		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
July 2020 | Vol. 98 No.14

Title:	DEEP HYBRID FEATURES FOR CODE SMELLS DETECTION
Author:	ABEER HAMDY, MOSTAFA TAZY
Abstract:	Code smells are symptoms of poor software design and implementation choices. Previous empirical studies have underlined their negative effect on software comprehension, fault-proneness and maintainability. A number of approaches have been proposed to identify the existence of code smells in the source code; recent studies have shown the potential of machine learning models in this context. However, previous approaches did not exploit the lexical and syntactical features of the source code; they instead modelled the source code using software metrics only. This paper proposes an approach for detecting the occurrence of the God class smell which utilizes both, the source code textual features and metrics to train three deep learning networks (i) Long short term memory, (ii) Gated recurrent unit and (iii) Convolutional neural network. We proposed utilizing deep leaning networks as they are reported to outperform traditional machine learning models in several domains including software engineering. To assess the proposed approach, a dataset for the God class smell was built using source codes acquired from the Ã¢â‚¬Å“Qualitas CorpusÃ¢â‚¬Â. Experimental results demonstrated that, the three deep learning networks outperformed three traditional machine learning models: NaÃƒÂ¯ve Bayes, Random forests and Decision trees. Additionally, of the three deep learning networks the Gated recurrent unit model is the superior in this context. Furthermore, combining both, the source code metrics and textual features enhanced the accuracy of detecting the God class smell.
Keywords:	Code Smells, Deep Learning, God Class, Software Maintenance, CNN, LSTM, GRU, VSM, IR, Text Mining
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	MEASURING SUCCESS OF ACCOUNTING INFORMATION SYSTEM: APPLYING THE DELONE AND MCLEAN MODEL AT THE ORGANIZATIONAL LEVEL
Author:	AWS AL-OKAILY, MOHD SHAARI ABD RAHMAN, MANAF AL-OKAILY, WAN NUR SYAHIDA WAN ISMAIL, AZWADI ALI
Abstract:	As Information Technology (IT) grows more advanced and competitive pressures for innovation increase, customary ways of providing stakeholders with information have become insufficient for decision needs. Organizations today need a successful Accounting Information System (AIS) that helps them achieve strategic and business objectives. Therefore, the objective of this research was to examine the possible effect of AIS success factors comprised of system quality, information quality and service quality on organizational impact with special reference to the listed Jordanian firms. To that end, our research model has been built upon the DeLone and McLean (D&M) model as a theoretical basis to measure AIS success. A total of 192 questionnaires were distributed to 192 firms listed in the Amman Stock Exchange (ASE) until the end of 2019, out of which 117 answers were valid for further analysis. The research findings showed that system quality, information quality and service quality success have an effect and strong relevance in AIS success at the organizational level. These findings confirmed the validity of the D&M model at the organizational level in the specific context of AIS as a mandatory system. Eventually, it can be inferred from our findings that Jordanian firms can improve their performance and realize organizational benefits by the quality of system, information and service.
Keywords:	Accounting Information System, Amman Stock Exchange, DeLone and McLean Model, Organizational Level.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	IMPROVEMENT OF IT OPERATION PERFORMANCE USING SYNERGY OF ITIL PROCESS IN RETAIL ORGANIZATION
Author:	JOKO ALAM, BENFANO SOEWITO
Abstract:	The increasing number of IT incident create issue to organization. Controlling the number of IT incident using ITIL framework is one of the success factor for organization in order to achieve its goals [18]. In the retail organization, the basic implementation of ITIL sometimes cannot fulfil the business requirement. It is requiring process improvement to get successful result to decrease or control number incidents. In this research, we have created new process that able to make synergy of Incident management and problem management process on ITIL version 4. The outcome of this research is to implement the new process to synergy the incident management and problem management in practices that will solve the IT support issues on retail organization.
Keywords:	ITIL, Retail, Incidents Managements, Problem Managements, Synergy, Process
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	AN ONTOLOGY-BASED SEMANTIC EXTRACTION APPROACH FROM TEXT CORPUS
Author:	KITTIPHONG SENGLOILUEAN, NGAMNIJ ARCH-INT, SOMJIT ARCH-INT
Abstract:	The Semantic Web is the salient technology of knowledge management, consisting of data extraction and annotation processes, which requires semantic representation to express data in an ontological format. The ontological extraction of unstructured data to enable the automatic generation of concepts and relations has led us to the presentation of our unique approach of automatic ontology extraction. However, domain experts are still required to modify the structure of ontological results, which makes the process very time-consuming and costly. Yet, there still exists the need for an ontology-based semantic extraction approach from text corpus to discover concepts, instances, and semantic relations between concepts or instances. This paper presents an approach of an ontology-based semantic extraction and the accompanying semantic extraction rules, as applied to tourism domain. The proposed semantic extraction rules are defined as extension rules working with GATE API. As a result, the efficiency of the proposed ontological extraction approach is validated through the Precision, Recall and F-measure scores, with average values of 91.48%, 89.12%, and 90.23%, respectively.
Keywords:	Ontology Extraction, Semantic Extraction Rules, Unstructured Data
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	IDENTIFYING FACTORS OF USER SATISFACTION WITH SUMMATIVE E-ASSESSMENT: A QUALITATIVE APPROACH
Author:	HASSAN BELLO, NOR ATHIYAH ABDULLAH
Abstract:	In Nigeria, candidates for electronic examinations have expressed negative opinions about the system resulting from fear or unfamiliarity with the assessment technology, and a lack of knowledge about the methods of e-assessments. This paper aims to investigate the factors determining user satisfaction with a summative e-assessment system in Nigeria from the examinees' point of view, and to address the challenges and problems faced during the e-assessment. Therefore, the research adopts a qualitative approach (by interview) to provide a further understanding of the main factors which affect user satisfaction with e-assessment. Secondly, to map those identified issues with a corresponding objective and subjective aspects of satisfaction. As a result, this could set the stage right for future studies on resolving issues and enhancing the e-assessment satisfaction. This study showed that the satisfaction of examinees with e-assessment would be influence by service quality, system quality, and user's computer experience. In contrast, information quality was found to be an insignificant determinant of user satisfaction with summative e-assessment. Past studies mostly address the relationship between these factors and user satisfaction quantitatively. This study reveals that Information System Success Model is the most suited underlying theory that could fit the case of e-assessment satisfaction.
Keywords:	Summative E-Assessment, User Satisfaction, Service Quality, System Quality, Computer Experience
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	KAZAKH HANDWRITTEN RECOGNITION
Author:	BEIBUT AMIRGALIYEV, ARMAN YELEUSSINOV, MIYACHI TAIZO
Abstract:	Recognition of handwritten texts in different languages has recently attracted great interest among researchers in connection with the development of various algorithms for machine learning, deep learning and computer vision. This paper proposes a labeling approach for collecting dataset for handwritten Kazakh text recognition (HKTR). We consider the stages of creating a handwritten database for the Kazakh language and preparing a training sample for training a neural network. The results of applying widely used machine learning algorithms for recognizing offline handwritten texts are presented. We evaluate the performance of the proposed method on the test sets from our Kazakh handwritten dataset and Russian handwritten dataset, and achieve performance with correct rate 85.63.
Keywords:	Handwriting rRecognition, Deep Learning, SVM, CNN.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	AN ADAPTIVE MORPHOLOGICAL FILTER FOR MOVING OBJECT SEGMENTATION
Author:	MUHAMMAD HAMEED SIDDIQI, MADALLAH ALRUWAILI, M. M. KAMRUZZAMAN, SAAD ALANAZI, SAID ELAIWAT, FAYADH ALENEZI
Abstract:	This work presents a system that combined well-known morphological filters in order to find true moving regions from a sequence of images. For localizing the changed region, a block-based change segmentation process is proposed. This change region is naturally a coarse region and also contains some holes. To compensate this, we used an edge-based dilation to get an anisotropic expansion of the coarse image. Then the segmentation is generated using watershed algorithm. To prevent over segmentation, we used a specially weighted gradient image to achieve segmentation. Also, we removed some local minima from that gradient image. Finally, a fusion is applied on morphological filters. Furthermore, we calculated the coverage ratio of edge pixels of each segmented region. Comparing with a converge threshold, we determined whether the segmented region is truly belongs to a moving region or not. In the end, the experimental result demonstrated the validity of our proposed method.
Keywords:	Moving Objects, Morphological Filter, Erosion, Dilation, Edge Detection, Watershed Segmentation
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	THE ANTECEDENT OF USER MOTIVATION TO USE COMMENT FEATURE IN INDONESIA ONLINE NEWS PORTAL
Author:	INDRA BUDI, PINTO LUHUR KARSANDA, FATIMAH AZZAHRO
Abstract:	The era of internet and mobile phones have changed business models in many industries, including news and media in Indonesia. Media companies are forced to shift their business model from selling offline newspaper to digitalizing their services. As a key to surviving in online media industry, many companies obsess with improving the level of user engagement. Providing comment feature in the news portal is one of possible ways to achieve better user engagement. However, the motivation that may drive users to use the comment feature is rather under research, especially in Indonesia. Thus, the purpose of the research is to determine antecedents of usersÃ¢â‚¬â„¢ intention to use comment feature on the online news portal. Using data collected from 334 respondents, we find that agreeableness, entertainment, impact, narcissism, and public opinion significantly influence user intention to use comment feature in online news portal.
Keywords:	Online News, User Motivation Factors, User Comments, User Engagement, Indonesia
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	THE USE OF INTELLIGENT SYSTEMS AND INNOVATION TO MODEL AND OPTIMIZE FUSED DEPOSITION MODELING PROCESS PARAMETERS FOR TIME MANUFACTURING AND MATERIAL CONSUMPTION
Author:	H. ISKSIOUI, S. ENNIMA , S. BOUREKKADI, M. OUBREK, A. ELGHARAD
Abstract:	Additive manufacturing processes, especially the FDM process (Fused Deposition Modeling), are used for prototyping or manufacturing complex geometries. The ease of using 3D scanners and printers made FDM process a must have in every tech-house or laboratory. To optimize it, the prototyping cost, the manufacturing time and the material consumption must be reduced. Thus, the process parameters that intervene in the quantity of material and the manufacturing time (platform and extruder temperature, layer thickness, number of shells and solid layers, infill pattern and density, print speed) have been analyzed. An experimental study using a statistical analysis and an optimal experimental plan Design-optimal have been made. In addition, a mathematical model adapted to the experimental results has been designed. The RSM (response surface method) has been used to optimize the model response and find the most suitable set of process parameters. Those inputs have been validated with the developed mathematical model.
Keywords:	Additive Manufacturing; Fused Deposition Modeling; Parameters Optimization; Response Surface Method
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	AN EFFICIENT TRAFFIC STATE ESTIMATION MODEL BASED ON FUZZY C-MEAN CLUSTERING AND MDL USING FCD
Author:	FATEMEH AHANIN, NORWATI MUSTAPHA, NASIR BIN SULAIMAN, MASLINA ZOLKEPLI
Abstract:	Monitoring and estimating of large-scale traffic have major role in traffic congestion reduction. Floating Car Data (FCD) is one of the best methods for collecting traffic data due to its versatility and cost efficiency. However, FCD suffers from data sparseness and many researches have been done to improve traffic estimation accuracy with respect to data sparsity. In this paper, a new model based on Fuzzy C-Mean (FCM) clustering and Minimum Description Length (MDL) is proposed to estimate the missing traffic state using FCD. First the Fuzzy clustering is implemented to cluster the road segments based on similarity of their speed at each time slot. Then the MDL principle is applied to estimate the missing traffic state. The experimentation results show that the proposed model can estimate the missing data more accurately than the HMM-based model using the same dataset.
Keywords:	Traffic State Estimation, Fuzzy c-mean Clustering, Pattern Mining, Minimum Description Length, FCD
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	INNOVATION AND INTELLIGENT SYSTEMS IN MODELING AND OPTIMIZING FUSED DEPOSITION MODELING PROCESS PARAMETERS FOR DIMENSIONAL ACCURACY USING SURFACE RESPONSE METHODOLOGY
Author:	H. ISKSIOUI, S. ENNIMA, A. ELGHARAD, M. OUBREK, S. BOUREKKADI
Abstract:	Fused Deposition Modeling (FDM) is a 3D printing process (additive manufacturing) that is widely used around the world in a variety of industrial applications due to its ability to create complex 3D parts and geometries. The accuracy of parts printed by FDM technology is greatly influenced by various process parameters which are often difficult to determine. Increasing dimensional accuracy is the major concern of most industrial applications and affects the cost and functionality of the fabricated part. One of the key issues of the FDM process is how to select the right parameter to reduce the dimensional errors.This study offers an optimality criterion to optimize FDM parameters in order to go over the limits of the traditional designs previously used. The influence of the FDM parameters is studied using the D-optimal surface response methodology. Their effects on dimensional accuracy are studied critically. Mathematical model has been formulated to develop a functional non-linear relationship between process parameters and dimensional accuracy. Ultimately, the optimal setting of the process parameters has been determined and the results show that the optimality criterion is a very promising technique to optimize the FDM process parameters.
Keywords:	Additive Manufacturing; Fused Deposition Modeling; Parameters Optimization; Response Surface Method; Dimensional Accuracy
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	AN ONTOLOGY-BASED PROFILING METHOD FOR ACCURATE WEB PERSONALIZATION SYSTEMS
Author:	ANAS EL-ANSARI, ABDERRAHIM BENI-HSSANE, MOSTAFA SAADI
Abstract:	In recent years, the huge development in information technology led to a data explosion on the web, motivating the need for powerful and efficient strategies for information retrieval. Personalized Web systems are an example used to enhance the user experience by offering tailor-made services according to his profile. Building accurate profiles representing the reel user's interests that can change in time is the major ingredient for an efficient personalization system. This work presents our approach for generating accurate and dynamic user profiles implicitly by tracking and capturing the user's interests and preferences. Moreover, we investigate techniques to improve the profiles' accuracy; through accumulating more browsing data from multiple sources, distinguishing the most relevant concepts, and also identifying the number of ontology levels in the conceptsÃ¢â‚¬â„¢ hierarchy needed to accurately represent each user's reel interests and preferences. Exploiting users' feedback, results prove feasibility and accuracy of the generated profiles.
Keywords:	Web personalization system, User profile, accuracy, Ontology.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	DISTANCE LEARNING POLICY IN INDONESIA FOR FACING PANDEMIC COVID-19: SCHOOL REACTION AND LESSON PLANS
Author:	JANU ARLINWIBOWO, HERI RETNAWATI, BADRUN KARTOWAGIRAN, GULZHAINA K. KASSYMOVA
Abstract:	The uncontrolled outbreak of the SARS-CoV2 novel coronavirus makes all countries confused. One of the impacts is the education sector so learning must be carried out online. This study aims to know the response of schools related to the COVID-19 emergency policy and preparation of learning conducted by teachers. This research is qualitative research with a phenomenological approach to defining school responses and teacher preparation for distance learning during the COVID-19 pandemic. The informants of this study were 49 high school teachers. The base of data collection is online using the Office Form and followed up with a private message to deepen the information. The stages of data analysis are to do data reduction, determine themes, explore engagement between themes, and make conclusions. The study conclusion is schools quickly adhere to government policies to implement distance learning. However, the follow-up at each school varied greatly. Each school interprets the government circular and adapts it to the situation of the school. Second, the teacher modified the existing learning design by considering local conditions and students' needs. Modifications to the design of learning were very varied because the needs of students and the character of the material were very versatile. The most difficult challenge was producing learning media and making fair assessment plans. The teachers were obstacles in making media because of the limited ability of IT and difficulty planning the assessment because they feel unable to see student activities carefully.
Keywords:	COVID-19, Distance Learning, Education, Lesson Plan, School Reaction
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	MULTI-OBJECTIVE OPTIMIZATION ALGORITHMS FOR WIRELESS SENSOR NETWORKS: A COMPREHENSIVE SURVEY
Author:	MAHMOUD MOSHREF, RIZIK AL-SAYYED, SALEH AL-SHARAEH
Abstract:	In recent years, wireless sensor networks (WSNs) topics took advantages as it integrated in internet of things (IoT) applications, there are massive acceleration in using WSNs in monitoring, and tracing applications indoor, and outdoor, such as disaster managing, wildlife tracking, home, health, military, and industry monitoring. Several researchers worked on improving or optimizing one objective, to optimize (reduce) WSNs energy consumption, increase network coverage, or reliability. Since 2004, some researchers have optimized multiple parameters using multi-objective optimization algorithms such as evolutionary algorithms and particle swarm algorithm, some tend to reduce multi-objectives to single one by using weighted sum methods, others tend to make a tradeoff between multi-objectives and give number of solutions so that the decision maker can take a proper decision. In this comprehensive survey, we reviewed most of the researches that addressed multi-objective optimization methods for WSNs during the years 2004 to 2019. Some of these researches use existing algorithms to solve multi-objective optimization problem; others proposed new methods or modified existing algorithms, either with Quality of Service (QoS) or without QoS considerations. In addition, we analyzed these papers to extract the robust and weak points from them. Next, we analyzed the problems that these researches tried to solve, the multi-objectives that optimized, the technical tasks, the mechanisms, and algorithm that these research papers used. Our focus in this survey is to help the researchers finding the available approaches in order to motivate future researches go further.
Keywords:	Wireless Sensor Network, Multi-objective, Optimization Algorithms, QoS.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text

Title:	CONTROL OF AN AUTONOMOUS PV SYSTEM USING THE BACKSTEPPING MPPT CONTROLLER UNDER REAL CLIMATIC CONDITIONS IN NORTHERN MOROCCO
Author:	HANANE YATIMI, YOUNESS OUBERRI, RIM MARAH, ELHASSAN AROUDAM
Abstract:	Maximum power point tracking (MPPT) methods are widely used with PV solar systems to maximize power extraction under variants whether conditions. On another hand the system stability around the maximum power point depends on the robustness of the used method for better load charging conditions. This paper presents a non-linear backstepping controller, based on the Lyapunov function, and applied to an autonomous PV system as a MPPT controller, to extract its maximum power, under simultaneous changes in solar radiation and temperature. A DC-DC boost converter is used as a bridge between the PV module and the load. To validate the robustness of the proposed backstepping controller, the system outcomes under variant meteorological conditions using both the backstepping controller and the well-known incremental conductance method are compared. The results based on analyzing and interpreting the power, voltage and current curves and system behavior, reveal that by using the backstepping controller, the asymptotic stability of the system is smoothly guaranteed with practically no oscillation around the maximum power point and far exceeds the incremental conductance performance in terms of speed and accuracy.
Keywords:	Photovoltaic (PV), Maximum Power Point Tracking (MPPT), Boost Converter, Backstepping Controller (BSC), Recursive Structure
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2020 -- Vol. 98. No. 14 -- 2020
Full Text