		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
February 2016 | Vol. 84 No.2

Title:	TRAINING AND DEVELOPMENT OFARTIFICIAL NEURAL NETWORK MODELS: SINGLE LAYER FEEDFORWARD AND MULTI LAYER FEEDFORWARD NEURAL NETWORK
Author:	VIDYULLATHA PELLAKURI, D. RAJESWARA RAO
Abstract:	Research in the artificial neural network has been attracting and most successful technology in recent years. Though the first model of artificial neurons was presented by Warren McCulloch and Walter Pitts in 1943, the new models have been raised even in the recent years. Some of the problems are solved by mathematical analysis but it leaves many queries openly for further developments. Anyway, the study of neurons, their interconnected nodes and their actions as the brains primary building blocks is one of the most important research fields in modern biology. The purpose of this research paper is to provide how to learn the logic behind the architectures, methodologies of artificial neural networks. This study consists of two parts: the first part shows the learning of single layer feed forward neural network (SLFFNN) architecture where as in second part the multi layer feed forward (MLFFNN) back-propagation neural network covers the learning and training of optimization techniques.
Keywords:	Artificial Neural Network, Back-Propagation Neural Network, Learning Rate, Momentum, Multi Layer Perceptron.
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	A SULE'S METHOD INITIATED GENETIC ALGORITHM FOR SOLVING QAP FORMULATION IN FACILITY LAYOUT DESIGN: A REAL WORLD APPLICATION
Author:	FABRICIO NIEBLES ATENCIO, DIONICIO NEIRA RODADO
Abstract:	This paper considers the Quadratic Assignment Problem (QAP) as one of the most important issues in optimization. This NP-hard problem has been largely studied in the scientific literature, and exact and approximate (heuristic and meta-heuristic) approaches have been used mainly to optimize one or more objectives. However, most of these studies do not consider or are not tested in real applications. Hence, in this work, we propose the use of Sule’s Method and genetic algorithms, for a QAP (stated as a facility Layout Problem) in a real industry application in Colombia so that the total cost to move the required material between the facilities is minimized. As far as we know, this is the first work in which Sule’s Method and genetic algorithms are used simultaneously for this combinatorial optimization problem. Additionally the proposed approach was tested using well-known datasets from the literature in order to assure its efficiency.
Keywords:	Facilty Layout Design; QAP; Genetic Algorithm; Sule’s Method
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	ACTIVITIES AND SUGGESTIONS FOR USING SOCIAL NETWORKING IN TEACHING ESL WRITING
Author:	MELOR MD YNUUS , HADI SALEHI , MAHDI AMINI , MOHAMMAD SHOJAEE, WANG YUN FEI
Abstract:	With the technology boosting in the new era in this globalized world, it is essential for people to be equipped with technical skills to be competent for life-long learning and working. And English, as the globalized language, is used widely between nations and has promoted the integration of economy. It is critical for youths to master English to compete for further study, the future jobs, and so on. The role of the teacher is to make students learn English with tech skills. Therefore, this research is focused on teaching English through modern tech tools. This research is mainly about exploring activities through social networking sites to teach ESL writing and looking for suggestion to enhance the effectiveness of activities. Data was collected through mono-method approach, which is a qualitative research. According to the research, it was found that there are many various writing activities taking place among teachers and students on the social networking sites; the teaching and learning is in the non-linear way. The teaching pedagogy can be the teacher–centered or student-centered when utilizing social networking tools. Besides, the appropriate suggestion can make the activities better. Hence, educators and teachers should be aware of the social networking tools on ESL teaching.
Keywords:	Social Networking, ESL Writing, Computer-Assisted Language Learning (CALL), Facebook, Wiki, Blog
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	QUALITY-DRIVEN FEATURE IDENTIFICATION AND DOCUMENTATION FROM SOURCE CODE
Author:	HAMZEH EYAL SALMAN, ABDELHAK-DJAMEL SERIAI, Mustafa Hammad
Abstract:	Software companies develop a large number of software products cater to the needs of customers in different domains. Each product offers a set of features to serve customers in a particular domain. Over the time, the product features (resp. their implementations) should be improved, changed or removed to meet new demands of customers. Identifying source code elements that implements each feature plays a pivot role in such software maintenance tasks. In this article, we present an approach to support effective feature identification and documentation from source code. The novelty of our approach is that we identify each feature implementation based on a semantic-correctness model that can achieve satisfactory results according to well-known evaluation metrics on the subject. We have implemented our approach and conducted evaluation with a large case study. Our evaluation showed that our approach always achieves promising results.
Keywords:	Feature Identification, Feature Location, Feature Documentation, Source Code, Reuse, Re-engineering, Quality, Clustering
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	AN EFFICIENT HYBRID TREE BASED ROUTING ALGORITHM FOR AD-HOC NETWORK
Author:	KADAMBRI AGARWAL , SACHIN KUMAR , A.K. SHARMA
Abstract:	Ad-hoc network can be outlined as network with none infrastructure. Route discovery is nice concern in Ad-hoc Network as topology changes dynamically. Several routing algorithmic rule exists in literature, which might be classified as Proactive, Reactive and Hybrid. Proactive algorithms ceaselessly notice the route e.g. OLSR. Reactive (on demand) solely notice the route once demanded e.g. AODV, DSR, DSDV. Hybrid uses the options of each proactive and reactive e.g. ZRP. We propose hybrid approach that shows best result among in the class.
Keywords:	Ad-hoc Network, AODV, DSDV, DSR, Throughput
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	A META-MODEL FOR AUTOMATIC MODELING DYNAMIC WEB APPLICATIONS
Author:	TANYA SATTAYA-APHITAN , HORST LICHTER , TONI ANWAR , SANSIRI TANACHUTIWAT
Abstract:	This paper proposes an approach to automatically transform source code of a web application into an abstraction model. A Web Application Program Dependency (WAPD) meta-model is being proposed to store dependency information based on a multi-tiered architecture, corresponding to web application’s behavior. A WebParseTree is used as an intermediate model for the transformation from the source code to the WAPD model. The WebParseTree is a DOM-like tree that consists of statements and dependencies stored information and behavior in the tree. To ensure that the resulting model is valid, it must conform to the defined web application rules. This validation step can be done automatically by a constraint validator using Object Constraint Language (OCL). The WAPD model will be represented as a generic model for web applications which can be used for many purposes such as automatic test case generation and automatic code transformation.
Keywords:	Web Parse Tree, Web Application Modeling, Web Application Meta-model, Data Object Modeling (DOM), Web Application Automatic Transformation.
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	AN OVERVIEW OF CONTENT-BASED IMAGE RETRIEVAL TECHNIQUES
Author:	ABEER ESA A M ALOMAIRI, GHAZALI SULONG
Abstract:	Content based image retrieval (CBIR) depends on several factors, such as, feature extraction method (the usage of appropriate features in CBIR), similarity measurement method and mathematical transform (chosen to calculate effective features), feedback usage and etc. All these factors are important in CBIR to enhance image retrieval accuracy and effort. An efficient retrieval mechanism can be achieved by improving some of its influencing factors. For this purpose, this paper provides a brief review of the factors that have an impact (positive or negative) on the CBIR. The usage of low-level image features such as shape, texture and color are assembling information from an image for recuperation. In this paper, various spectral methods of texture features extraction are discussed. In addition, all the current methods of demonstrating image texture features in the modern literature have been investigated for the purpose to achieve the research’s aim (to discover the most adequate features in CBIR that support image retrieval quality and retrieve the relevant images to the query image ). This paper also addresses the shortcomings of one spectral approach and the solutions provided by another approach for finding the most effective approach in texture feature representation.
Keywords:	Image retrieval, Texture feature, Low level features, Features extraction, Features influencing factors, spectral features, DCT, DWT,GFT
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	AN INTRINSIC REAL-TIME MULTIMODAL RECOGNITION SYSTEM USING DEEP NEURAL NETWORKS
Author:	J.SEETHALAKSHMI, C.JAYAKUMAR
Abstract:	In this paper, an embedded finger-vein and voice recognition system for authentication on ATM network is proposed. The system is implemented on an embedded platform and equipped with a novel finger-vein and voice recognition algorithm. The proposed system consists of four hardware modules: radio frequency identification system, image acquisition module, embedded main board, and human machine communication module. RFID module will start the very initial communication between the user and the device. The proposed system is designed for applications where the training database contains Finger-vein and voice for each individual. The final decision is made by multi model architecture. The multimodal system is developed through fusion of finger-vein and voice. These images of the user are acquired by the image acquisition module of the hardware. The finger-vein recognition algorithm is coded and targeted as firmware of the embedded main board. Human machine interface module communicates with the user through keyboard and displays the outcome of the match in human recognizable formats like LCD or LED displays as well as voice message. The RFID module enhances the security and credibility of the whole system by giving short message service (SMS) through GSM technology platform to the actual user. This system is tested on IITK database and overall accuracy of the system is found to be more than 99% accurate respectively.
Keywords:	Embedded Finger Vein Recognition, Voice Recognitions System, RFID Module, Embedded Platform, Communication Module, Image Acquisition Module, Deep Neural Network Etc.
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	VEHICLE COUNTING AND VEHICLE SPEED MEASUREMENT BASED ON VIDEO PROCESSING
Author:	HARDY SANTOSA SUNDORO, AGUS HARJOKO
Abstract:	Vehicle counting system and vehicle speed measurement based on video processing are few of systems that utilize digital image processing system as a detector of a moving object such as a vehicle to do the counting and speed measurement. This system is an early stage in the development of Intelligent Transportation System. The methods used in this system are background subtraction with Gaussian Mixture Model (GMM) algorithm and blob detection. Background subtraction method is used because it is a method that can separate foreground and background smoothly and adaptive to the condition of the frame. The blob detection method provide the coordinates in the form of centroid so it will show the movement of the vehicle. System trials conducted on three conditions, namely in the morning, afternoon, and evening. Speed calibration testing parameters obtained with the use of a speed gun. The accuracy of vehicle counting obtained by the evaluation method system by comparing the real situation with the results of the system. The value of the vehicle speed measurement uncertainty obtained by using standard deviation calculations and the combined uncertainty. Vehicle counting accuracy obtained in the morning conditions is 75.69%. Vehicle counting accuracy obatined in the afternoon is 90.50%. Accuracy of counting vehicles obtained 85.31% in the evening. The value of the uncertainty around those conditions is approximately ± 3 km/h.
Keywords:	Intelligent Transportation System, Video Processing, Blob Detection, Background Subtraction, Speed Gun
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	ENHANCING MULTIPLE CHANNELS IN WIRELESS MESH NETWORKS BY USING ARTIFICIAL BEE COLONY SCHEDULING ALGORITHM WITH RANKING STRATEGY
Author:	FAROOQ BASIL ABDULQADER, RAVIE CHANDREN MUNIYANDI
Abstract:	The communication links of multi-hop wireless networks are less efficient than those of traditional wired networks. For example, collision-free data transmission is difficult to achieve in a wireless network. This work introduces a smart algorithm that enhances multiple communication channels in a wireless network. This study aims to implement the artificial bee colony (ABC) algorithm to prevent data collisions. A thorough review is conducted to identify the drawbacks of a wireless network. The investigation reveals that, within a given range, the nodes of a wireless network cannot transmit signals simultaneously because the transmission from multiple nodes interferes with one another. Unwanted communication is also difficult to detect because of the presence of hidden and exposed nodes. Free transmission by network stations may lead to message collision. For example, if two communicating nodes are out of range, then a third node within the range may interfere with the communication. Results of this study show that the ABC algorithm enhances the communication channel in a wireless mesh network by preventing data collision during transmission. The implementation of the swarm intelligent algorithm provides a simple solution to the aforementioned deployment problems. Therefore, combining the general ABC algorithm and a ranking strategy in a packet radio network improves the communication among multiple nodes in rapid time
Keywords:	Artificial Bee Colony Algorithm, Ranking Strategy, Multiple Channel, Wireless Mesh Network, Packet Radio Networks
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	STBC-OFDM SYSTEM BASED ON DISCRETE FRAMELET TRANSFORM
Author:	SUHA Q. HADI, P. EHKAN, M. S. ANUAR, AWATIF ALI JAFAAR
Abstract:	This paper proposed anew Space Time Block Coded Orthogonal Frequency-Division Multiplexing (STBC-OFDM) system based on Discrete Framelet transform (FT) instead of Fast Fourier Transform (FFT) under different channel environments. The proposed system (STBC-FT-OFDM) has been compared with traditional (STBC-FFT-OFDM) system and (STBC-OFDM) based on Discrete Wavelet Transform (STBC-DWT-OFDM) system. Through calculating the Bit Error Rate (BER) performance, it proved that the performance of the proposed system is outperform compared with the performance of the other two systems. BER performance of the system is analyzed by employing various digital modulations technique (BPSK, QPSK) over an Additive White Gaussian Noise (AWGN), flat fading, and multipath selective fading channels
Keywords:	OFDM, STBC, Framelet Transform, Wireless Channel, PSK Modulation.
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	INPUT SPLIT FREQUENT PATTERN TREE USING MAPREDUCE PARADIGM IN HADOOP
Author:	GREESHMA L, PRADEEPINI G
Abstract:	Big data has been attracted in information industry and in the society in the recent years, due to the wide availability of huge amount of data in the Internet and the complexity of data is growing every day. Hence distributed data mining algorithms has decided to exploit big data adaptable to current technology. Since there exist some limitations in traditional algorithm for dealing with the massive volume of data set which degrades the performance. So, thereby we require fast and efficient scalable frequent item sets for storing and processing large data sets. Existing algorithm like apriori algorithm performs a multiple scans from external storage, which leads to heavy burden for I/O devices. In this paper, we proposed Association Rule Mining based on Hadoop Distributed File System for storing huge amount of data and implemented using MapReduce object oriented programming paradigm for processing of a data.
Keywords:	Big Data, Hadoop Distributed File System, MapReduce, Association Rule Mining, Distributed Frequent Item set Mining.
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	AFFINITY PROPAGATION AND RFM-MODEL FOR CRM’S DATA ANALYSIS
Author:	E.S. MARGIANTI, R. REFIANTI, A.B. MUTIARA, K. NUZULINA
Abstract:	The number of existing competition between companies make a company does not only focus on product development, but also in relation to customers. Customer Relationship Management (CRM) is a strategy to manage and maintain relationships with customers as well as an attempt to determine the wants and needs of customers. The analysis needs to produce the information on which customers are valuable or not. This will allow companies to implement efficient and effective measures to be loyal customers. This research is a data mining process with the method used is clustering by Affinity Propagation and Recency Frequency and Monetary (RFM) model on 1.000 Customer data. Distance method used on Affinity Propagation algorithm is Euclidean Distance and Manhattan Distance. Application was built using MATLAB to facilitate companies to analyze customer transaction data. From 1.000 customer data it generates 51 clusters. The best results if used Euclidean distance with preference median or Manhattan distance with preference minimum. The results of the clustering process is analyzed using comparison of RFM model and divide customer into eight type of customer and then into three groups. The results of customer segmentation are Most Valuable Customer 3.7%, Most Growable Customer 26.3% and Below Zero Customer 70%.
Keywords:	Affinity Propagation, CRM, RFM, Clustering, Euclidean Distance, Manhattan Distance
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	COMPUTING ICEBERG QUERIES HAVING NON ANTI MONOTONE CONSTRAINS WITH BIT MAP NUMBER
Author:	PALLAM RAVI, DR. D. HARITHA , DR. NIRANJAN POLALA
Abstract:	Computing aggregation values of user interesting attributes are important in decision and knowledge discovering systems .In real world the users are interested only view to the aggregation values which meet some constrain this type of queries are call iceberg queries. We can optimize memory requirement and CPU time for computing iceberg Queries having anti monotone constrains by eliminating non target set, but for Non anti monotone constrains we cannot eliminate non target sets, so it requires huge memory for answering the query, we propose a algorithm which produce target results using minimum memory and CPU time for computation by bit map numbers, explain with a sample iceberg query
Keywords:	Non Anti Monotone, Iceberg Query, Anti Monotone , Bit Map Numbers
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	PROVIDING SECURITY IN CLOUD BASED NETWORKS THROUGH SOFTWARE DEFINED NETWORKS
Author:	Dr.CHINTHAGUNTA MUKUNDHA, Dr.I.SURYA PRABHA, KARNAM SREENU
Abstract:	Now days we have observed that the fast change in the cloud network by the Software Defined Networking (SDN) paradigm that differentiate the control plane from the data plane to give the flexibility for programmability and centralized control of the cloud networks, SDN networks not only provide simplification of cloud network management it also provides more security with SDN by implementing firewalls with in the SDNs. The demand of cloud increased day by day with the increasing of usage of cloud. The SDN is provided with OpenFlow network, cloud network states are dynamically updated and configurations are frequently changed. Open Flow accepts various Field actions that can dynamically change the packet headers. A firewall embedded in SDN can immediately enforce updated rules in the firewall policy to check security violations. Cloud computing allows all categories of users to use applications without installation and access their personal files at any system with internet access .Here we present that the way forward is to integrate SDN and fully utilize its feature to solve the security problems in cloud networks. We focus on the security aspect and investigate how to enhance the security with SDN firewalls for the cloud networks.
Keywords:	Cloud Network, Software Defined Networks,Firewalls,Security,Cloud Computing
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	DEVELOPMENT OF DATA COMMUNICATION SYSTEM FOR VIRTUAL HOSPITAL SCHEME BETWEEN PUBLIC HEALTH CENTERS AT REMOTE AREAS AND REGENCY PUBLIC HOSPITAL BASED ON RADIO FREQUENCY COMMUNICATION
Author:	S. HAWIBOWO, SUNARNO, M. M. WARUWU, R. WIJAYA
Abstract:	The existence of inpatient public health centers in remote areas needs to be supported with a data communication telemedicine system. The system includes remote station at each public health center which consists of telemedicine sensors such as the blood pressure monitor, the body temperature sensor, the electrocardiograph, the psych meter, and the heart rate monitor. The sensor circuits are connected to a modulator frequency shift keying (FSK) transceiver (Tx/Rx), and an antenna. The data is sent wirelessly to the base station. The base station device which is a computer-based control center was placed in a regency public hospital. The base station consists of an antenna, Tx/Rx, FSK demodulator, a PC (personal computer) with software. The results of the communication system test at Gunungkidul regency indicate that the accuracy level of the real time data measurement transmission has an average of 95 % at a distance of 0-40 km. The average of the successful data text transmission reached 97.6%. For the image data transmission, the received image quality decreased to 93.9% at a distance of 5 km and 55.3 % at a distance of 40 km. Variations of this quality degradation caused by distortion and interference of the frequency. The successful rate of the data transmission was sufficient for the purposes of early diagnosis, except for image data transmission remains to be improved.
Keywords:	public health centers, radio frequency, data communications, virtual hospital
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text

Title:	SECURE METHOD FOR EMBEDDING PLAINTEXT ON AN ELLIPTIC CURVE USING TDMRC CODE AND KOBLITZ METHOD
Author:	CIMI THOMAS M, DR. VARGHESE PAUL
Abstract:	The web applications are becoming popular and there is an increase in the amount of sensitive information transmitted over internet. Encryption algorithms play an important role in ensuring the security of data. Elliptic Curve Cryptography (ECC) is a public key encryption method which can be used for message encryption, key exchange and for creating digital signatures. ECC is considered as a good alternative to RSA and other public key encryption algorithms as it offers high level of security with smaller key sizes. ECC is well suited for applications which run on devices with power and memory constraints like smart cards and cell phones. SMS messages can be encrypted using ECC without degrading the performance of mobile devices. In elliptic curve analog of ElGamal system, the plaintext message has to be encoded into an elliptic curve before encryption. In this paper different methods suggested in the literature for encoding characters in the text message to an elliptic curve are examined and a new method for encoding the characters to the curve using TDMRC code is proposed. TDMRC code is a symmetric key encryption algorithm and is polyalphabetic. The polyalphabetic nature of TDMRC code can be utilized to defeat cryptanalysis based on letter frequencies .The proposed encryption scheme will be a reliable scheme and will offer high security as the plaintext is encrypted twice.
Keywords:	Encryption, Decryption, Elliptic Curve Cryptography, Encoding, Decoding
Source:	Journal of Theoretical and Applied Information Technology 20^th February 2016 -- Vol. 8. No. 2 -- 2016
Full Text