		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 2018 | Vol. 96 No.4

Title:	REAL TIME FACIAL EXPRESSION RECOGNITION IN THE PRESENCE OF ROTATION AND PARTIAL OCCLUSIONS
Author:	FARHAD GOODARZI, M. IQBAL SARIPAN, MOHD HAMIRUCE MARHABAN, FAKHRUL ZAMAN BIN ROKHANI
Abstract:	In the real world, occlusion is considered as an important problem in the domain of emotion recognition. This study investigates the occlusion in real time using a fully automatic system. The features are extracted effectively from special areas of the face using both texture and geometrical features on the face. The system uses a trained backpropagation neural network to find the seven basic emotions. The experiments were conducted on normal, and with occlusions on forehead, eyes, and mouth. The proposed system was able to detect emotions with high recognition rates. The results are presented for near frontal and multi view faces using UPM3DFE and BU3DFE 3D facial expression databases.
Keywords:	Face Emotion Recognition, Neural Network, Backpropagation, Feature Extraction, Occlusion, 3DFE
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	A BAYESIAN NETWORK APPROACH TO MINE SPATIAL DATA CUBE
Author:	MIDOUN MOHAMMED, BELBACHIR HAFIDA
Abstract:	Spatial data mining is an extension of data mining that considers the interactions in space. It involves various techniques and methods in various areas of research. It takes into account the specificities of spatial information such as spatial relationships that can be topological, metric or directional. These relationships are implicit and difficult to represent. A Bayesian network is a graphical model that encodes causal probabilistic relationships among variables of interest, which has a powerful ability for representing and reasoning and provides an effective way to spatial data mining. Moreover, spatial data cubes allow storage and exploration of spatial data. They support spatial, non-spatial and mixed dimensions. A spatial dimension may contain vector and raster data. The spatial hierarchies can represent topological relationships between spatial objects. We propose to use Bayesian networks for knowledge discovery in spatial data cubes. The goal of our approach is first to consider spatial relationships in the data mining process, and secondly to benefit from the strength of the data warehouses to apply spatial data mining on different aggregation levels according to the topological relations between spatial data. In this article, we give a state of the art on spatial data mining and propose a framework for data mining in spatial data cubes, using Bayesian networks. We show in the proposed case study that our approach confirms the results observed in the field and it is an important way to take into account the specificities of spatial data in the spatial data mining process.
Keywords:	F Spatial data mining, Bayesian networks, Spatial data cube, Spatial aggregation, Spatial Analysis
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	CLUSTERING FAILED COURSES OF ENGINEERING STUDENTS USING ASSOCIATION RULE MINING
Author:	ROSEMARIE M. BAUTISTA
Abstract:	In todays world, the fast-paced changes in technology and upswing volume of organizational data in almost all domains including academe are very remarkable. This coupled with the aspiration to gain competitive advantage necessitate the utilization of data mining. This paper applies the processes in the Knowledge Discovery in Databases by Fayyad and presents in methodological way the steps performed towards finding the associations between courses failed by engineering students. It started with the preparation of data moving towards proper transformation of it for data mining and concluding with data interpretation and evaluation. Using association rule mining through Apriori algorithm, the rules were extracted from the database. The statistical significance and the strength of the rule were analyzed using 3 measures of usefulness: lift, support and confidence. All the rules generated have positive co-relation, that is, the relationships of the consequent of the rule with the antecedent are not due to chance. The over-all output of the study is expected to offer viable results that may be used by administrator, academic advisor and curriculum planners in devising worth-while strategies such as improvement of teaching methodology, re-structure of curriculum, modification of course pre-requisites or development of supplemental activities to students.
Keywords:	Data Mining, Association Rule Mining, Market Basket Analysis, Knowledge Discovery in Databases, Educational Data Mining
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	ENGLISH SENTIMENT CLASSIFICATION USING A GOWER-2 COEFFICIENT AND A GENETIC ALGORITHM WITH A FITNESS-PROPORTIONATE SELECTION IN A PARALLEL NETWORK ENVIRONMENT
Author:	DR.VO NGOC PHU, DR.VO THI NGOC TRAN
Abstract:	We have already studied a data mining field and a natural language processing field for many years. There are many significant relationships between the data mining and the natural language processing. Sentiment classification Has HAd many crucial contributions to many different fields in everyday life, such as in political Activities, commodity production, and commercial Activities. A new model using a Gower-2 Coefficient (HA) and a Genetic Algorithm (GA) with a fitness function (FF) which is a Fitness-proportionate Selection (FPS) has been proposed for the sentiment classification. This can be applied to a big data. The GA can process many bit arrays. Thus, it saves a lot of storage spaces. We do not need lots of storage spaces to store a big data. Firstly, we create many sentiment lexicons of our basis English sentiment dictionary (bESD) by using the HA through a Google search engine with AND operator and OR operator. Next, According to the sentiment lexicons of the bESD, we encode 7,000,000 sentences of our training data set including the 3,500,000 negative and the 3,500,000 positive in English successfully into the bit arrays in a small storage space. We also encrypt all sentences of 8,000,000 documents of our testing data set comprising the 4,000,000 positive and the 4,000,000 negative in English successfully into the bit arrays in the small storage space. We use the GA with the FPS to cluster one bit array (corresponding to one sentence) of one document of the testing data set into either the bit arrays of the negative sentences or the bit arrays of the positive sentences of the training data set. The sentiment classification of one document is based on the results of the sentiment classification of the sentences of this document of the testing data set. We tested the proposed model in both a sequential environment and a distributed network system. We achieved 88.12% accuracy of the testing data set. The execution time of the model in the parallel network environment is faster than the execution time of the model in the sequential system. The results of this work can be widely used in applications and research of the English sentiment classification.
Keywords:	English Sentiment Classification; Distributed System; Gower-2 Similarity Coefficient; Cloudera; Hadoop Map And Hadoop Reduce; Genetic Algorithm; Fitness-Proportionate Selection
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	THE IMPACT OF DEMOGRAPHIC FACTORS AND VISUAL AESTHETICS OF MOBILE APPLICATION INTERFACE ON INTENTION TO USE MOBILE BANKING IN JORDAN
Author:	MALIK KHLAIF GHARAIBEH, MUHAMMAD RAFIE MOHD ARSHAD
Abstract:	The current study examined the effect of demographic profiles and visual aesthetics of mobile application interface on the intention of using mobile banking services among clients living Jordan. The proposed research model was based on three aesthetics from human compute interaction researches. We used SPSS version 22 to analyse the data which was composed of 579 questionnaires from different cities in Jordan using the convenience sampling technique. This study empirically presents that the intention of using mobile banking was positively and significantly influenced by the simplicity of mobile application interface and colourfulness of mobile application interface. Meanwhile, craftsmanship of mobile application interface was found to be insignificantly affected by the intention to use. The results also showed that the intention to use is statistically impacted by internet usage frequency. In contrast, age and familiarity with mobile applications have not significant effect on intention to use mobile banking. There are several factors that bring efficiency to the intention to use mobile banking. Prior studies investigated the relationship between these variables and the adoption of mobile banking services. However, none has paid attention on the impact of visual aesthetics on the intention to use mobile banking services. Findings of the current study prove that the proposed research model is a comprehensive to study the acceptance of mobile banking in Jordan. Overall, the results indicated the appropriateness of fundamental elements of visual aesthetics model in mobile banking adoption context.
Keywords:	Visual Aesthetics; Simplicity Of Mobile Application Interface; Mobile Banking; Jordan.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	HILBERT SPACE RELATIONAL SCATTERED DISTANCE CLUSTERING FOR DENSELY POPULATED AND SPARSELY DISTRIBUTED HIGH DIMENSIONAL DATA OBJECTS
Author:	R.PUSHPALATHA, Dr.K.MEENAKSHI SUNDARAM
Abstract:	Clustering high-dimensional data is the process of grouping the similar data from large amounts of database. Hence it is essential and significant issue in both machine learning and data mining. But, Clustering on high dimensional data has low accuracy and quality of the clustering algorithm is reduced due to the data objects from a variety of clusters in different subspaces consisting of dissimilar groupings of dimensions. The Different clustering algorithm is designed to solve the difficulties, however the cluster objects hides in the subspaces due to it sparseness and low dimensionality. In order to evaluate both sparsely distributed and densely populated data objects in any given plane, Hilbert Space Relational Scattered Distance Clustering (HS-RSDC) technique is introduced. The HS-RSDC using Controlled Effort Boundary Operation namely UNION_BOUND, INTERSECT_BOUND and PARTITION_BOUND to improve the clustering accuracy. This helps to improve multi space data object mining quality in various real world clustering applications. The Hilbert space relational cluster objects are processed for producing the accurate cluster by reducing subspaces in the data plane. After that, Scattered Distance measures are employed to calculate the distance of geometric median. Finally, the HS-RSDC boundary computation operations associate unlabeled data objects to more appropriate cluster using relational object number. The relational object number is assigned internally and globally in HS-RSDC method to remove unlabelled data objects and to discover different types of correlation events over the cluster objects. HS-RSDC handles the boundary overhead and improves the efficiency of user pruning queries. By minimizing the number of intermediate pruning, the total traversal length of data object search is reduced. Experimental results show that the proposed HS-RSDC method increases the performance in terms of clustering accuracy, clustering time, space complexity.
Keywords:	Data Mining, High Dimensional Data, Cluster Analysis, Hilbert Space, Pruning Process, Scattered Distance, Controlled Effort Boundary Operation.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	A REVIEW AND OPEN ISSUES OF MULTIFARIOUS IMAGE STEGANOGRAPHY TECHNIQUES IN SPATIAL DOMAIN
Author:	MOHAMMED MAHDI HASHIM, MOHD SHAFRY MOHD RAHIM, ALI ABDULRAHEEM ALWAN
Abstract:	Nowadays, information hiding is becoming a helpful technique and fetch more attention due fast growth of using internet, it is applied for sending secret information by using different techniques. Steganography is one of major important technique in information hiding. Steganography is science of concealing the secure information within a carrier object to provide the secure communication though the internet, so that no one can recognize and detect it's except the sender & receiver. In steganography, many various carrier formats can be used such as an image, video, protocol, audio. The digital image is most popular used as a carrier file due its frequency on internet. There are many techniques variable for image steganography, each has own strong and weak points. In this study, we conducted a review of image steganography in spatial domain to explore the term image steganography by reviewing, collecting, synthesizing and analyze the challenges of different studies which related to this area published from 2014 to 2017. The aims of this review is provides an overview of image steganography and comparison between approved studies are discussed according to the pixel selection , payload capacity and embedding algorithm to open important research issues in the future works and obtain a robust method.
Keywords:	Information Hiding, Image Steganography, Least Significant Bit (LSB), Different types of Steganography, Spatial Domain.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	GAME-THEORETICAL MODEL OF LABOUR FORCE TRAINING
Author:	IRINA ZAITSEVA, OLEG MALAFEYEV, SERGEI STREKOPYTOV, ANNA ERMAKOVA, DMITRY SHLAEV
Abstract:	The continuous and discrete models of labour force training are being built. The application of the results from the theory of differential games and dynamic programming allows presenting the optimal strategies of labour force training that can be calculated.
Keywords:	Continuous Game-Theoretical Model, Discrete Game-Theoretical Model, Labor Force Training.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	PERFORMANCE STUDY IN AUTONOMOUS AND CONNECTED VEHICLES A INDUSTRY 4.0 ISSUE
Author:	ALESSANDRA PIERONI, NOEMI SCARPATO, MARCO BRILLI
Abstract:	Industry 4.0 represents an opportunity. The term 4.0 is used to specify the current industrial revolution, not-only from the technological point of view but also from the economical, sociological and strategical point of view. Indeed, this revolution involves different sectors: from manufacturing to healthcare. Its disruptive diffusion is due to several enabling technologies, such as Internet of Things (or Internet of Everything or Industrial Internet of Things), and, as said, it is a vision rather than a technological step forward. In this evolutionary process, the Connected and Autonomous Vehicles (CAVs) represent the perfect connection between technology and society world, an issue that stands actually in the center of Industry 4.0. This article intends to extend a previous work of the authors, in which a new and non-conventional approach to manage the great amount of data that is generated by the CAVs has been proposed. In particular, the validity of the approach will be demonstrated by means of performance indices specifically defined for this case study.
Keywords:	Autonomous Vehicle, Connected Vehicle, Big Data, Graphdb, Internet Of Things, Industry 4.0, Performance Indices.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	PREVENTING SECURITY ATTACKS ON MOBILE PATTERN PASSWORDS
Author:	Bh PADMA, GVS RAJKUMAR
Abstract:	An Android Smartphone is a personal device, which keeps many of our personal files and data, such as photos, videos, messages, bank account information etc. Keeping these files safe from outsiders may be troublesome especially when they try to speculate the device passwords. So Android authentication processes should always pursue robust security enhancements to preserve the security of the sensitive data stored in the mobiles. For pattern locking systems of Android, older versions such as Kit Kat and Lollipop make use of authentication systems which rely on SHA-1 and MD5 unsalted hashes, but the latest versions such as Android Marshmallow employ Gatekeeper Mechanism and store the passwords and authenticate the users in a trusted execution environment and are more secured from brute-forcing. The former methods are vulnerable to dictionary and rainbow table attacks since they are unsalted hashes, whereas the later Android hashing schemes such as HMAC or Scrypt hashes use salts for hashing but cannot flee from hacker’s forensic tools that crack the passwords and they do need an additional hardware support. Therefore this paper presents two substitute methodologies that suggest a new approach to enhance the basic SHA-1 hashing scheme using Elliptic Curves to prevent pre-computation attacks such as dictionaries, rainbow tables and brute forcing on pattern password scheme. These proposed methods seem to be simple and secure without employing a complex hardware-backed environment such as Trusted Execution Environment (TEE). This paper also presents a comparison among the proposed schemes with respect to Strict Avalanche Effect and CPU Execution Times after the implementation.
Keywords:	Android, Smartphone, SHA-1, Brute- Force, Dictionaries, TEE
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	THE INFLUENCE OF PERCEIVED RISK AND CONSUMER INNOVATIVENESS ON INTENTION TO USE OF INTERNET OF THINGS SERVICE
Author:	JUNGYEON SUNG, JAEWOOK JO
Abstract:	The current study is focused on consumer response for IoT (the Internet of Things) service. In particular, it explored consumer response which is influenced by the intention to use based on the Unified Theory of Acceptance and Use of Technology (UTAUT). UTAUT has been generally introduced as model and theory of adoption of new technology instead of Technology Acceptance Model (TAM). It is used as an exploration research for consumer’s response of IoT service. Even though technology has improved and rapidly changed, if it doesn’t understand how to adjust or work well from the point of view of consumer, the technology won’t be necessary for consumers. The results of 147 participants show that moderating effect of consumer innovativeness is influenced on attitude toward IoT service and intention to use. So, the result of the study indicated the point of view consumer’s response such as perceived risk and consumer innovativeness different from previous research in the basis of UTAUT.
Keywords:	IoT, UTAUT, Perceived risk, Consumer innovativeness, Intention to use
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	ADAPTIVE SPECTRAL SUBTRACTION FOR ROBUST SPEECH RECOGNITION
Author:	JUNG-SEOK YOON, JI-HWAN KIM, JEONG-SIK PARK
Abstract:	Speech recognition rate degrades drastically in extreme noisy environments. Spectral subtraction is one of the representative noise reduction method, but it is vulnerable to non-stationary noise although it is quite effective for stationary noise. In this paper, we propose an adaptive spectral subtraction method to improve the speech recognition performance. The proposed method is to consistently update the noise component in non-speech regions and remove the corresponding component in following speech regions. To validate of the noise reduction performance, we conducted several experiments for each noise power level. Our approach achieved better performance compared to the conventional spectral subtraction approach.
Keywords:	Noise Reduction, Spectral Subtraction, Speech Recognition, Voice Activity Detection
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	A STUDY ON BIG DATA BASED NON-FACE-TO-FACE IDENTITY PROOFING MODEL
Author:	HEEGYUN YEOM, DAESON CHOI, KWANSOO JUNG, SEOKHUN KIM
Abstract:	Online service providers are increasingly considering the adoption of a variety of additional mechanisms to supplement the authentication security provided by conventional password verification. Recently, the authentication and authorization methods using the user attribute information have been used for various services. In particular, the need for various approaches to non-face-to-face identification technology for online user registering and authentication are increasing demands because of the growth of online financial services and the rapid development of financial technology. However, non-face-to-face approaches can be generally exposed to a greater number of threats than face-to-face approaches. Therefore, identification policies and technologies to verify users by using various factors and channels are being studied in order to complement the risks and to be more reliable non-face-to-face identification methods. One of these new approaches is to collect and verify a large number of personal information of user. Thus, we propose a big-data based non-face-to-face Identity Proofing model that verifies identity on online based on various and large amount of information of user. The proposed model performs identification of various attribute information required for the identity verification level. In addition, the proposed model can be quantified identity proofing reliability as collects and verifies only the user information required for assurance level of identity proofing.
Keywords:	Non- Face-To -Face, Authorization, Identity Proofing, Big Data
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	QOS-DRIVEN MIGRATION SCHEME BASED ON PRIORITY IN CLOUD COMPUTING
Author:	A-YOUNG SON, EUI-NAM HUH
Abstract:	Migration used many areas like resource management in cloud computing environment. Numerous schemes of resource scaling based on migration are designed in the Cloud Data Center (CDC) s. However, cloud service providers (CSPs) have not yet provided sufficient efficiency to meet user requirements such as energy efficiency, performance and cost. Furthermore, most of the previous researches did not consider the multi-metric. Thus, we have to consider combining decision method with Fuzzy and AHP for multi-metric. The simulations show that the hierarchical migration scheme is necessary to meet user requirement. In this paper, we proposed migration scheme based on priority in cloud computing. We also performed resource scaling based on fuzzy system and analyzed effect of metric to maximize energy efficiency. Finally, we demonstrated the proposed method by using different migration strategies.
Keywords:	Cloud computing, Resource scaling, Analytical Hierarchical Process (AHP), Fuzzy, Multi-Criteria Decision Making (MCDM), Data Center
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	INTERGRATED MULTILAYER METADATA BASED ON INTELLECTUAL INFORMATION TECHNOLOGY FOR CUSTOMIZATION SERVICES OF IMAGES WITH DIFFERENT USAGE PERMISSION OF LICENSE
Author:	EUN-JI SEO, IL-HWAN KIM , DEOK-GI HONG , YOUNGMO KIM, SEOK-YOON KIM
Abstract:	Tags and metadata are used to manually retrieve public domain images, but it would require a lot of time and money to build such a system into an automated one. Therefore, it is necessary to extract the tags and metadata utilizing intelligent information technology, and semantic metadata is preferred for this purpose rather than simple metadata for each image content. In this paper, we have designed and implemented multi-layer metadata that can be used for customized search recommendation based on intelligent information using MPEG-7, Dublin core, and CCRel. The metadata of public domain images are described with the right of usage, feature information and semantic information, and they are expressed in an XML document form so that they can be exchanged on the web easily.
Keywords:	Intelligent Information Technology, Public Domain Works, Free-use Licenses, Metadata
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	A STUDY ON CLOUD-BASED MEDIA SERVICE REFERENCE MODEL SUPPORTING MULTI-DRM
Author:	YOUNGMO KIM, BYEONGCHAN PARK, YU-HYEON WON
Abstract:	In the online content distribution platform, DRM technology is the core technology for implementing business model, and most distribution platforms use only one DRM technology. While the sales amount in these content distribution platforms is distributed to the copyright owner and the content distributor accordingly, the copyright owner and user cannot choose a different DRM purchase cost since only the DRM technology proposed by the content distributor is used. In this paper, we analyze the requirements for constructing media service platform supporting multi-DRM with more than one DRM and propose a cloud-based media service model that supports multi-DRM based on these requirements. The simulation results shows that the profit settlement part of the proposed reference model yields fair dividend payment to participants according to the actual usage rate of DRM and contents.
Keywords:	Cloud Media Service, DRM, Copyright, Reference Model
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	A STUDY ON iBiz.FS ARCHITECTURE DESIGN FOR ESTABLISHING ELECTRONIC FINANCE SYSTEM
Author:	KYUNG-MO KOO, KOO-RACK PARK, DONG-HYUN KIM
Abstract:	Recently, financial institutions regard the role of bank branches as important but the cases of branches' closure and integration are occurring more often. Also electronic finance related services of financial institutions are migrating to further diverse and complicated shape, and customers' dependence on system is abruptly increasing. Accordingly, accurate processing of transaction data produced from the system and the security thereof shall be deemed as very important factors. In order to establish this system, it is necessary to set up the system with further systematic and standardized element. In this regard, this thesis proposes the architecture design methodology suitable to establishment of electronic finance system based on information engineering design methodology. The development methodology proposed herein is equipped with efficient and standardized structure, and is expected to enable establishment of speedy and stable system by software design based on application architecture. The verification result of the proposed design methodology shows the effect of reducing the number of duration days by 13.2%, and cost reduction by 15.1%. Through the proposed architecture design methodology, the ground for systemic design at even high level in the area to establish electronic finance system would be introduced, and through this system development period would be accelerated and development costs would be saved. By application of further systematic standardization in development of electronic finance system, high quality system could be developed. As the direction for future study, studies are required for additional analyses on technology and security architecture applicable to electronic finance system. Through these analyses, further studies on flexible expandability and systematic practice architecture application method shall be maintained.
Keywords:	Application Architecture, Information Engineering Methodology, e-Bank System, Software Development Standard, Message Processing Method, Framework, Business Process
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	DECLARATIVE STACK FOR DISTRIBUTED GRAPH PROCESSING
Author:	RADWA ELSHAWI, ARWA ALDHABAAN, SHERIF SAKR
Abstract:	Recently, people, devices, processes and other entities have been more connected than at any other point in history. In general, graphs have been used to represent data sets in various application domains including computational biology, social science, telecommunications, astronomy, semantic web and protein networks among many others. In practice, systemsstacks of large scale graph processing platforms are suffering from the lack of declarative processing interface. They are mainly relying on low level programming abstractions which can be only used by sophisticated software developers and are not adequate for many users. In order to tackle this challenge and improve the performance and user acceptance of large scale graph processing frameworks, we present a declarative querying framework that can seamlessly integrate with various big graph processing system platforms. Our experimental evaluation shows the effectiveness and efficiency of our proposed framework.
Keywords:	Big Data, Big Graph, Hadoop, Spark
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	POCS-VF: PROXIMATE OPTIMUM CHANNEL SELECTION THROUGH VOID FILLING AND BURST SEGMENTING FOR BURST SCHEDULING IN OBS NETWORKS
Author:	V. KISHEN AJAY KUMAR, K. SURESH REDDY, M.N. GIRI PRASAD
Abstract:	The burst scheduling in OBS networks is critical research objective that attained the interest of many researchers in last few years. OBS is phenomenal and promising data transfer strategy for present and future internet communication requirements. It is clearly quoted in acclaimed recent reviews on burst scheduling in OBS networks that optimal burst scheduling models are in considerable need in the context of minimizing the burst drop ratio and maximizing the channel utilization. Hence in this regard, a novel burst scheduling with burst segmenting and void filling strategy called “Proximate Optimum Channel Selection through Void Filling and Burst Segmenting” strategy for burst scheduling in OBS networks is proposed here in this manuscript. The experimental study done on simulation environment evincing that the proposed model is optimal with minimal burst drop ratio, maximum channel utilization and minimal average time to schedule that compared to the contemporary benchmark model called MSBFVF found in recent literature.
Keywords:	Burst Scheduling, Optical burst switching, Void filling, Burst drop ratio
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	USING K-MEANS ALGORITHM AND FP-GROWTH BASE ON FP-TREE STRUCTURE FOR RECOMMENDATION CUSTOMER SME
Author:	MUHAMMAD ALI SYAKUR, BAIN KHUSNUL KHOTIMAH, EKA MALA SARI ROCHMAN, BUDI DWI SATOTO
Abstract:	The market basket has been finded patterns of purchase customer in SME. Purchase patterns can help to make recommendations and product promotions. This research used K-Means algorithm for sales data clustering and uses FP-Growth Algorithm to know the relation of each cluster. K-Means clustering to classify customer data based on the same attribute, then determined the relationship between patterns in each group with FP-Growth Algorithm. K-Means to do customer segmentation based on background, customer characteristic and level of purchasing power. To facilitate the analysis of customer relationships with products purchased, then each cluster profilling customer will be processed data record by FP Growth to know the relevance of goods purchased. The research presents a discussion of the comparison of time complexity between FP-Growth algorithms and Apriori Algorithms. This research would been done the development and application of the use of Trees ie FP-Tree (Frequent Pattern Tree). They are an extension of the use of Trees in the data structure. FP-Tree is used in conjunction with the FP-Growth algorithm to determine the frequent itemset of a database, in contrast to the a priori paradigm of scanning the database repeatedly to determine the frequent itemset. In this study, the number of transactions with many items of goods and consumer purchasing power are varied, grouped first by using K-Means algorithm, cluster results formed into several groups including five customer groups based on customer profile. The result of the test is average on minsupp = 60 and minconf = 40, so the average processing time is 957 ms.
Keywords:	K-Means, Fp-Growth, FP-Tree, SME, Profilling Customer, Pattern
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	EVALUATION OF FEATURES FOR VOICE ACTIVITY DETECTION USING DEEP NEURAL NETWORK
Author:	SUCI DWIJAYANTI, MASATO MIYOSHI
Abstract:	Voice activity detection (VAD) is implemented in the preprocessing stage of various speech applications to identify speech and non-speech periods. Recently, deep neural networks (DNNs) have been utilized for VAD given their superior performance over other methods. When used to identify speech and non-speech periods, DNNs depend on the input of different features to discriminate speech from noise. Hence, different features have been used as input for DNN-based VAD. However, the contribution and effectiveness of such features have not been thoroughly evaluated. In this paper, we address these aspects by comparing five features, namely, log power spectra, filter bank, mel-frequency cepstral coefficients, relative spectral perceptual linear predictive analysis, and amplitude modulation spectrogram, which are widely used on speech processing, to evaluate their performance in a DNN-based VAD. Experiments on the TIMIT speech corpus show that the amplitude modulation spectrogram is the feature with the best performance given its high accuracy even when processing speech data with low signal-to-noise ratio. The next feature showing high performance is log power spectra, which can be considered as a raw feature because it does not require as many calculations or processing as the other features. This suggests that raw features may be suitable inputs for DNN-based VAD. Moreover, limiting the number and processing of features for DNNs may foster system performance, real-time application, and portability of VAD by reducing the computational cost, required memory and storage.
Keywords:	DNN, Speech Period, Speech Features, Voice Activity Detection, Amplitude Modulation Spectrogram, Log Power Spectra
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	IMPROVING QUALITY OF SOFTWARE DEVELOPMENT LIFE CYCLE (SDLC) PROCESS USING CMMI FOR DEVELOPMENT VERSION 1.3 (A CASE STUDY APPROACH)
Author:	SITI ELDA HIERERRA, YOHANNES KURNIAWAN
Abstract:	The purpose of this research is to know how to improve the quality of Software Development Life Cycle (SDLC) process through some stages: identify existing SDLC process weaknesses, provide an evaluation of the current SDLC process, and provide solutions to overcome its weaknesses. Analysis methods used in this research based on CMMI Development version 1.3 by referring to the continuous representation and project roadmap which focus on 5 (five) processes area: Project Planning, Project Monitoring and Control, Requirement Management, Configuration Management, Process and Product Quality Assurance. Assessment method used in this research is SCAMPI (Standard CMMI Appraisal Method for Process Improvement) Class C. Based on the results of the assessment, SDLC process has not been yet successfully reach capability level 1 due to the organization has not yet implement fully specific practices on five processes area, so it means there is still a score less than 4 (four) for the specific practice. Based on these results, author gives the proposed solution for specific area which still has a weakness, in order to increase the specific practice score into 4 (four).
Keywords:	Software Development Life Cycle, CMMI for development, Continuous Improvement, Information system, Software Development.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	EXTRACTING UML MODELS AND OCL INTEGRITY CONSTRAINTS FROM OBJECT RELATIONAL DATABASE
Author:	TOUFIK FOUAD, BAHAJ MOHAMED
Abstract:	Database reverse engineering is the process of extracting and transforming database metadata to a rich set of models. These models must be able to describe data structure at different levels of abstraction, starting from physical to conceptual schema. The obtained schema may be used to ease, among others, database structure update, evolution and maintenance. In the past few years, the object oriented construct was merged into relational database. Nevertheless, a few methods of object relational database (ORDB) reverse engineering was presented. In this sense, the main goal of this article is to present an approach of database reverse engineering which cover the transformation of new added object construct. At the end of transformation we obtain a conceptual schema (CS) expressed as UML class diagram. The returned CS is extended with a set of OCL (Object Constraint Language) clauses which represent at a higher level of abstraction, the database integrity constraints. We provide a program that implements our approach for ORACLE 11g database management system.
Keywords:	UML, OCL, ORDB, SQL, Reverse Engineering
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	FUZZY MULTI-CRITERIA RANDOM SEED AND CUTOFF POINT APPROACH FOR CREDIT RISK ASSESSMENT
Author:	BEULAH JEBA JAYA Y., DR. J. JEBAMALAR TAMILSELVI
Abstract:	Data mining classification techniques have been studied extensively for credit risk assessment. Existing techniques by default uses 0.5 as the cutoff irrespective of datasets and classifiers to predict the binary outcomes, thus limiting their classification performance on imbalanced group sizes of datasets. This paper addresses two key problems with the existing techniques and talks about the advantages of using Multiple Criteria Decision Making (MCDM) technique on multiple evaluation criteria. The first key problem is applying default cutoff irrespective of datasets and classifiers. The second one is utilizing single criteria for evaluating classification performance and predicting cutoff point. This research work identifies the best cutoff point with respect to datasets and classifiers and integrates MCDM under fuzzy environment in all data mining stages of evaluation to take better decisions on multiple criteria, selection of initial random seed in the clustering phase for better cluster quality and Best Seed Clustering combined Classification (BSCC hybrid algorithm) with selected features to improve classification performance. The integration of these techniques gives a better hand to improve cluster quality and classification performance score with respect to datasets and classifiers because the cutoff point varies from dataset to dataset and classifiers to classifiers. Experimental outcomes from applied credit dataset of UCI machine learning repository found to be competitive and the proposed BSCC hybrid algorithm increases the performance score on obtained cutoff point over non-hybrid approach with default cutoff.
Keywords:	Credit Risk, Classification, Clustering, Fuzzy MCDM, Cutoff Point, Random Seed
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text

Title:	A FRAMEWORK FOR HANDLING BIG DATA DIMENSIONALITY BASED ON FUZZY-ROUGH TECHNIQUE
Author:	1MAI ABDRABO, MOHAMMED ELMOGY, GHADA ELTAWEEL, SHERIF BARAKAT
Abstract:	Big Data is a huge amount of high dimensional data, which is produced from different sources. Big Data dimensionality is a considerable challenge in data processing applications. In this paper, we proposed a framework for handling Big Data dimensionality based on MapReduce parallel processing and FuzzyRough for feature selection. This paper proposes a new method for selecting features based on fuzzy similarity relations. The initial experimentation shows that it reduces dimensionality and enhances classification accuracy. The proposed framework consists of three main steps. The first is the preprocessing data step. As for the next two steps, they are a map and reduce steps, which belong to MapReduce concept. In map step, FuzzyRough is utilized for selecting features. In reduce step, the fuzzy similarity is presented for reducing the extracted features. In our experimental results, the proposed framework achieved 86.4% accuracy by using decision tree technique, while the accuracy of the previous frameworks, which are performed on the same data set, achieved accuracy between 70 to 80%.
Keywords:	uzzyRough set, MapReduce, Feature selection, Decision tree.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2018 -- Vol. 96. No. 4 -- 2018
Full Text