		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
May 2016 | Vol. 87 No.2

Title:	SIGNIFICANT PREPROCESSING METHOD IN EEG-BASED EMOTIONS CLASSIFICATION
Author:	MUHAMMAD NADZERI MUNAWAR, RIYANARTO SARNO, DIMAS ANTON ASFANI, TOMOHIKO IGASAKI, BRILIAN T. NUGRAHA
Abstract:	EEG preprocessing methods for classifying person emotions have been widely applied. However, there still remain some parts where determining significant preprocessing method can be improved. In this regards, this paper proposes a method to determine the most significant preprocessing methods, among them to determine (i) denoising method; (ii) frequency bands; (iii) subjects; (iv) channels; and (v) features. The purposes are to improve the accuracy of emotion classification based on valence and arousal emotion model. EEG data from 34 participants will be recorded with the questionnaires (valence and arousal) that have been taken from the participants when they receive stimuli from picture, music, and video. EEG data will be divided into 5 seconds for each trial. Then, EEG data will be processed using denoising method and feature extraction. After that, the most significant preprocessing methods will be chosen using statistical analysis Pearson-Correlation. The preprocessed EEG data will be categorized. The average accuracy results using SVM are 66.09% (valence) and 75.66% (arousal) while the average accuracy results using KNN are 82.33% (valence) and 87.32% (arousal). For comparison, the average accuracy results without choosing the most significant preprocessing method are 52% (valence) and 49% (arousal) using SVM while the average accuracy results using KNN are 50.13% (valence) and 56% (arousal).
Keywords:	Significant Preprocessing Method, Electroencephalogram (EEG), Emotion Classification, Valence, Arousal
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	SOCIAL MEDIA USAGE IN ACADEMIC RESEARCH
Author:	MUHAMMAD MURAD KHAN, IMRAN GHANI, SEUNG RYUL JEONG, ROLIANA IBRAHIM, HABIB-UR-REHMAN
Abstract:	Recently researchers have used conversation prism and social media prisma, to consolidate social medias with respect to their use. Although both identified 25 types, having average five examples each, they did not identify contribution of each type in academic research. Moreover some of mentioned social services had been suspended or changed. In this paper we attempt to access each social media mentioned in conversation prism in order to first, identify services that are operational to date, services which have suspended and those which have changed during course of time. Second, we compare number of publications associated with each social media, in order to identify which social media has contributed most to academic research. Third, we attempt to find correlation between number of publications and development tools provided by respective social applications. Fourth, social medias are ranked with respect to number of times other social medias share content with respective social application. It was found that out of 168 social applications, 10% changed their service objective while 13% were suspended. Among all social application, AMAZON had highest i.e. 147,000 number of citations on Google scholar whereas 90.7% of total citations were contributed by top 30 social medias. For developers, 22 out of top 30 social medias provided developer options in form of either application programming interface (API) or software development kits (SDK) and Facebook was found to be most cross referred social media based on content sharing. Finally conclusion and future work of study is presented.
Keywords:	Social Media, Academic Research, Conversation Prism, Developer Tools, API, SDK
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	HISTOGRAM EQUALIZATION BASED FRONT-END PROCESSING FOR NOISY SPEECH RECOGNITION
Author:	IBRAHIM MISSAOUI, ZIED LACHIRI
Abstract:	In this paper, we present Gabor features extraction based on front-end processing using histogram equalization for noisy speech recognition. The proposed features named as Histogram Equalization of Gabor Bark Spectrum features, HeqGBS features are extracted using 2-D Gabor processing followed by a histogram equalization step from spectro-temporal representation of Bark spectrum of speech signal. The histogram equalization is used as front-end processing in order to reduce and eliminate the undesired information from the used spectrum representation. The proposed HeqGBS features are evaluated on recognition task of noisy isolated speech words using HMM. The obtained recognition rates confirm that the HeqGBS features yield interesting results compared to those of the Gabor features which are obtained from log Mel-spectrogram.
Keywords:	Front-end Processing, Histogram Equalization, 2-D Gabor processing, Feature extraction, Noisy Speech Recognition
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	INITIAL RECOMMENDATIONS OF MOOCS CHARACTERISTICS FOR ACADEMIC DISCIPLINE CLUSTERS
Author:	HUZAIFAH MOHD SALAMON, NAZMONA MAT ALI, SURAYA MISKON, NORASNITA AHMAD
Abstract:	Massive Open Online Courses (known as MOOCs) have been introduced as an extensive and pervasive learning style in order to increase students performance. Many academics and students in Malaysian higher education institutions have begun to show their interest in applying MOOCs to deliver course material or conduct distance education in an innovative way. However, there are no guidelines available to assist the application of MOOCs; in particular, there are no guidelines to help academics develop their own MOOCs based on their area of expertise. In the education domain, usually these areas of expertise are arranged according to certain groups referred to as academic discipline clusters. This study investigates existing MOOCs characteristics and recommends specific characteristics in relation to academic discipline clusters. Content analysis was carried out by exploring MOOCs characteristics implemented successfully in six universities worldwide. This included an examination of the platforms used and the courses that applied MOOCs. Based on the results, the desirable characteristics of MOOCs are recommended with regard to academic discipline clusters, with the Universiti Teknologi Malaysia used as a case study.
Keywords:	Massive Open Online Courses, MOOCs, Malaysia HEIs, Learning style
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	POWERFUL NETWORK MONITORING SYSTEM WITH ADDITIONAL SERVICES INCREASING THE NETWORK PERFORMANCE
Author:	CHITLURU VEERABHADRA RAO, T PAVAN KUMAR, Dr V SRIKANTH
Abstract:	A powerful and excellent network monitoring system called Nagios helps the various organizations of medium and large scale to detect and solve the IT infrastructure monitoring related problems before they affect crucial and confidential business information. A new feature of services were added to the existing system which has no such type are configuration for Various levels of authentication, Bandwidth usage and alerting services. The Nagios alerts user whenever a defect occurs and alerts when the problem resolved. The alerts were delivered through email,sms,pager.The alert about a particular service can also be delivered through commenting the service from the admin manually. As there were group of admins, any can send alert to the hosts and the chance of conveying wrong alerts by any exist. So making the different login credentials to all the level of authorities helps the user to receive correct alert about the status of the service.The bandwidth usage indication of a client system added to Nagios indicates the Bandwidth usage from a host machine and if the usage limit reached,an alert will be generated and delivered to the admin.Network Development Life Cycle was chosen as a methodology for implementing this system in the network. Nagios is installed in Ubuntu Operating System along with Multi-Router Traffic Grapher (MRTG) and Mail Postfix. MRTG and Mail Postfix were configured to be integrated with the Nagios System. On the client side,NSClient++ has been installed, for monitoring the bandwidth and performance of windows based on operating system.
Keywords:	Nagios, Network monitoring, Email notification, SMS alert, Network Performance,Multi Router-Traffic Grapher (MRTG)
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	IMPROVED METHOD FOR THE FORMATION OF LINGUISTIC STANDARDS FOR OF INTRUSION DETECTION SYSTEMS
Author:	AKHEMETOV BAKHYTZHAN, KORCHENKO ANNA, AKHMETOVA SANZIRA, ZHUMANGALIEVA NAZYM
Abstract:	Due to intensive development of digital business, malicious software and other cyber threats are becoming more common. To increase the level of security necessary special remedies that can be effective when new types of threats and allow fuzzy conditions to detect cyberattacks targeting multiple resources of information systems. Different attacking effects on related resources give rise to different sets of parametric anomalies in a heterogeneous environment. Known tuple model of the formation of a set of core components that allow to detect cyberattacks. For its effective application requires a formal approach to the formation of fuzzy (linguistic) standards. To this end a method is developed that focuses on the tasks of identifying cyberattacks on computer systems, which is based on mathematical models and methods of fuzzy logic and is implemented through six basic stages: the formation of subsets of identifiers linguistic assessments, forming the base matrix of frequencies, the formation of the derivative matrix of frequencies, the formation of fuzzy terms, the formation of the reference fuzzy numbers, visualization of linguistic standards. The method allows to improve the process of formalization of linguistic standards receive options to improve the efficiency of construction of the corresponding intrusion detection systems.
Keywords:	Artificial Neural Network (ANN), Static Var Compensator (SVC), Autonomous Hybrid Power System (AHPS)
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	A NOVEL PROPAGATION TECHNIQUE IN FREE SPACE OPTICAL COMMUNICATION
Author:	A.K. RAHMAN, C.B.M. RASHIDI, S.A. ALJUNID, M.S. ANUAR, R.ENDUT, K.R. UMMUL
Abstract:	This paper focus on mitigating the atmospheric turbulence effect in free space optical communication using a dual diffuser modulation (DDM) technique. The most deteriorate the FSOC is scintillation where it affected the wave front cause to fluctuating signal and ultimately receiver can turn into saturate or loss signal. DD approach enhances the detecting bit 1 and bit 0 and improves the power received to combat with turbulence effect. The performance focus on Signal-to-Noise (SNR) and Bit Error Rate (BER) by using the Kolmogorovs scintillation theory. The numerical result shows that the DD approach improves the range where estimated approximately 40% improvement under weak turbulence and 80% under strong turbulence.
Keywords:	Dual Diffuser Modulation, Free Space Optical Communications, Atmospheric Turbulence
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	TEST CASE PRIORITIZATION ON REAL TIME APPLICATIONS
Author:	SNEHA PASALA, PRASAD MSR, RAMA KRISHNA V
Abstract:	Even though test case prioritization is known for its efficiency in detecting faults early by making use of prioritized test suits, it isnt used in real time applications as it needs faults to be known beforehand. Average Percentage of Faults Detected determines the effectiveness of test suite orders either it may be prioritized/non -prioritized. It effectively chooses the suite orders such that the faults are detected at an early stage and with less number of test cases. Thus for measuring this certainty, APFD is chosen due to its effective results in our work. By making use of APFD metric, test case suites are prioritized. APFD values for various builds of a HR application are calculated to prove the efficiency of test case prioritization in real-time applications and projects.
Keywords:	HR application, real time analysis, Prioritization criteria, component based criteria, module based criteria, Faults, APFD
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	GENERALIZED PROBABILISTIC DESCRIPTION OF HOMOGENEOUS FLOWS OF EVENTS FOR SOLVING INFORMATIONAL SECURITY PROBLEMS
Author:	YURI YURIEVICH GROMOV, IVAN GEORGIEVICH KARPOV, YURI VIKTOROVICH MININ, OLGA GENNADEVNA IVANOVA
Abstract:	The method of producing a generalized probabilistic description of flows of events that are characterized by ordinariness, stationarity and lack of aftereffects for solving informational security problems is obtained. The examples of these flows are test queries to network addresses, attempts of available ports scanning, etc. The independence of increments property could be unrealized for these events, but the Markov lack of aftereffects property is necessarily realized. It consists that there is no influence to the time of appearing the future event of past events, excluding the last event. The authors obtained the distributions of flows of events for linear flow intensity function, Poisson, binominal, and negative binominal lows. We also obtained expressions for the distribution laws of k - th event occurrence and their main numerical characteristics.
Keywords:	Informational Security, Flow Of Events, Probability, Probability Distribution Density, Mathematical Expectation, Variance
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	EVALUATING THE PERFORMANCE OF DEEP SUPERVISED AUTO ENCODER IN SINGLE SAMPLE FACE RECOGNITION PROBLEM USING KULLBACK-LEIBLER DIVERGENCE SPARSITY REGULARIZER
Author:	OTNIEL Y. VIKTORISA, ITO WASITO, ARIDA F. SYAFIANDINI
Abstract:	Recent development on supervised auto encoder research gives promising solutions toward single sample face recognition problems. In this research, Kullback-Leibler Divergence (KLD) approach is proposed to obtain penalty of sparsity constraint for deep auto encoder learning process. This approach is tested using two datasets, Extended Yale B (cropped version) and LFWcrop. For comparison, Log and εL1 also employed as sparsity regularizers. Experiment results confirm that KLD has better performance in image classification of both datasets compared to Log and εL1.
Keywords:	Single Sample Face Recognition, Deep Auto Encoder, Kullback-Leibler Divergence, Sparsity, Sparsity Regularizer
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	QUESTION CLASSIFICATION USING SUPPORT VECTOR MACHINE AND PATTERN MATCHING
Author:	ALI MUTTALEB HASAN, LAILATUL QADRI ZAKARIA
Abstract:	Question classification plays a crucial role in the question answering system, and it aim to accurately assign one or more labels to question based on expected answer type. Nonetheless, classifying users question is a very challenging task due to the flexibility of Natural Language where a question can be written in many different forms and information within the sentence may not be enough to effectively to classify the question. Limited researches have focused on question classification for Arabic question answering. In this research we used support vector machine (SVM) and pattern matching to classify question into three main classes which are "Who", "Where" and "What". The SVM leverage features such as n-gram and WordNet. The WordNet is used to map words in questions to their synonyms that have the same meaning. Five pattern were introduced to analyze "What" question and label the questions with "definition", "person", "location" or "object". The dataset set used in this research consist of 200 question about Hadith from Sahih Al Bukhari. The experimental result scored F-measure at 95.2%, 84.6%, and 83.6% respectively for "Who", "Where" and "What". The result show that the SVM classifier is useful to classify question in Arabic language.
Keywords:	Question Classification System; Machine Learning.
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	SMES PERFORMANCE AND SUBSIDIES IN IT INVESTMENTS: A VIS-A-VIS APROACH
Author:	CHRISTOS LEMONAKIS, KONSTANTINOS VASSAKIS, ALEXANDROS GAREFALAKIS, PETRO PAPA
Abstract:	In the knowledge-based and globalized economy, information provides value to firms and Information Technology (IT) is the mechanism through can be achieved. Companies that exploit endless possibilities of Information Technology obtain the capacity to overcome future challenges. This study is focused on the case of Greek SMEs that face an extremely competitive and unfriendly macro environment and examines the performance of IT investments of Greek SMEs through a combination of qualitative and quantitative longitudinal data. A variety of financial as well as qualitative (primary) data are used for the examination of the correlation between profitability and IT.Α survey-based methodology was used for the collection of qualitative data of Greek SMEs covering the time period of 2004-2010. The examining period is divided into two sub-periods: pre crisis and post crisis periods. Additionally, the examination of the relationship of European IT investment subsidy with firm profitability is examined. The results of this empirical study indicate that companies with IT investments present higher profitability than their rivals. SMEs are the backbone of national economy, thus their competitiveness plays a significant role to national development and growth. Therefore, the findings of this research have implications for practitioners, managers and policy makers.
Keywords:	IT investments, SMEs Performance, Profitability, Competitiveness and European Subsidies
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	GROUP DECISION MAKERS-BASED MODEL FOR EVALUATING THE FEASIBILITY OF INFORMATION AND COMMUNICATIONS TECHNOLOGY PROJECT (CASE STUDY : LOCAL GOVERNMENT OF MUSI RAWAS)
Author:	WIJANG WIDHIARSO, SRI HARTATI, RETANTYO WARDOYO
Abstract:	Feasibility study of information and communications technology (ICT) project becomes more and more important due to the significant growth of ICT project investment as well as its complexity analysis, especially in term of benefit estimation. Recently, Advanced Information Economic (AIE) has been proposed for evaluating the ICT project feasibility, which considers the benefit and cost analysis. In spite of its easiness, AIE remains weakness relating to the subjectivity factor while determine the expected benefit and risk value. This drawback potentially brings the unreasonable result, such as the extremely high value of Return on Investment (ROI). In addition, AIE has not incorporated the group of decision makers, which is practically considered as the main influence factor of project appraisal. This paper substantially discusses the new variant of information economic that considers the group decision maker for evaluating feasibility of ICT project, namely Group Decision Making Information Economic (GDM IE). This method also includes the benefit and risk template to enhance the applicability of GDM IE, where the benefit and risk related value is derived from the actual and practical references gathered from the several local governments in South of Sumatera. Further more, three kinds of models are involved in GDM IE for evaluating the benefit and risk value. First method (i.e., model A) selects the benefits and risks value based on the existing value of the template. Second method (i.e., model B), compares the selected reference value (template) with the new benefit value, which is entered by the user. The last method (i.e., model C), the user can directly entered the value of benefit and risk to evaluate the feasibility of ICT project. To investigate its applicability, this paper also utilized GDM IE for evaluating the ICT projects in Musi Rawas District.
Keywords:	GDM IE, ICT Project, AIE, Benefits, Risks
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	DYNAMIC LOAD BALANCING FOR CLOUD PARTITION IN PUBLIC CLOUD MODEL USING VISTA SCHEDULER ALGORITHM
Author:	MANISHANKAR S, SANDHYA R, BHAGYASHREE S
Abstract:	Larger the information technology grows, larger will be the data generated, balancing the huge data is always a big question for the information management industry. Cloud computing uses virtual data storage and infrastructure which manages stores and processes huge volume of data. As the cloud offers major services to the clients, it is very important to balance the incoming requests. The aim of the system is to propose an efficient scheduling algorithm and to achieve optimal load balancing. The algorithm address the challenges faced with cloud load management by selecting best cloud partition for workload management, incorporating a novel selection and scheduling algorithm with an assignment problem principle approach for scheduling known as VISTA scheduling algorithm and achieving optimized solution with minimum utilization of processing metrics.
Keywords:	Load Balancing, Public Cloud, Cloud Partition, Assignment Problem, Vista Scheduling Algorithm
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	A NOVEL HARDWARE PARAMETERS BASED CLOUD DATA ENCRYPTION AND DECRYPTION AGAINST UN-AUTHORIZED USERS
Author:	KAVURI K S V A SATHEESH, GANGADHARA RAO KANCHERLA, BASAVESWARARAO BOBBA
Abstract:	Now-a-days, there is a revolutionary trend to use cloud services, so more customers are attracting to use public cloud storage. Data storage outsourcing to cloud storage servers is an emerging trend among many firms and users. To relieve from the burden of storage management, broad data access with independent geographical locations and economizing of expenditure investment on software, hardware and maintenance, most of the organizations are outsourcing their data management operations to external service providers. The most attractive part of the cloud computing is the computation outsourcing with its uniqueness, which is becoming the major research area and also getting paid more attention and interest from both academia and industry. As research is progressing day-by-day, obstacles of cloud computing are getting into the focus of vision, simultaneously few challenges are getting solved, and few solutions are better optimized. Among the new born or existing, the challenge which is in most limelight always is security of the outsourced data. Consequently data owner neither have any control on hosted data nor on hosted data centers. Number of techniques addressed this problem, to ensure data security and integrity hosted in cloud. But all of them have their own limitations. In this paper, we propose a new model of CP-ABE, which uses hardware parameters such as cloud instances, server configurations are used in the setup, key generation, encryption and decryption phases.
Keywords:	Attribute-based encryption, Cloud Parameters, CP-ABE, KP-ABE, Cloud Security, Outsourcing Computation.
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	CLOUD COMPUTING SECURITY THROUGH PARALLELIZING FULLY HOMOMORPHIC ENCRYPTION APPLIED TO MULTI-CLOUD APPROACH
Author:	OUADIA ZIBOUH, ANOUAR DALLI, HILAL DRISSI
Abstract:	Cloud computing represents a major change in the way IT resources are utilized and creates value for businesses. It is the future of information technology that offers many benefits such as flexibility, efficiency, scalability, integration and cost reduction. However, the security concern is the major drawback of widespread adoption of this technology by organizations that use sensitive and important information. Therefore, the main aim of this paper is to propose a new framework to secure cloud computing, prevent security risks and improves the performance and the time of data processing .This framework combines between various powerful security techniques such secret sharing schema, Fully Homomorphic Encryption (FHE), multi cloud approach and the implementation of a processing dispatcher which distributes a set of operations on FHE encrypted data between a number of processing engines.
Keywords:	Could Computing, Security, Multi-Clouds, DepSky, RACS, HAIL, ICStore, FHE
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	DESIGN AND CONSTRUCTION OF CONTROL SYSTEM SEPIC CONVERTER FOR SOLAR PANEL BASED ON FUZZY LOGIC
Author:	A. H. LOKA, T. HARDIANTO, B. S. KALOKO
Abstract:	Within renewable energy field, solar panel that principled at photovoltaic effect has been used as alternative energy. MPPT method is using to obtain maximum output power from solar panel if loads are fluctuate. MPPT that implemented use fuzzy logic in function to regulate on/off time of MOSFET in SEPIC converter by generating PWM signals. The results of testing provide load power at irradiance 1000 W/m2, 800 W/m2, 600 W/m2, and 400 W/m2 when using MPPT is close on power value of MPP better than direct-coupled method. Average value of power ratio with MPPT based on fuzzy logic is 70.833 % whereas direct-coupled is only 29.312 %.
Keywords:	Solar Panel, Fuzzy Logic, MPPT, SEPIC converter, Simulink
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	USING DATA MINING TO DEVELOP MODEL FOR CLASSIFYING DIABETIC PATIENT CONTROL LEVEL BASED ON HISTORICAL MEDICAL RECORDS
Author:	TARIG MOHAMED AHMED
Abstract:	Nowadays, diabetes is considered as one of the diseases which cause more deaths than any other disease in the world. To avoid the dangerous complications of the diabetes, patients should control a blood glucose level as the HbA1c (accumulative blood glucose level for 3 months) should be less than 7%. In this paper a new predicted model has been developed by using data mining techniques. The model aims to classify the diabetic patients into two classes which are: under control (HbA1c < 7%) and out of control (HbA1c > 7%). The treatments plans for 10061 diabetic patients were used to build the model. After comprehensive survey for classification techniques, three algorithms have been selected which were NaivaeBayse, Logistic and J48. By using WEKA application, the model has been implemented. Based on the results of experiment, Logistic algorithm has been selected as best one with high accuracy rate of 74.8%. To enhance the model accuracy, the nutrition system and exercise need to be added to the dataset as future work.
Keywords:	Diabetes, Data Mining, Classification techniques
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	WIRELESS FAULT TOLERANCES DECISION USING ARTIFICIAL INTELLIGENCE TECHNIQUE
Author:	MONEER ALI LILO, L.A.LATIFF, AMINUDIN BIN HAJI ABU, YOUSIF I. AL MASHHADANY
Abstract:	Wireless techniques utilized in industrial applications face significant challenges in preventing noise, collision, and data fusion, particularly when wireless sensors are used to identify and classify fault in real time for protection. This study will focus on the design of integrated wireless fault diagnosis system, which is protecting the induction motor (IM) from the vibration via decrease the speed. The filtering, signal processing, and Artificial Intelligent (AI) techniques are applied to improve the reliability and flexibility to prevent vibration increases on the IM. Wireless sensors of speed and vibration and card decision are designed based on the wireless application via the C++ related to the microcontroller, also, MATLAB coding was utilized to design the signal processing and the AI steps. The system was successful to identify the misalignment fault and dropping the speed when vibrations rising for preventing the damage may be happen on the IM. The vibration value reduced via the system producing response signal proportional with fault values based on modify the main speed signal to dropping the speed of IM.
Keywords:	Industrial Wireless Sensor, Artificial Intelligent Technique, Signals Processing, Fault Diagnosis System
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	SURFACING POINT CLOUD DATA FROM MULTIPLE ACQUISITIONS
Author:	GOPAL GAIKWAD, SHRUTI PATIL, ROHIT PATIL, NITIN KARMARKAR
Abstract:	The trend of using LIDAR (Light Detection and Ranging) based systems for surveying is increasing every day. These systems output Point cloud data, which can be further processed to produce vital information about the topology of the surveyed area. In this paper, we provide a novel method to process the point cloud data and build the model of the surveyed area that represent the surveyed area more accurately. This method is more noise tolerable and no need to care about the outliers as these outliers gets eroded by morphological erosion operation. In this way, we will not lose features. The scope of this work is restricted to processing the data surveyed from a closed cavities or cave to understand their topology and estimate their volume. Generally, the surveyed data collected using multiple sample sets and as such, each sample set does not register with each others and may consist holes in point cloud due to operational discrepancies. This approach will use the morphological operation to fill the holes. We thereafter use the Sobel cross gradient operator to find out a common border. The KNN algorithm will then define smoother and much thinner.
Keywords:	Point Cloud, Morphological Operation, Sobel Mask Filter, KNN Algorithm, Multiple
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	PERFORMANCE CHARACTERIZATION OF ROHC FOR SATELLITE-BASED UNIDIRECTIONAL LINKS USING ERROR-FREE CHANNELS
Author:	WAY-CHUANG ANG, MUHAMMAD-IMRAN SARWAR, TAT-CHEE WAN
Abstract:	Satellite communication systems play a vital role in providing Wide Area Network (WAN) due broader coverage but at the same time impose challenge for IP services in unidirectional Satellite link. This research evaluates RObust Header Compression (ROHC) for Unidirectional Lightweight Encapsulation (ULE) in terms of network performance and practical implementation design of a ROHC via Satellite test-bed. Moreover, mathematical model was presented to estimate the theoretical performance characteristics of ROHC compressed traffic which is then compared with empirical results. The experiments showed that ROHC delivered significant improvement in bandwidth utilization for packets with small payload sizes with up to 86% gain in throughput performance when compressing traffic. Packets with larger payload sizes exhibited an exponential decrease of throughput gain achievable through ROHC as the size of the payload increased. This paper also discusses the effectiveness of ROHC for IPv4 versus IPv6 traffic that was evaluated indicates IPv6 traffic streams benefited to a greater degree from ROHC than did IPv4 traffic streams, even on non-ideal links.
Keywords:	Satellite Communication, Unidirectional Lightweight Encapsulation (ULE), RObust Header Compression (ROHC), Digital Video Broadcasting Satellite (DVB-S), Mesh Networking
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text

Title:	JOIN-LESS APPROACH FOR FINDING CO-LOCATION PATTERNS- USING MAP-REDUCE FRAMEWORK
Author:	M.SHESHIKALA, D.RAJESWARA RAO, R. VIJAYA PRAKASH
Abstract:	Spatial co-location patterns represent a subset of features whose instances are frequently co-located in close proximity; For example Mountain area and new truck purchased are frequently co-located patterns, indicating that a person living close to mountainous areas is likely to buy a truck. Since the instances of spatial features are embedded in a continuous space and share a variety of spatial relationships the implementation of co-location mining can be taken as a challenge. For this, many Algorithms have been proposed, but they are prohibitively expensive with the larger data sets. We propose a parallel join-less approach for co-location pattern mining which materializes spatial neighbour relationships without any loss of the co-location instances. The parallel join-less approach drastically reduces the computation time in finding an instance look-up schema which is used for identifying co-location instances, whereas the previous join-less co-location mining algorithm finds the instances sequentially which increases the computation time. The proposed algorithm is developed on Map-Reduce. The experimental results shows the speed up in computational performance. This algorithm works well for data sets with larger size &having more number of features. As the size of the data set decreases it becomes close to the sequential approach.
Keywords:	Spatial data Mining, Parallel Co-location Mining, join-less, Approach, Participation Ratio, Participation Index, Map Reduce
Source:	Journal of Theoretical and Applied Information Technology 20^th May 2016 -- Vol. 87. No. 2 -- 2016
Full Text