		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
October 2015 | Vol. 80 No.2

Title:	IMPROVEMENT OF PERFORMANCE INTRUSION DETECTION SYSTEM (IDS) USING ARTIFICIAL NEURAL NETWORK ENSEMBLE
Author:	WIHARTO, ABDUL AZIZ, UDHI PERMANA
Abstract:	The main focus from one of the problems in computer networks is computer security systems because of the high threat of attack from the internet in recent years. Therefore, an Intrusion Detection System (IDS) that monitors the traffic of computer networks and oversight of suspicious activities in a computer network is required. Research on intrusion detection system have been carried out. Several researches have used artificial neural networks combined with a fuzzy clustering method to detect attacks. However, there is an issue that arise from the use of such algorithms. A single artificial neural network can produce overfitting on intrusion detection system output. This research used two methods of artificial neural networks, namely Lavenberg-Marquardt and Quasi-Newton to overcome that issue. Both algorithms are used to detect computer networks from attack. In addition, the use Possibilistic Fuzzy C-Means (PFCM) before going into the neural network ensemble with simple average. Then on the output, Naive Bayesian classification method is used. Dataset used in the research were NSL-KDD dataset which is an improvement of KDD Cup'99. KDDTrain+ used for training data and KDDTest+ for testing data. Evaluation results show good precision in detection of DoS (89.82%), R2L (75.78%), normal (72.25%) and Probe (70.70%). However, U2R just get 14.62%. At recall, good results achieved by normal state (91.44%), Probe (87.11%) and DoS (83.31%). Low results occurred in U2R (9.50%) and R2L (6.14%). Meanwhile, lowest accuracy on normal category (81.18%) and highest in U2R (98.70%). The results showed that the neural network ensemble method produces a better average accuracy than previous researches, amounting to 90.85%.
Keywords:	Accuracy, Anomaly Based, Intrusion Detection System, Neural Network Ensembles, NSL-KDD
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	DATA COMPRESSION METHODS
Author:	ALEKSANDR BORISOVICH VAVRENYUK, ARKADY PAVLOVICH KLARIN, VIKTOR VALENTINOVICH MAKAROV, VIKTOR ALEХANDROVICH SHURYGIN
Abstract:	Currently, there is a sharp worldwide increase in the volumes of the transmitted, stored, and processed information. Despite a certain share of superficiality, the term "information explosion" rather precisely describes the existing situation. According to the American research statistics, the volume of information created by the mankind by the year 2007 and stored on the artificial carriers amounted to 295 billion gigabytes (2.95×1020 bytes). These volumes determine the great importance of the "data compression" field of knowledge. The concept of "data compression" (DC) is very broad. Therefore, this article makes an attempt of the DC systematization (classification), which can facilitate the study of the problem as a whole as well as the choice of an appropriate method for solving a particular problem. The most known areas and specific examples of the DC application are concerned.
Keywords:	Data Compression, Application Areas, Information System, Physical Experiment, Collider, Space Researches, Efficient Data Presentation.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	A CONCEPTUAL METAMODEL APPROACH TO ANALYSING RISKS IN BUSINESS PROCESS MODELS
Author:	HANANE LHANNAOUI, MOHAMMED ISSAM KABBAJ, ZOHRA BAKKOURY
Abstract:	Business processes are performing ineffectively due to different risks. Several methods are proposed for the identification and management of risks in business process environments. In this paper, we propose a technique, for analysing risks in business process models, that originates from the safety domain. This approach initiates the improvement of business process models in an early phase of business process lifecycle by translating risk analysis output to design. Moreover, we introduce a conceptual meta-model for our integrated approach. This will describe specific concepts of business related risk analysis and will facilitate the exploitation of risk analysis output for further process improvement.
Keywords:	UML, HAZOP, Risk Analysis, Business Process Models, Design
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	ENSURING SECURITY ON MOBILE DEVICE DATA WITH TWO PHASE RSA ALGORITHM OVER CLOUD STORAGE
Author:	SUJITHRA. M, PADMAVATHI. G
Abstract:	Mobile devices are rapidly becoming a key computing platform and an essential part of human life as the most effective and convenient communication tools not bounded by time and place. With the rapid growth of mobile devices and mobile applications, the need for mobile security also has increased dramatically. Due to increasing use of mobile devices the requirement of cloud computing in mobile devices arises, which gave birth to Mobile Cloud Computing. Mobile Cloud Computing refers to an infrastructure where data storage can happen away from mobile device i.e. on a cloud. To ensure the correctness of users' data in the cloud, the framework mainly focuses on the data security over the Cloud Computing Paradigm by purposing new cryptographic technique named as Two Phase RSA Encryption. The comparison has been conducted by running several encryption settings to process different sizes of data blocks to evaluate the algorithm’s encryption/decryption speed and compared them to choose the best data encryption algorithm so that it can implement in future work.
Keywords:	Encryption, Decryption, Mobile Device, Cloud Storage, Data Storage
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	EFFICIENT REVERSE SKYLINE ALGORITHM FOR DISCOVERING TOP K-DOMINANT PRODUCTS
Author:	SHAILESH KHAPRE, M.S. SALEEM BASHA, A. MOHAMED ABBAS
Abstract:	Recent boom in internet growth and the advancement in internet security have led to rapid growth in Ecommerce and related services. In this context, capturing the preferences of customers plays an important role in decisions about the design and launch of new products in the market. The science that primarily deals with the support of such decisions is the Operational Research. Since many of the research problems of Operational Research have to do with the analysis of large volumes of data, therefore there has been a keen interest in data management methods to solve these problems. In this work we develop new algorithms for two problems related to the analysis of large volumes of consumer preferences, with practical applications in market research. The first problem we consider is to find the potential buyers of a product (potential customer’s identification). We formulated this problem as a reverse query skyline and propose a new algorithm called ERS. Secondly, Practical applications often require simultaneous processing of multiple queries. To resolve this problem, we formulated a new type of query, which is referred to as a query to find the k dominant candidates (k-dominant query). Our experimental evaluation validates the efﬁciency of the proposed algorithm which outperforms BRS by a huge margin.
Keywords:	Skyline Algorithms, Market Analysis, Personalized Service Mining, Personalized marketing, E-Commerce.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	A HYBRID OF SINGULAR VALUE DECOMPOSITION AND REGRESSION ANALYSIS COLLABORATIVE FILTERING WITH LINEAR INCREMENTAL UPDATE METHOD
Author:	WIJAK SRISUJJALERTWAJA, DUSSADEE PRASERTTITIPONG
Abstract:	Collaborative filtering (CF) approach comprises of several well-known techniques which successful in creating personalized recommendations. Singular Value Decomposition (SVD) based technique is the dominant class of CF techniques. The techniques rooted from SVD concept mostly return the high accuracy recommendation results than others. These SVD-based techniques are come up with the concept of model-based CF techniques, in which the relationship of historical ratings between users and items are learned. The learning processes usually perform in off-line mode. The model parameters are assessed according to this off-line process for constructing the knowledge models which are further use in on-line recommendation environments. However, the accuracy of the SVD-based technique is reduced according to the increasing number of solutions that they have to evaluate compared with the steady number of knowledge that they have learned, namely users-items sparse problem. On the other hand, the memory-based CF techniques are also suggested in literatures. These techniques are relied on collecting knowledge about ratings between users and items in computational area and re-computing the entire knowledge every time when the recommendations are called for. Thus, the users-items sparse problem is not an obstructer for memory-based CF techniques, because the new knowledge is always encompassed to the fundamental knowledge. Even though, memory-based CF techniques do not cause of difficulty in the users-items sparse problem, they impractical for implementing in on-line environment. Because of memory-based CF techniques take a lot of time for estimating just only one recommendation result. Hence, this paper proposed a hybrid of SVD-based technique and memory-based technique for CF. A regression analysis algorithm is proposed as a memory-based CF technique. The incremental update method with linear time refreshment also presented in this paper for making the practical on-line knowledge maintenance. The empirical experiment was established. The accuracy results acquired from the hybrid between the revolutionary RSVD technique and the proposed linear regression analysis with incremental update method depicted the highest accuracy, especially in users-items sparse situations.
Keywords:	Recommender Systems, Collaborative Filtering, Singular Value Decomposition, Incremental Update, Users-Items Sparse Problem
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	FORMAL ANALYSIS OF WEIGHTED LONGITUDINAL ROUTERS NETWORK VIA SCALE-FREE NETWORK. A CASE STUDY
Author:	FIDA HUSSAIN CHANDIO, ABDUL WAHEED MAHESAR, SAYED CHHATTAN SHAH, FOZIA ANWAR, AKRAM ZEKI
Abstract:	The process of identifying the central nodes in complex networks research has remained interesting and very important issue for network analysis. The identification of main nodes in the network can lead to many answers for the solution of security and other problems depending on the type of complex networks under analysis. Different topological metrics of the network can be used to locate the major nodes in the network but the degree and betweenness (Load) centralities perform very important role in evolution and communication of nodes in growing networks. Unfortunately, these metrics have been analyzed in different complex systems mainly either on the bases of the number of links to nodes in the network or with much focused from the perspective of weights of links. Therefore, locating the main nodes in the network not only depends on links but majorly on weight of links. Routers network of the internet is an example of scale-free nature which follow power-law distribution and causes inhomogeneous structure with some nodes with large number of links while many with a few. Further, in this type of distribution few nodes become very important. In this paper, we analyze the behavior of routers network by using two metrics of centralities with weighted and un-weighted links based on the dataset of PTCL routers network in Pakistan. Furthermore, by using centralities measures we try to show that weight of links is important as compare to number of links by following the concept from “rich get richer” to “fit get richer” in routers network. Moreover, we prove that weighted routers network is very close to scale-free networks as compared to un-weighted, and due to this phenomenon these networks sustain their robustness.
Keywords:	Scale-free networks; weighted networks analysis; load distribution; degree distribution; shortest distance; graph theory
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	A NEW PARALLEL AND DISTRIBUTED FRAMEWORK BASED ON MOBILE AGENTS FOR HPC: SPMD APPLICATIONS
Author:	FATÉMA ZAHRA BENCHARA, MOHAMED YOUSSFI, OMAR BOUATTANE, HASSAN OUAJJI
Abstract:	This paper proposes a new distributed framework and its main components for HPC (High Performance Computing). It is based on a cooperative mobile agents model which implements the team works strategies to perform parallel programs execution as distributed one. The program and data to be performed is encapsulated on team leader agent which deploys its worker agents AVPUs (Agent Virtual Processing Units). All the AVPUs have to move to a specific node and perform and provide their computational results. Consider the great number of data and of the AVPUs to be managed by the team leader agent and which alter negatively the HPC. In this work we focused on introducing a specific mobile agent the MPA (Mobile Provider Agent) which implements some mechanisms for the management of data and tasks and the AVPUs to ensure a load balancing model. It applies also some additional strategies to maintain the others performance keys thanks to the mobile agents several skills.
Keywords:	High Performance Computing, Distributed Computing Environment, SPMD Applications, Mobile Agents, Big Data Processing
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	ANALYSIS OF SHIFT REGISTER USING INTEGRATED POWER AND CLOCK DISTRIBUTION NETWORK BASED MASTER SLAVE FLIP FLOP
Author:	S.THOMAS NIBA
Abstract:	The increase in integrated circuit design complexity density and performance, specifically in 3-D integration, requires more complicated power, ground, and clock distribution network. This network consumes a large portion of the limited on-chip metal resources. In digital ICs, the clock distribution network (CDN) distributes the clock signal, which acts as a timing reference within the system. Since the clock signal is heavily loaded, has the highest capacitance and operates at high frequencies, the CDN consumes a large amount of the total power in synchronous systems. The integrated power and clock distribution network (IPCDN) is used to reduce the metal requirements, routing complexity, and power. The IPCDN is proposed in order to eliminate the need for the global and local clock distribution network. In IPCDN, a differential power clock signal with a suitable dc voltage level and sinusoidal voltage-swing clock from the differential positive power clock and negative power clock signals. IPCDN does not require any change to be made to the conventional combinational and sequential circuit design. The element of IPCDN, including the LC differential power clock signal driver and the clock buffer, have been simulated using Taiwan semiconductor manufacturing company 65-nm CMOS technology with a power clock signal, a 1-volt dc component, and 400-mv sinusoidal swing at a frequency of 5 GHz. The behaviour of a master slave flip flop with IPCDN was integrated at extreme corners. From these results we can implement this master slave flip flop in the shift register applications and compare the results with respect to shift register based on normal master slave flip flop.
Keywords:	Clock Buffer, Clocked Inverter (Domino Logic), Combinational, Pass Transistor, Distribution Network, LC Differential Driver, Power–Clock, Sequential.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	MONITORING, INTROSPECTING AND PERFORMANCE EVALUATION OF SERVER VIRTUALIZATION IN CLOUD ENVIRONMENT USING FEED BACK CONTROL SYSTEM DESIGN
Author:	VEDULA VENKATESWARA RAO, Dr. MANDAPATI VENKATESWARA RAO
Abstract:	Data centers of today are rapidly moving towards the use of server virtualization as a preferred way of sharing a pool of server hardware resources between multiple ‘guest domains’ that host different applications. The hypervisors of the virtualized servers, such as the Xen use fair schedulers to schedule the guest domains, according to priorities or weights assigned to the domain by administrators. The hosted application’s performance is sensitive to the scheduling parameters of the domain on which the application runs. However, the exact relationship between these parameters of the domain and the application performance measures such as response time or throughput is not obvious and not static as well. Furthermore, due to the dynamics present in the system there is need for continuous tuning of the scheduling parameters. The main contribution of our work is the design and implementation of a controller that optimizes the performance of applications running on guest domains. We focus on a scenario where a specific target for the response time of an application may not be provided. The goal is to dynamically compute the CPU shares for the virtual machines in such a way that the application throughput should be maximized, while keeping the response time as low as possible, with the minimum possible allocation of CPU share for the guest domain. The optimizing controller design is based on the feedback control theoretic concept. The controller computes the values of the scheduling parameters for every guest domain in such a way that it minimizes the CPU usage and response time, and maximizes throughput of the applications. To evaluate our work, we deployed multi-tier application in virtual machines hosted on the Xen virtual machine monitor. The performance evaluation results show that the controller brings the cap value close to the expected optimal value. The optimizing controller also rapidly responds to changes in the system when a disturbance task is introduced or load on the application is changed.
Keywords:	Cloud Computing, Data Center, Virtualization, hypervisor, Xen, virtual machine, Green IT, scheduler, performance, response time, throughput, feedback control theory.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	A REPORT ON REDUCING DIMENSIONS FOR BIG DATA USING KERNEL METHODS
Author:	CH. RAJA RAMESH, K RAGHAVA RAO, G.JENA, C V SASTRY
Abstract:	Big-Data is very popular word to perform huge data processing; it brings so many opportunities to the academia, industry and society. Big data hold great promise for discovery of patterns and heterogeneities which are not possible with small data. Big Data faces many challenges like unique computational and statistical challenges including scalability and storage. Among these challenges some maybe mentioned as noise accumulation, spurious correlation, incidental endogeneity and measurement errors. Most of the problems occur based on the size of the data associated with large number of attributes. Irrelevant attributes add noise to the data and increase the size of the model. Moreover datasets with many attributes may contain groups of data that are correlated. All these attributes may be measuring the same feature. One way of dealing with this problem is to eliminate some attributes (dimensions) which do not exhibit large variance and hence do not affect the clusters. Several techniques exist to ignore certain attributes or dimensions such as Principle component analysis (PCA), Singular Value Decomposition (SVD) etc. We review these techniques in this paper with respect to clustering. We plan to use principle component analysis and Kernel methods for Dimensionality reduction which is an essential preprocessing technique for large scale data sets. It can be used to improve both the efficiency and effectiveness of classifiers.
Keywords:	Big Data , Dimensionality Reduction, Feature Extraction, Fuzzy , Term Data
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	MODELING AND CONTROL OF A DOUBLY FED INDUCTION GENERATOR BASE WIND TURBINE SYSTEM OPTIMIZITION OF THE POWER
Author:	MAROUANE EL AZZAOUI, HASSANE MAHMOUDI
Abstract:	In recent years, wind energy has become one of the most important and promising sources of renewable energy. As a result, wind energy demands additional transmission capacity and better means of maintaining system reliability. The evolution of technology related to the wind system industry has led to the development of a generation of variable speed wind turbines that present numerous advantages compared to fixed-speed wind turbines. This paper deals with the modeling and control of a wind turbine driven doubly fed induction generator (DFIG) that feeds AC power to the utility grid. Initially, a model of the wind turbine and maximum power point tracking (MPPT) control strategy of the doubly-fed induction generator is presented. Thereafter, control vector-oriented stator flux is performed. Finally, the simulation results of the wind system using a doubly-fed of 3MW are presented in a Matlab/Simulink environment.
Keywords:	Converter, Doubly Fed Induction Generator (DFIG), MPPT, vector control, wind turbine.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	USABILITY EVALUATION OF SOME POPULAR PAAS PROVIDERS IN CLOUD COMPUTING ENVIRONMENT
Author:	SHARMISTHA ROY, BRATATI CHAKRABORTI, PRASANT KUMAR PATTNAIK, RAJIB MALL
Abstract:	This paper aims to focus on the usability evaluation of two interactive and popular cloud PaaS (Platform as a Service) providers namely Microsoft Azure and Appharbor. Usability evaluation has been carried out in two stages: Performance evaluation is carried out by taking CPU Utilization, Memory Usage and Disk Seeking Rate as essential parameters and in next stage customer satisfaction is measured by considering user feedback mechanism based on Interview and Questionnaire method.
Keywords:	PaaS service, Usability evaluation, Cloud computing, Questionnaire method
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	ADAPTIVE SLIDING WINDOW ALGORITHM FOR WEATHER DATA SEGMENTATION
Author:	Yahyia BenYahmed, Azuraliza Abu Bakar, Abdul RazakHamdan, Almahdi Ahmed,Sharifah Mastura Syed Abdullah
Abstract:	Data segmentation is one of the primary tasks of time series mining. This task is often used to generate interesting subsequences from a large time series sequence. Segmentation is one of the essential components in extracting significant patterns of weather time series data, which may be useful in identifying the trend and changes in weather prediction. The task use interpolation to approximate the signal with a best-fitting series and return the last point of the segments as change point or as a sequence of time points as a window. Sliding window algorithm (SWA) is a well-known time series data segmentation method, in which a segment with an error threshold and fixed window size is created when the change point is reached. In actual data such as weather data, SWA is unsuitable because appropriate error threshold and change point are required to avoid information loss. In this paper, we propose an adaptive sliding window algorithm (ASWA) that categorizes weather time series data based on the change point information.
Keywords:	Time Series, Segmentation, Change Points, Sliding Window, Adaptive Sliding Window
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	A CONCEPTUAL FRAMEWORK FOR A MULTIDIMENSIONAL MODEL OF TALENT MANAGEMENT DATA WAREHOUSE
Author:	AZWA ABDUL AZIZ, MUHAMMAD SANI ILIYASU, IBRAHIM ABDUL KARIM MAHMOUD, RAJA HASYIFAH RAJA BONGSU, JULAILY AIDA JUSOH
Abstract:	The modern business environment and dynamic economic situation has made the workforce and business ethics more versatile and sophisticated. This development forges a complex business atmosphere that compels industries to compete productively for sustainable growth. Thus, it becomes imperative for organizations to manage their talents (workforce) effectively to achieve sustenance in the modern economic climate. Regrettably, it has been challenging for HR managers to identify, select and retain competent individual’s that suits their industrial needs (talent management). Therefore, this paper proposes a conceptual framework for a Multidimensional Model of a Data Warehouse (DW) for Talent Management (TM). Further, a hybrid approach of multidimensional modeling will be adopted in developing the model of the DW. In addition, student personal information and academic performances from institute of higher learning across Malaysia will be used as the data sources. Similarly, industrial needs (job vacancies) outlined by Multimedia Development Corporation (MDEC) Malaysia will be considered as user requirement. The proposed DW will provide information that will facilitate direct mapping of candidate to industrial needs among other TM practices. Also, the DW will facilitate various TM related analytics using appropriate Business Intelligence tool.
Keywords:	Data Warehouse, Multidimensional Modeling, Star Schema, Business Intelligence, Talent Management.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	AN IMPROVED LSB IMAGE STEGANOGRAPHY TECHNIQUE USING BIT-INVERSE IN 24 BIT COLOUR IMAGE
Author:	MOHAMMED ABDUL MAJEED, ROSSILAWATI SULAIMAN
Abstract:	Steganography is an art of disguising the fact that communication is going on by concealing information in other information. In general, the communication carrier can be files in many formats; however, digital images are the most common due to their frequent use on the Internet. This paper introduces an improvement on the standard least significant bit (LSB)-based image steganography technique and proposes the bit inversion method that improves the stego-images quality in 24-bit colour image. A stego-image is the outcome of an image (usually called the cover image), after a secret message is hidden in it. In this technique, the LSB’s of some pixels of the cover image are inverted, when inputs of specific patterns of some bits related to the pixels are found. In this way, less number of pixels is modified in comparison to the standard LSB method. Our focus is to obtain a high value ratio of the Peak Signal-to-Noise (PSNR) of the stego-image, to make sure that both stego-image and the original image are difficult to discern by human eyes. The proposed bit inversion method starts with the last LSBs of both green and blue colour planes that will be replaced by the first and the second most significant bits (MSB) of the secret image. The proposed method introduces two additional levels of security to the standard LSB steganography. The first level is that because only the green and blue colours are used, instead of three colors red, green, and blue in the standard LSB, the red colour will act as noise data, and thus increases the complexity of an attacker, when he/she tries to retrieve the secret message. The second level exploits the new bit inversion technique that reverses the bits of the image pixels after applying the standard LSB. Experiments have been conducted using a collection of standard images to evaluate the proposed technique, which give the Peak Signal-to-Noise Ratio (PSNR) values of 72, 61, and 70 for Lena.jpg, Babbon.jpg, and Pepper.jpg respectively. From the experiment, we also observed that by using the bit inverse technique, less numbers of pixels are modified compared with the standard LSB method.
Keywords:	Image Steganography, LSB, Bit-Inverse, Robustness, Colour Image
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	STREAMING TWITTER DATA ANALYSIS USING SPARK FOR EFFECTIVE JOB SEARCH
Author:	LEKHA R. NAIR, DR. SUJALA D. SHETTY
Abstract:	Near real time Big Data from social network sites like Twitter or Facebook has been an interesting source for analytics by researchers in recent years owing to various factors including its up-to-date-ness, availability and popularity, though there may be a compromise in genuineness or accuracy. Apache Spark, the trendy big data processing engine that offers faster solutions compared to Hadoop, can be effectively utilized in finding patterns of relevance useful for the common man from these sites. Recently many organizations are advertising their job vacancies through tweets, which saves time and cost in recruitment. This paper addresses the issue of real time analyzing and filtering those numerous job advertisements from among the millions of other streaming tweets and classify them into various job categories to facilitate effective job search, utilizing Spark.
Keywords:	Big Data Analytics, Tweet Stream Analysis, Spark Streaming, Social Network Analysis, Streaming Big Data Processing
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	PHISHING EMAIL CLASSIFIERS EVALUATION: EMAIL BODY AND HEADER APPROACH
Author:	AMMAR YAHYA DAEEF, R. BADLISHAH AHMAD, YASMIN YACOB, NAIMAH YAAKOB, MOHD. NAZRI BIN MOHD. WARIP
Abstract:	The internet is a great importance to millions of people in their social and financial activities every day. This not only limited to individual users of the Internet, but also to organizations for the purposes of trade and others. A huge number of financial activities occur every day with millions of dollars are transferred where this large amount of financial events open the appetite of fraudsters to implement fraudulent activities. Thus, users vulnerable to many threats, including the theft of private information, banking information, and many more. Recently, phishing is a serious threat which steals user’s sensitive information and regarded as the most profitable cybercrime. Phishing mainly relies on email claiming originating from trusted source contains an embedded link to redirect victims to not benign website in order to get users financial data. As the risk of Phishing emails increases progressively, detecting and overriding this phenomenon has become very urgent, especially the zero day phishing campaigns which are new phishing emails not seen by anti-phishing tools. Although there are several solutions for phishing detection such as blacklists and heuristics, there is no clear discussion about the required processing time and the complexity of the designed solutions. This paper aims to make such dissection for server side solutions which proved to be the best choice to defeat zero day attacks.
Keywords:	Phishing, Emails, Body features, Header features, and Classifiers
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	A GENERIC VOBE FRAMEWORK TO MANAGE HOME HEALTHCARE COLLABORATION
Author:	HOGER MAHMUD, JOAN LU
Abstract:	In this paper we propose a conceptual framework to manage Home HealthCare (HHC) provision and stakeholder collaborations using the concepts of Virtual Breeding Environment (VBE) and Virtual Organisation (VO). Providing healthcare at home is gaining popularity as more and more patients prefer to receive care in the comfort of their homes. Providing care at home is complex and involves many stakeholders; collaboration and resource sharing between these stakeholders is essential for a successful home healthcare provision. In this paper we outline a framework to classify different parties involved in Home Healthcare (HHC) collaboration based on their roles. The framework consists of two main components which we call HHC-VBE and HHC-VO. The proposed framework is applied to a simple home healthcare case study and it is later evaluated. The result shows that the framework is simple and flexible and can be applied to other scenarios. This research contributes towards addressing the ongoing challenge of HHC collaboration management.
Keywords:	Virtual Breeding Environment (VBE), Virtual Organisation (VO), Home Healthcare (HHC)
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text

Title:	ELEARNING ENVIRONMENT AS A FACILITATOR FOR KNOWLEDGE CREATION USING SECI MODEL IN THE CONTEXT OF BA
Author:	SALEH KASEM, SAMIR HAMMAMI, MANSOUR NASER ALRAJA
Abstract:	Using eLearning technology today in education is changing the way in which knowledge is introduced, stored and distributed, accordingly; knowledge management technologies is used to rapidly capture, organize and deliver large amounts of new knowledge. BA as a shared context in eLearning environment requires students to share, construct and utilize knowledge through knowledge creation processes as proposed in Nonaka's model of knowledge creation (SECI). This research aims to introduce and prove that eLearning environments supports the knowledge processes and creates conditions which are consistent with Nonaka's model of knowledge creation (SECI) and the concept of BA as a shared context for knowledge creation processes and activities, a research model was built and hypotheses were formed to reflect it, then a survey was distributed between the students of Syrian Virtual University (SVU) to collect the primary data to discover the strength of relationships between the model variables, The results demonstrates that BA as a shared context affects positively knowledge creation model (SECI) in the mediation of eLearning environment. This research is a consolidated contribution to field of eLearning by engaging knowledge management concepts in the whole process of it.
Keywords:	Knowledge, SECI, Context, BA, eLearning, SVU.
Source:	Journal of Theoretical and Applied Information Technology 20^th October 2015 -- Vol. 80. No. 2 -- 2015
Full Text