		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
March 2019 | Vol. 97 No.06

Title:	CORRELATES OF SUCCESS IN JAVA PROGRAMMING: PREDICTING THE PERFORMANCE OF STUDENTS IN A JAVA COURSE FROM THE RESULTS OF LOWER LEVEL COURSES
Author:	BASHIR S GALADANCI, MARYAM I MUKHTAR, SANAH A MUAZ
Abstract:	Over the years, a number of factors that could determine success in programming have been investigated; yet computer programming is still challenging to most students. This paper is aimed at determining the relationship among students’ results of a third year Java Workshop Course with those of lower level courses taken in year one and year two and then developing predictive models based on this relationship. The examination results in 20 courses for a total of 109 students of Bayero University Kano that enrolled for BSc Computer Science course in the 2012/2013 session are analyzed using correlation and linear regression. The correlation results revealed that out of the 20 selected courses, the strongest correlation occurs in the course ((CSC2251: Analysis of Algorithms) (r= 0.756), p<0.001). Some programming courses, Computer Science theory courses (CSC) and Mathematics courses were also found to have strong correlations with the Java performance. The regression results revealed that a regression module, based upon the linear combination of (CSC 2203(VB), CSC2212 (C++), (CSC2251 (Analysis of Algorithms), CSC2202 (Data Structures) and CSC 1303(Introduction to Computer Science)) which is statistically significant at, F_ (5, 103) = 47.09, p = .000 accounts for 70% variance in the Java Programming results.
Keywords:	Predicting Performance, Java Programming, Correlation, Regression, Students
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	THE CITIZENS ACCEPTANCE FACTORS OF TRANSPORTATION APPLICATION ONLINE IN BATAM: AN ADAPTATION OF THE UTAUT2 MODEL AND INFORMATION SYSTEM SUCCESS MODEL
Author:	MANGAPUL SIAHAAN, NILO LEGOWO
Abstract:	The growth of the internet and the advance of information technology, made very significant changes to transportation in Indonesia especially in Batam City. The emergence of applications for online transportations services such as Gojek / Grab has made some people switch to using conventional transportation to online transportation. But with the development of online transportation, there are still people in Batam City taking action against online transportation. For this reason, researchers conducted research to look for factors that influence the acceptance of the people of Batam City on online transportation. The researcher used the UTAUT2 research model (Unified Theory of Acceptance and Use of Technology 2) and the IS Success Model DeLone & McLean. The construct of this research model uses constructs of performance expectancy, effort expectancy, facilitating conditions, price value, information quality, system quality, service quality, behavioral intention, user satisfaction, use behavior. The number of respondents in this study amounted to 400 respondents using SPSS Amos version 22. The results of the analysis showed that the factors that significantly influenced the acceptance of the people of Batam City on the application of online transportation services were seen from constructs of behavioral intention (user intention) 91.2%, performance expectancy is 51.7%, price value is 42.6%, while construct of user satisfaction is influenced by system quality by 68%, information quality is 28.2%, service quality is 12.6%.
Keywords:	Transportation application online, UTAUT2, Information System Success Model Five
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	DEVELOPMENT AND ANALYSIS OF QUALITY COMPREHENSIVE MODEL WITH SCRUM TREE ALGORITHM FOR AUTOMATIC USER STORY PROCESSING
Author:	MRS. RUPALI A. MAHAJAN, DR. S. K. YADAV, DR. SURENDRA A. MAHAJAN
Abstract:	Scrum framework is needed to keep up openness of a project life cycle. If structure ceases to conserve the transparency subsequently it is vital to hunt down the reason behind same. This paper provides the new algorithm that helps you to examine the openness within tasks as per scrum user stories. The core assumption is that, user stories are back bone of work and this can be formulated at preliminary stage of project cycle and the actual performance of stories takes a long time to accomplish. If any of these tasks are time intensive, it is crucial to formulate sub-stories for major task and conduct whole Scrum cycle for same. To address this problem, proposed research focusing on decision goal modeling with scrum tree algorithm where project manager can get automatic goal scheduling effectively as per scrum stories. The evaluation of proposed system is done for real time project and also tested for Thurman dataset. Performance parameters like data centrality
Keywords:	Scrum, Agile, Kanban, Sprint, Sprint Retrospective
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	EXPLORING THE GENERAL AWARENESS OF YOUNG USERS ACCORDING TO AIDA MODEL APPLIED TO SOCIAL NETWORKING ADS
Author:	OSAMA AHMED ABDELKADER, MOHAMED HASSAN RABIE
Abstract:	The information revolution represents an essential feature of the era that the world is currently living in. Social Networking is one of the important elements of this revolution. According to the literature review, previous studies focused on measuring of the model elements depending on specific perceptions toward determined ads. This study presents a contemporary application of AIDA model stages; Attention, Interest, Desire and Action on Social Networking Advertise (SNA), with the impact analysis of gender and SNA-image. This paper reviews the literature need of measuring the general awareness of SN users according to AIDA model applied to SNAs. Additionally, it explores the perceptions of youth who represent the largest sector among SN users, especially universities' students. A proposed questionnaire was contributed as a research instrument, the reliability and validity of the questionnaire were tested by a group of statistical measures included Cronbach's α and Exploratory Factor Analysis (EFA). Data were collected based on snowball sampling. There are 738 participants in this survey; 570 females and 168 males. After data collection, the goodness fit of the proposed model was examined and ensured by seven fit indicates. The main contributions of this study are exploring the general perception of young users about AIDA stages applying on SNA. Moreover, the influences of SNA-image and gender on AIDA stages were tested. These contributions enable marketers and advertisers to predict the effectiveness of their advertising campaigns through social networking sites (SNSs). Findings discussion, limitations of the study and suggested future researches were provided to extend the applicability of its contributions.
Keywords:	Marketing, Social Networking Advertise, AIDA, Forecasting, Ad Effectiveness.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	COMPREHENSIVE ANALYSIS OF SCOPE OF NEGATION FOR SENTIMENT ANALYSIS OVER SOCIAL MEDIA
Author:	NIKHIL KUMAR SINGH, DEEPAK SINGH TOMAR
Abstract:	Handle Negation is essential for effective sentiment analysis decision support system. Negation control comprised identification of negation cues, scope of negation and their influence within it. Negation can either invert, reduce or increase the polarity score. This paper present comprehensive assessment of recent research on negation control for sentiment analysis technique. Explore negation cue and scope detection techniques in collaboration with classification technique over social media data set. This assessment has included the evaluation of sentiment classification (Support vector machine, Navies Bayes, Linear Regression and Random Forest) and scope detection techniques (conjunction Analysis, Punctuation Mark and grammatical dependency tree) over presented prepossessing framework. This paper yield interesting result about collective response of negation scope detection and classification technique for sentiment analysis. Negative scope feature vector significantly increase the polarity classification accuracy of sentiment classification technique. Grammatical dependency tree in collaboration with SVM and Naves Bayes can detect negation with better accuracy as compere to conjunction and punctuation word scope detection technique.
Keywords:	Sentiment Analysis, Negation Cues, Scope Detection, Conjunction Analysis, Punctuation Mark, Grammatical Dependency Tree, Navies Bayes, Linear Regression, Random Forest, SVM.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	OBJECT-BASED IMAGE ANALYSIS APPLIED FOR DIFFERENT STAGES OF RUBBER PLANTATIONS MAPPING USING THAICHOTE SATELLITE DATA
Author:	WASANA PUTKLANG, CHARAT MONGKOLSAWAT, RASAMEE SUWANWERAKAMTORN
Abstract:	During 2000 to 2011, rubber plantations rapidly expanded in northeast Thailand, which had not been historically planted. Information about planted areas and their distribution is a prerequisite for formulating land use planning and understanding its consequences on ecosystems. This study aimed to establish a model for digitally devising a synergistic approach to distinguishing the different stages of rubber plantations in the northeasternmost region of Thailand and a small portion of the Lao People's Democratic Republic (Lao PDR). The combination of Object-Based Image Analysis (OBIA), Vegetation Canopy Density (VCD), plant phenology and intensive ground observation was applied to THAICHOTE satellite data. Two levels of classification based on OBIA approach were performed. At the first level, multi-scale image segmentation of pansharpened imagery was performed to divide the image set into objects with different spectral and spatial characteristics. Incorporating the normalized difference vegetation index (NDVI) and brightness index (BI) into the objects, the image set was subdivided into four different subsets of VCD. Analyses were then performed at the next level classification on each of VCD subsets by using certain and a range of different approaches to discriminate stand age rubber tree plantations. Rubber tree phenology and OBIA feature optimization were used to differentiate the different stages of rubber plantations. The results indicated that the agreement between field-based classification and image-based classification was well correlated. The overall accuracy of 79.00 % and Cohen’s kappa coefficient of 0.77 were achieved for the integrated models for the different stage of rubber plantations.
Keywords:	THAICHOTE satellite data; Different stages of rubber plantations; Object-based image analysis (OBIA); Vegetation canopy density (VCD); Plant phenology; Northeast Thailand
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	EMPIRICAL STUDIES ON THE IMPACT OF SOFTWARE CUSTOMIZATION ON QUALITY ATTRIBUTES: A SYSTEMATIC REVIEW
Author:	ABDULRAZZAQ QASEM ALI , ABU BAKAR MD SULTAN , ABDUL AZIM ABD GHANI , HAZURA ZULZALIL
Abstract:	Software needs to deliver acceptable levels of quality, whilst meeting the functional demands of users. This need is gaining more consideration in Enterprise Resource Planning (ERP) and multi-tenant software. This study investigated the effect of software customization on external quality attributes via four pertinent primary studies, which were summarized, aggregated, discussed and presented through a systematic literature review. The primary studies in this review were chosen through the application of inclusion and exclusion criteria to applicable articles published during the period 2000-2016; they were analysed using research questions that focused on software customization, software quality attributes and measures, approaches, and impact results. The results revealed that each primary study had been applied in the context of ERP and demonstrated that different types of customizations can have various effects on particular quality attributes. Accordingly, further research is needed to determine the impact of customization on each external quality attribute.
Keywords:	Customization; ERP; Software Quality Attributes; Systematic Literature Review.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	ASSOCIATION RULES IMPLEMENTATION FOR AFFINITY ANALYSIS BETWEEN ELEMENTS COMPOSING MULTIMEDIA OBJECTS
Author:	MENDOZA-PALECHOR, FABIO E. , CARRASCAL OVIEDO, DE-LA-HOZ-FRANCO, EMIRO
Abstract:	The multimedia objects are a constantly growing resource in the world wide web, consequently it has generated as a necessity the design of methods and tools that allow to obtain new knowledge from the information analyzed. Association rules are a technique of Data Mining, whose purpose is to search for correlations between elements of a collection of data (data) as support for decision making from the identification and analysis of these correlations. Using algorithms such as: A priori, Frequent Parent Growth, QFP Algorithm, CBA, CMAR, CPAR, among others. On the other hand, multimedia applications today require the processing of unstructured data provided by multimedia objects, which are made up of text, images, audio and videos. For the storage, processing and management of multimedia objects, solutions have been generated that allow efficient search of data of interest to the end user, considering that the semantics of a multimedia object must be expressed by all the elements that composed of. In this article an analysis of the state of the art in relation to the implementation of the Association Rules in the processing of Multimedia objects is made, in addition the analysis of the consulted literature allows to generate questions about the possibility of generating a method of association rules for the analysis of these objects.
Keywords:	Association Rules, Multimedia Object, Data Mining, Data-Set, Correlations.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	ENHANCING ARABIC NAMED ENTITY RECOGNITION USING PARALLEL TECHNIQUES
Author:	ZIADOON A. OTAIWI, MOHAMMED A. OTAIR, KHALDOON A. AOTAIWE, AHMAD ODAT, FERAS ALMASHAKBAH
Abstract:	Named entities recognition systems (Proper Names) are used in the development of many natural language processing applications. There is a paucity of published research in the field of identifying the named entities from texts written in Arabic. This is due to the fact that the Arabic language has a specificity regarding the complexity of spelling and morphology, which is an obstacle to the development of a technique to identify the names of the Arabic entities or the so-called Arabic Named Entity Recognition system (ANER). This paper presented the experiments conducted to identify the appropriate technique to design a robust and reliable system for identifying Arabic entities. For this purpose, this study focuses on the most common state-of-art in the field of identification of Arabic named entities, then a comparison was made between five of the most famous tools that interested in identifying the Arab entities, after that, integrated each of two tools together to get 10 different parallel techniques. The results of the comparison between the tools showed that Rosette achieved the best results followed by Madamira, while it was the worst performance results in the gate tool and for hybrid systems, the R-F (combining Rosette and Farasa) achieved the best performance with better accuracy than individual tools.
Keywords:	Parallel Techniques, Arabic Named Entity, Named Entity Recognition, Tool
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	ANALYSIS USABILITY AND CONTENT IN KNOWN SYSTEM IMPLEMENTATION
Author:	RITAWATI , AHMAD NURUL FAJAR
Abstract:	The purpose of this study is to analysis usability and content of KNOWN system implementation in Bank Syariah Mandiri (BSM). Based on the data, KNOWN system visitor is less than 10 percent on January to April 2017. The author will conduct research to find out whether the employee's user experience in using KNOWN has gone well or not. This study, will focus on 2 factors in user experience, namely usability and content. This study consists of five steps, such as: (1) Questionnaire Preparation, (2) Questionnaire Distribution, (3) Usability Testing, (4) Analyzing and Data Interpretation, and (5) Recommendation. The results of this study are how good the level of usability and content on the KNOWN site and KNOWN recommendations in the future for the company.
Keywords:	Usability, Usability Testing, Knowledge Management System
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	INTERCONNECTED MODERN HIGHER EDUCATION IN INDONESIA BASED ON SOA
Author:	ALDIAN NURCAHYO, AHMAD NURUL FAJAR, SEPTIA REDISA SRIRATNASARI, MOH SUKRON MUFAQIH, SARIFUL BACHTIAR
Abstract:	The adoption of Service Oriented Architecture (SOA) in modern higher education will help to solve the problems of adaptability by reducing integration complexity of new systems, reusing services, interoperability and increasing the agility of learning system. Furthermore, share services and cloud computing solutions could helped modern higher education and universities to create low costs and efficient service management by collaboration and open environment. The creation off interconnected modern higher education ecosystem has become an important way for players in the field of education. This paper is to propose SOA adoption solutions for universities and education institutions by modelling and designing the interconnected modern higher education’s system. The aim is to create a new educational environment where learners have digital course and information accessible easily to support their educational and career goals. On the other hand, the solution is to understand the way universities and education institution solved demands complexity of the digital learning system by reducing investment costs. Moreover, we are purposing new alternatives of the architecture systems that focused on interoperability and cross-platform functionality in order to deal with high level components diversity.
Keywords:	Service Oriented Architecture SOA, Interconnected Modern Higher Education, Universities, E-Learning.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	NOVEL ARCHITECTURE OF CLOUD COMPUTING FOR INTERNET OF THINGS
Author:	CHETNA DABAS
Abstract:	In the years to come, futuristic research and business opportunism will hugely rely on the fusion of two very popular technologies called Cloud Computing and Internet of Things. The victory of Internet of Things seeks for service accessories consisting up of crucial parameters like reliability, scalability, ubiquity, good performance to name a few. This further demands cloud computing to be in place for the concrete support of the Internet of Things paradigm. Cloud Computing is weaved with in-built intellect support for the integration with Internet of Things and on the other hand cloud environment aims at boosting up of the Internet of Things scalability and cost factors in great ways. This research paper presents review of literature, surveyed practices, points out research issues in the above context, and proposes a novel fused architecture of Cloud Computing for the Internet of Things technology, validates the proposed architecture while implementing an application using IOT devices and Google Cloud, compared the proposed work for MQTT protocol with the existing work and performs better than it, further, in another existing work the cloud component was completely missing whereas it is embedded in the proposed architecture for offering scalability in the Internet of Things scenario, at last this research paper concludes with the open research issues and assumptions along with limitations of the proposed work.
Keywords:	Internet of Things, Cloud Computing, Architecture, Applications, Games
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	SEMANTIC INTEGRATION SHARING FOR E-GOVERNMENT DOMAINS ONTOLOGY: DESIGN AND IMPLEMENTATION USING OWL
Author:	ABDULLAH ALSHEHAB1, NASER N. ALAZEMI, HAWAF ABD ALHAKEM
Abstract:	Integrating information system in any domain for E-government is facing several problems, such as structural and semantic sharing in similar information for applications and services. In addition, representation across heterogeneous organizations. In this aspect, the semantic web played a dynamic role in sharing and managing knowledge sharing. Therefore, e-government services need to modeling, re-engineering governmental sharing, and processing to provide information delivery according to the citizen and locations. Semantic Web technology based on the ontology has brought promising solutions to the above engineering problems. This paper is ongoing for previous work presents a framework for generating semantic model ontologies in OWL syntax from a government service domain. However, current works employing OWL ontologies in e-government to the Semantic Web viewer, which implemented semantic sharing integration for e-government domains (Civil information, Health information, Education Information) ontology, which present the case of the State of Kuwait interoperability integration. The domain ontology is created using ontology knowledge-based editor Protégé and OWL-Viz. Thus facilitating to improve the knowledge sharing so that citizens can take more knowledge benefits from the e-government sharing. In addition, the ontology will be useful in the knowledge sharing of semantic e-government integration, and semantic Web applications. Thus facilitating the design of e-government systems that can be easily integrated and maintained. Web Protégé ontology can be easily sharing with a distributed group of users who can engage in collaborative authoring activities from wherever they happen to be logged in.
Keywords:	E-government; Semantic Web; Domain ontology; Services; Framework; owl; Integration; Citizens; Kuwait e-government; OWL-Viz; Protégé
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	BOOTSRAPPING INSTANCE-BASED ONTOLOGY MATCHING VIA UNSUPERVISED GENERATION OF TRAINING SAMPLES
Author:	MANSIR ABUBAKAR, HAZLINA HAMDAN, NORWATI MUSTAPHA, TEH NORANIS MOHD ARIS
Abstract:	Training set is the key role player that can improve the performance of any classification task. Different techniques and methods are being applied to generate training set depending on its area of application. Researchers in data science and semantic web community use different kind of training sets generated to improve the performances of classifications and information retrieval capability. Operational Training Set Generator (TSG) should always solve a minimum of two issues; (1) it must address the computational cost in producing a reasonable outcome, thereby reducing the computational cost in the whole system. The run-time of TSG is near linear as in blocking approach and (2) it must produce the qualitative training sets. We use LogTfIdf as the cosine similarity function of two given vectors to produce Bag of Words (BoW); the tokenizer is developed to specially take care of delimiters that often come across URIs and other RDF essentials. We evaluated our UTSG on nine cross-domain benchmark ontologies publically available in OAEI website. The results obtained shows that our UTSG outperforms the two baseline TSGs previously developed to address similar problem.
Keywords:	Semantic Web, Link Open Data, Semantic Heterogeneity, Ontology Matching, Instance-based Matching, Training Set
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	CLASSIFICATION OF PNEUMONIA PATIENTS RISK USING HYBRID GENETIC ALGORITHM-DISCRIMINANT ANALYSIS AND NAÏVE BAYES
Author:	IRHAMAH, SITI MAR’ATUS RAHIMATIN, HERI KUSWANTO, LAKSMI WULANDARI
Abstract:	Pneumonia is the most common causes of death in developing countries, such as in Indonesia. Therefore, appropriate pneumonia classification is very important in determining the disease severity and to know the most appropriate treatment for the patient. In this study, Discriminant Analysis (DA), hybrid Genetic Algorithm- Discriminant Analysis (HGA-DA) and Naïve Bayes (NB) are used to classify risk class of patient. GA is an artificial intelligent method that can avoid a trap in local optima and easy to implement in solving various objective functions and constraints, while NB is a simple but powerful method that returns not only prediction but also the degree of certainty. In this study, GA is used to improve multi-class classification performance of DA. Firstly, GA is used for variable selection in DA, and then a comparative study with other variable selection methods is performed. In addition, Genetic Algorithm is also implemented for parameter estimation. Analysis results show that there are differences in selected variables from four selection methods in classifying patient risk class. The use of hybrid methods of DA and GA in variable selection and parameter optimization stages gives better multi-class classification results than DA or NB, since it produces highest Geometric Mean (GM) and Area Under Curve (AUC) criterion.
Keywords:	Pneumonia, Multi-class Classification, Discriminant Analysis, Genetic Algorithm, Naïve Bayes
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	MODELING THE STRUCTURE OF SOCIAL NETWORKS BY USING THE PYTHAGOREAN SPIRAL
Author:	IZEM ACIA, WAKRIM MOHAMED, GHADI ABDERRAHIM
Abstract:	Since the good representation of the complex networks structure can effectively communicate more information and can help explore them and understand their behaviors, the purpose of this paper is to present and model the structure of social networks. Mathematical concepts can be a powerful tool for modeling. However, complex networks in the real world are far too complicated to model in their entirety. Therefore, it is important to identify the information that the generated model may help illustrate. In the present work, we use the spiral of Pythagoras and a combination of mathematical concepts in pre-topology, graph theory and fuzzy logic to generate two different models: the Rings Model and the Member-ship Matrix. The first proposed model has a geometric representation which makes all the nodes visible and every direct link between two nodes illustrates the number of, direct and indirect, paths that connect them and the cost of each one. The second proposed model is a matrix where every column depicts the relation between the corresponding node and the rest of the network. The most important benefit of the models presented in this paper is that they allow the human eye to get information about the strength of connection between the nodes, of complex networks, in an easy and fast way.
Keywords:	Spiral of Pythagoras, Pretopology, Fuzzy Logic, Social Networks, Complex Networks, Mathematical Modeling, Matrix, Rings Model
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	RELIABLE LICENSE PLATE RECOGNITION SYSTEM BASED ON ADAPTIVE NON-PLATE FILTRATION METHODS
Author:	LAMA ALKHALED, MUHAMMAD EHSAN RANA
Abstract:	This paper proposes a technique to filter out the false negative detection of license plate caused by using edge algorithm to specifying the targeting areas. The proposed technique implements filters bases on the histogram value for the three main channels of the image (RGB). The paper consists of the following three main stages: (a) Detection based on edge detecting method, (b) calculating the histogram values of RGB color model, and (c) finally, verifying and detecting valid license plate regions by applying different histogram- based rules on features extracted out from the calculated histogram values. Experimental results show that the proposed method is very effective in assisting to neglect many noises caused by different conditions such as poor illumination and varied weather
Keywords:	license Plate Detection (LPD), Histogram Distribution, Detection Accuracy, False Rejection Rate (FRR)
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	RESOURCE ALLOCATION OPTIMIZATION BASED ON CHANNEL QUALITY FOR LONG TERM EVOLUTION SYSTEMS (LTE)
Author:	SARA RIAHI, AZZEDDINE RIAHI
Abstract:	In this paper we focus on an important task of the eNodeB in the architecture of LTE networks, the RRM (Radio Resource Management) its goal is to accept or reject network connection requests, ensuring optimum distribution of radio resources between UEs (Users equipment). It consists mainly of two elements AC (Admission Control) and PS (Packet Scheduling). In this work we will focus on the PS, which achieves an efficient allocation of radio resources in both directions is to say Uplink (considered in our case) and downlink. Several approaches and algorithms have been proposed in the literature to address this need (allocate resources effectively) this diversity and variety of algorithms is related to the factors considered for the optimal management of radio resource, specifically the type of traffic and requested QoS by the EU. In this paper a study of several scheduling algorithms proposed for LTE (uplink and downlink) is made. Therefore, we offer our evaluation and reviews. In this paper we are interested in the allocation of radio resources in LTE uplink (uplink) in particular with a comparative study between the scheduling algorithms flows that are: Round Robin (RR) Max Min Fair (MMF ), Maximum-Largest Weighted Delay First (M-LWDF) and Exponential Proportional Fair (PF EXP).We considered the real-time stream or RT (Video and VoIP), considering the QoS criteria: time, spectral efficiency and throughput. The results obtained show the advantages and disadvantages of using one algorithm over another.
Keywords:	Resource allocation, Uplink, Downlink, LTE, scheduling algorithms.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	POST-EDITING OF WORDS IN KAZAKH SENTENCES FOR INFORMATION RETRIEVAL
Author:	SHORMAKOVA A., ZHUMANOV ZH., RAKHIMOVA D.
Abstract:	In this paper, the proposed method for determining incorrect words for any context is described in more details. Also, the paper describes the completeness of the meaning of words in Kazakh sentences for incorrect words in post-editing. And the second main task is to find the most suitable variant for these words found by the full meaning of the word for any context. According to the results of the study, the relevance and weighty significance for the Kazakh language was shown to determine the full meaning of the word. After the work done, this methodology shows that it is very relevant and effective especially for the Turkic languages. Although the system is aimed to find the wrong words and analyze these words for post-editing, but these modules can be considered as separate modules for working with contexts. The work was also done for information retrieval and for the analysis of the initial input data. In this work, the essence of the work of a search system is indicated which uses the above-said algorithm for the algorithm for searching and processing data.
Keywords:	Completeness Of Word; Kazakh Language; Intelligent Analysis Of Sentences ; Machine Translation; Information Retrieval.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	NEW ALGORITHM IN IMAGE COMPRESSION BASED ON DISCRETE COSINE TRANSFORM
Author:	ZYAD THALJI
Abstract:	Digital image compression is the most important field in digital image processing. Communication technologies and storage are using compression to compressed digital images. Digital image compression provides storage space when storing images on storage media and saving time when transferring data over communication networks. This paper aimed to compress an image by resizing the image dimension, the resizing image based on pixel location. The study used many methods to reach its goals. The method of separating the colour image is used to split the image into three intensity images (red intensity images, blue intensity images and green intensity images). The Discrete Cosine Transform (DCT) is used after the splitting the resizing image, resizing the image dimension reduced the dimension of the image to quarter. The new algorithm was applied for ten selected images from the internet, the experiment results show that the new algorithm has a high efficiency in image compression.
Keywords:	Image Compression, Image Resize, Discrete Cosine Transform, Inverse Discrete Cosine Transform, Colour Image.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	AN ANALYTICAL APPROACH FOR BANKRUPTCY PREDICTION USING BIG DATA AND MACHINE LEARNING TECHNIQUE
Author:	S.SAROJINI DEVI , Dr Y.RADHIKA
Abstract:	Bankruptcy is defined as a legal procedure used to claim the identity of an organization or a person on the basis of their creditworthiness and debtor. There is a huge requirement for effective prediction models to evaluate the risks arising in bankruptcy at early stages and to overcome financial losses. Another critical risk considered in bankruptcy is periodic increase in financial data and updates, which increase the size of the system. The existing tools and techniques are limited to less number of inputs and big data cannot be processed directly with these techniques. Big data analytic technique, such as Hadoop, provides an opportunity to process large financial data, which is retrieved from data source such as DataStream, FAME, Company, and House. In this research, bankruptcy prediction model has been developed by using a combined approach of Big Data and Naive Bayes machine learning algorithm. A huge amount of financial data is extracted and stored in Hadoop database through key pair conversion technique and big data analysis and prediction is carried out using naive Bayes
Keywords:	Big Data Analytics; Bankruptcy; Naive Bayes Algorithm; Financial Models; Datastream; FAME (Forecasting Analysis And Modelling Environment); Industrial Risk; Management Risk; Financial Flexibility; Credibility; Competitiveness; Operational Risk.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text

Title:	DEVELOPING BIG DATA FRAME WORKS FOR EFFICIENT INTELLIGENT TRANSPORT SYSTEM FOR SAFETY AND SECURITY
Author:	P. KIRAN KUMAR , A. VIJAY GOPAL
Abstract:	Big data is an advanced technology where we can use its services for our application. Big data handles large volumes of data upon a sudden rise and request of the users. Transportation system is one where we have to handle big data. Based on the gathered data the decision has to be taken for safer measures and efficient, profitable and secured. In this paper we conducted a survey on big data in ITS (Intelligent Transportation System). Data collection, analytics and frame works can be explained. We concluded from our survey by using big data we will resolve our traditional traffic problems. We attempted to provide architecture for ITS using big data thencalculation of bayonet traffic flow, calculation ofaverage speed of a road, querying the travel path of a vehicle, checking and controlling the fake vehicles.
Keywords:	ITS, big data, vehicle tracking, Large Data Storage, Cloud Computing.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2019 -- Vol. 97. No. 06 -- 2019
Full Text