywords:	Fuzzy Soft Sets, Intuitionistic Fuzzy Soft Sets, Intuitionistic Fuzzy Soft Matrix. Intuitionistic Fuzzy Max Min Average Composition Method.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	DUPLICATE WEB PAGES DETECTION WITH THE SUPPORT OF 2D TABLE APPROACH
Author:	A.C. SANTHA SHEELA, C. JAYA KUMAR
Abstract:	Duplicate and near duplicate web pages are stopping the process of search engine. As a consequence of duplicate and near duplicates, the common issue for the search engines is raising the indexed storage pages. This high storage memory will slow down the process which automatically increases the serving cost. Finally, the duplication will be raised while gathering the required data from the various sources based on the user’s query. The duplication will definitely slow down the information retrieval process. Duplication is nothing but the similar content or documents located under various sites. Content duplication can be taken place at different forms and levels such as exact document copy, paragraph copy, sentence copy, single word changes and sentence structure changes. Duplication detection is the process of identifying the multi-ple representations of a same real world object. In this paper, the content duplication is identified using two dimensional (2D) text matrix approach. By using the proposed 2D matrix approach, the system was able to detect duplicate web pages with a high precision value 92% is highlighting that the duplicate web page detection with the 2D technique is performing well
Keywords:	Near Duplicate Detection, 2D Approach, Information Retrieval, Content Duplicate.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	BEAM: BANDWIDTH EFFICIENT ACKNOWLEDGEMENT BASED MULTICASTING PROTOCOL FOR SUB-URBAN SCENARIO IN VANET
Author:	P.GOKULAKRISHNAN , P.GANESHKUMAR
Abstract:	The purpose of this research work is to improve the performance of Vehicular Ad-hoc Networks (VANET) by reducing the number of in-network message transactions, and there by efficiently utilizing the bandwidth during an emergency situation. Bandwidth Efficient Acknowledgement based Multicasting protocol (BEAM) is proposed instead of the existing broadcasting protocol such as Acknowledged Broadcast from Static to highly Mobile (ABSM) an adaptive broadcast protocol. In BEAM, the emergency situations are predicted based on the status report send by the vehicles to the nearby Road Side Units (RSU). RSU (ie source) creates a multicast group, and sends an emergency message to all group members. The members reply with acknowledgements. Unlike ABSM protocol, with BEAM the vehicles decide whether to receive a message or not. The BEAM does not disturb all vehicles in the network and it helps conserve the bandwidth by exchanging minimum number of messages to multiple recipients simultaneously. Performance of BEAM is evaluated based on the number of in-network message transactions, involved in sub-urban scenario of VANET. BEAM reduces at most 13% of the in-network message transactions when compared to the existing broadcasting protocol.
Keywords:	Bandwidth Efficiency, Emergency Messages, Status Report, Multicasting Group, Sub-urban Vehicular Ad-Hoc Networks, Intelligent Transportation System.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	A NEW FUZZY C MEANS CLUSTERING ALGORITHM BASED ON CONSTRAINED DYNAMIC TIME WARPING DISTANCE MEASURE
Author:	V KATHIRESAN, Dr P SUMATHI
Abstract:	A decade back, Dynamic Time Warping (DTW) was establishing into Data Mining neighborhood as effectiveness for different responsibilities for moments sequence evils including categorization, group, and variance discovery. The method has flourished, chiefly in the last three years, and has been useful to a multiplicity of troubles in a variety of authority. In this paper, distant intellect clustering methods that make use of a solitary position iterative modified fuzzy C-means grouping algorithm is projected based leading the preceding in sequence. This technique is able to work out the fuzzy C-means algorithm's difficulty to the clustering worth is really reproduction by the data issue and the stochastic initializing the middle of clustering. Experimental results make obvious that the Modified FCM advance create better clusters than FCM clustering algorithms.
Keywords:	Centroid, Cluster, Precision, Segmentation
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	A NOVEL FUZZY-BASED ADAPTIVE TIMER BURST ASSEMBLY ALGORITHM FOR OPTICAL BURST SWITCHING NETWORKS
Author:	ABUBAKAR MUHAMMAD UMARU, MUHAMMAD SHAFIE ABD LATIFF, YAHAYA COULIBALY
Abstract:	Optical Burst Switching (OBS) is envisioned as the intermediate candidate technology for the next generation all-optical switching networks. OBS has the capability to statistically multiplex data at the burst level and at the same time function effectively without the need for optical memory. OBS harnesses the Wavelength Division Multiplexing (WDM) capability of the optical fiber to transport large volume of data by aggregating different client packets into a larger packet known as a burst. Burst assembly that is the first process in OBS is the focus of this paper, and this is because of the crucial role burst assembly plays in the performance of a network. The performance of burst assembly affects the congestion and contention levels of the network which in turn affects the overall network performance in terms of delay and loss. In this paper, a new burst assembly algorithm that uses fuzzy logic to adjust the threshold of the timer-based burst assembly algorithm is proposed. The goal of the algorithm is to minimize loss and end-to-end delay. Furthermore, two sets of fuzzy rules have been used to investigate the effects of different fuzzy rules on the performance of the network. Through simulation, the new algorithm shows performance improvement over the conventional timer-based assembly algorithm.
Keywords:	Burst Assembly, Fuzzy Logic, Delay, Packet Loss Ratio, Optical Burst Switching
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	NCBEERP: A NEW CLUSTERING PROTOCOL FOR IMPROVING ENERGY EFFICIENCY FOR WIRELESS SENSOR NETWORKS
Author:	K.MUTHUMAYIL, S.MANIKANDAN, V.RAJAMANI
Abstract:	The wide use of Wireless Sensor Networks (WSNs) is blocked by the extremely restricted energy demands of the singular sensor nodes. This is the motivation behind why a huge piece of the examination in WSNs concentrates on the advancement of energy effective steering protocols. In this paper, another convention called Novel Cluster Based Energy Efficient Routing Protocol (NCBEERP), which seeks after energy preservation through adjusted clustering, is proposed. NCBEERP models the system as a rout framework and, utilizing the node maintenance calculation, computes the mixes of nodes that might be picked as cluster heads and energize [improve the battery] the dead nodes with a specific end goal to enlarge the system lifetime. The execution assessment of NCBEERP is helped out through recreation tests, which display the adequacy of this convention as far as system energy proficiency against other well-known protocols
Keywords:	Wireless Adhoc Networks; Energy Efficiency; Novel Clustering Approach; Clustering.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	DETECTION AND PREVENTION OF SYBIL ATTACK IN WIRELESS SENSOR NETWORK EMPLOYING RANDOM PASSWORD COMPARISON METHOD
Author:	R. AMUTHAVALLI, DR. R. S. BHUVANESWARAN
Abstract:	Security is imperative for some Sensor Network Applications. An especially unsafe assault against sensor and impromptu systems is known as the Sybil attack, where a node illegitimately asserts numerous characters. In this type of attack a legal node is converted into a Sybil node which is a replica node with a different personality but using a similar ID. This leads to data leakage which causes data integrity violations. In existing research, nodes can detect the suspect nodes by checking the nodes in its neighborhood i.e within a given range. The neighbor nodes exchange information about each other and detect the Sybil node as it provides misleading information. The Sybil nodes are not detected directly by checking the ID or other node related information. In this paper, a Random Password Comparison [RPC] method is proposed that facilitates deployment and control of the position of node thereby preventing the Sybil attack. The RPC method is dynamic and accurate in detecting the Sybil attack. This method improves data transmission in the network and will also increase the throughput.
Keywords:	Wireless Sensor Networks; Sybil Node, Data Integrity Violation, Random Password Comparison.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	THE IMPLEMENTATION OF BINARY GENETIC ALGORITHM (BGA) FOR OPTIMIZING THE TASK OF INDONESIAN NAVY SHIP PATROLS RELATED TO THE SECURITY OF INDONESIA SEAS
Author:	PUDJI SANTOSO, KETUT BUDA A, 3MASROERI, M. ISA IRAWAN, AAB. DINARIYANA
Abstract:	This paper discussed the concept of decision making on the model of sea security system to overcome the cases related to territorial trespasses by foreign countries in the east maritime region of Indonesia. The most common cases are illegal fishing, illegal logging, and borders trespasses. In order to find an apt strategy in minimazing the trespasses in this area, this study conducted a simulation on the task for ship patrol using optimized method called Binary Genetic Algorithm (BGA). This model was used to select the optimized ship patrol combination in each zone with 3 scenes that were 5, 7 and 9 zones. The purpose of these divisions was to get the fleet mix, the best ship in each zone with minimum operational cost for the maximum coverage area. The parameter used in this study was crossover probability (Pc< 75%) and mutational probabilty (Pm=0,1) that was conducted to 10-100 population, 500-1000 generations. The results of the simulation of 3 zones were; for 5 zone, the fleet mix obtained was {Z1=8; Z2=8; Z3=4; Z4=5; Z5=2}, for 7 zone, the fleet mix obtained was {Z1=4; Z2=4; Z3=4; Z4=2; Z5=4; Z6=3; Z7=3}, and for 9 zone, the fleet mix obtained was{Z1=2; Z2=3; Z3=2; Z4=7; Z5=4; Z6=2; Z7=2; Z8=3; Z9=2}, and based on the comparison of the width of the coverage area and the operational cost between those zones, the most ideal implementation was 9 zones because it had 1.686.803.53 Mile2 for its coverage area and its operational cost was IDR 4,164,270,892.
Keywords:	BGA, Fleet Mix, Zone, Decision Making
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	DIFFERENTIAL EVOLUTION AND GENETIC ALGORITHM BASED FEATURE SUBSET SELECTION FOR RECOGNITION OF RIVER ICE TYPES
Author:	BHARATHI P. T, Dr. P. SUBASHINI
Abstract:	One of the essential motivations for feature selection is to defeat the curse of dimensionality problem. Feature selection optimization is nothing but generating best feature subset with maximum relevance, which improves the result of classification accuracy in pattern recognition. In this research work, Differential Evolution and Genetic Algorithm, the two population based feature selection methods are compared. First, this paper presents Differential Evolution float number optimizer in the combinatorial optimization problem of feature selection. In order to build the solution generated by the Differential Evolution float-optimizer suitable for feature selection, roulette wheel structure is constructed and supplied with the probabilities of features distribution. To generate the most promising feature set during iterations these probabilities are constructed. Second, Genetic Algorithm minimizes the Joint Conditional Entropy between the input and output variables. Practical results indicate Differential Evolution feature selection method with ten features achieves 93% accuracy when compared with Genetic Algorithm method.
Keywords:	Differential Evolution, Genetic Algorithm, Feature Extraction, Confusion Matrix, Probabilistic Neural Network Classifier.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	ALGHORITHME ADVANCED HYBRID ROUTING PROTOCOL FOR WIRELESS SENSOR NETWORKS
Author:	CHAHIDI BADR ,FIHRI MOHAMMED, EZZATI ABDELLAH
Abstract:	Sensor networks offer several services; especially in the area of monitoring, such as environmental and medical observation. Routing protocols open an avenue of research, especially in the delivery of the information between network nodes. Increase the life of a sensor network is a major challenge in the research subject, particularly with devices characterized by batteries as energy sources and storage devices and calculates limited, making the process complicated routing, since we must take account of these constraints in the development of a new protocol. Our work item on the reduction of energy and it is minimizing traffic, HRP and a new protocol that handles all this is affecting both the Mac layer and the network layer. The results obtained in the simulation protocol and effective in this level (energy) compared to other protocols of the same type. In this article we treated the mechanisms that ensure quality of service, at the energy consumption, are more we will try to explain how our protocol at the network layer.
Keywords:	Network Clustering, Routing Protocol, HRP, Ad Hoc Network, Mobility
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	AFFLUENT CONTEXT AWARE SYSTEMS BASED ON THE USER BEHAVIOR IN MOBILE-PERVASIVE COMPUTING ENVIRONMENT
Author:	H.SHAHEEN, Dr.S.KARTHIK
Abstract:	A huge number of embedded devices offer their services to the end users in pervasive environments. Context-aware discovery is a rich and very dynamic system extensively applied for combining the different mobile devices, sensors, actuators and software functions. Existing knowledge-based system using the Common KADS (CKADS) system represent contextual information but algorithm are not effective in predicting the user behavior. Current Location-aware Private Service Discovery (LPSD) considers the discovery path for reducing the distributed topology and flooding operations. LPSD in pervasive environment is not effective in accurately locating the required service by searching method. To present an architecture principle for accurately predicting the user behavior in mobile-pervasive computing environment, Affluent Context Aware Systems based on the User Behavior (ACAS-UB) is proposed in this paper. ACAS-UB mechanism contains the class of mobile devices that can sense (i.e.,) search the physical pervasive environment. Affluent means effectively engaged mobile devices in ACAS-UB mechanism which uses the context information. The ACAS-UB context information contains the judgment of the similar users and also the response from the other users for improving the effectiveness in pervasive environment user behavior prediction. Master-slave concept is used in the ACAS-UB mechanism for the easy collection of response information from the different users. ACAS-UB mechanism construct the user profile initially from the context information, then performs the similarity measure and finally work is to predict the user behavior. ACAS-UB mechanism provides the hints which are necessary to explore different options, rather than just limiting the options in mobile-pervasive computing environment. ACAS-UB mechanism is experimented on the factors such as message overhead in pervasive environment, scalability and approximately 10 % lesser processing time.
Keywords:	Pervasive Environment, Affluent Context Aware Systems, User Behavior, Context Information, Master-Slave, Response Information
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text

Title:	BACKPROPAGATION NEURAL NETWORK AND CORRELATION-BASED FEATURE SELECTION FOR EARNING RESPONSE COEFFICIENT PREDICTION
Author:	ABDUL SYUKUR, CATUR SUPRIYANTO
Abstract:	This paper evaluates the prediction of Earning Response Coefficient (ERC) through data mining. The collected data included 10 variables which are earning persistance, firm size, systematic risk, earning growth, earnings predictability, operating leverage, financial leverage, barrier to entry, transaction gains (losses) and ERC as a target prediction. Backpropagation Neural Network (BPNN) and correlation feature selection are applied in order to predict ERC which is trained and tested using 10-fold validation. Samples used in this study are 241 firms listed in the Jakarta Stock Exchange (JSE) from 2000-2002. The results of experiments achieve two main finding: BPNN and correlation feature selection perform well to predict ERC and our prediction model is capable to select the relevant attribute for the prediction.
Keywords:	Earning Response Coefficient, Backpropagation Neural Network, Prediction.
Source:	Journal of Theoretical and Applied Information Technology 10 September 2014 -- Vol. 67. No. 1 -- 2014
Full Text