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

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

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

Journal of Theoretical and Applied Information Technology
May 2020 | Vol. 98 No.09

Title:	TEXT-INDEPENDENT CHINESE WRITER IDENTIFICATION USING HYBRID SLT-LBP FEATURE
Author:	GLORIA JENIS TAN, ROSELY KUMOI, MOHD SHAFRY MOHD RAHIM, TAN CHI WEE, GHAZALI SULONG
Abstract:	This study proposes a new hybrid method using texture features of input handwriting document image as global to overcome the limitation of data heterogeneity, which causing the ambiguity and leads to inconsistent results apart from problems of scale involve database size. The method first adopts Slantlet Transform (SLT) to bring out hidden texture details prior to feature extractions. Then, Local Binary Pattern (LBP) descriptor is applied on the SLT image to extract texture features. A new hybrid method Slantlet Transform based Local Binary Pattern (SLT-LBP), are experimented on an open and widely used HIT-MW Chinese database for performance evaluation. This study strengthens the idea that to unravel some of data heterogeneity and lead to improve identification performance, especially searching for relevant document from large complex repositories is an essential issue.
Keywords:	Chinese Handwriting, Local Binary Pattern, Slantlet Transform, Text-independent, Texture, Writer Identification
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	FACTOR ANALYSIS OF PT. GOJEK INDONESIA IN SOCIAL CRM THROUGH SOCIAL MEDIA
Author:	FEONI YULIA, TIARA PUTRI ANANDA, NILO LEGOWO, EMIL ROBERT KABURUAN
Abstract:	The current business orientation has changed from product-oriented, to customer-oriented. Customers are very active in assessing various businesses that exist through various ways, including through social media. Seeing this phenomenon many companies have begun using social media to reach their customers. A connection with customers through social media must be supported by Social CRM. Social CRM is a business strategy to engage customers through social media by building their trust and loyalty. There is one company in Indonesia that is good in the application of CRM, namely PT. Gojek Indonesia. Gojek is a startup company which became the first startup in Indonesia that holds decacorn status. Gojek has made Twitter as a platform for social CRM. Application of social CRM is not that easy. Customers will be free to criticize and vent their emotions through social media. In this case, writers are interesting to find out the factors that are the strength of Gojek in carrying out Social CRM activities through social media Twitter. This research uses factor analysis techniques. The population used in this study are @GojekIndonesiaâ€™s Twitter followers. The results showed that there are 2 new components that make up social CRM at PT. Gojek Indonesia. The first factor is the "customer hearing" which represents the factors of listening, embracing, greetings and responses. The second factor is "Serving Customer" which represents supporting, energizing and talking factors. Based on the loading factors, the main strength of PT. Gojek Indonesia in applying social CRM, is "Greetings". This shows that PT. Gojek Indonesia gives good Greetings to customers to make customers comfortable in communicating through social media. Then the other main strength of PT. Gojek Indonesia is "Supporting". This shows that PT. Gojek Indonesia routinely provides services to customers through social media so that they can be good in social CRM.
Keywords:	Social CRM, Customer Relationship Management, Factor Analysis, Twitter
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	EMPIRICAL STUDY AND ENHANCEMENT ON DEEP TRANSFER LEARNING FOR SKIN LESIONS DETECTION
Author:	NOUR ELDEEN M. KHALIFA, MOHAMED LOEY, AHMED A. MAWGOUD, MOHAMED HAMED N. TAHA
Abstract:	Skin cancer is the most common type of cancer. One in every three cancers diagnosed is a skin cancer according to skin cancer foundation statistics globally. The early detection of this type of cancer would help in raising the opportunities of curing it. The advances in computer algorithms such as deep learning would help doctors to detect and diagnose skin cancer automatically in early stages. This paper introduces an empirical study and enhancement on deep transfer learning for skin lesions detection. The study selects different pre-trained deep convolutional neural network models such as resnet18, squeezenet, google net, vgg16, and vgg19 to be applied into two different datasets. The datasets are MODE-NODE and ISIC skin lesion datasets. Data augmentation techniques have been adopted in this study to enlarge the total number of images in the datasets to be 5 times larger than the original datasets. The adopted augmentation techniques make the DCNN models more robust and prevent overfitting. Moreover, seven accredited performance matrices in deep learning have been used to conclude an optimal selection of the most appropriate DCNN model that fits the nature of the skin lesions datasets. The study concludes that vgg19 is the most appropriate DCNN according to testing accuracy measurement and achieved 98.8%. The seven performance matrices strengthen this result. Also, a comparative result was introduced with related works. The vgg19 overcomes the related work in terms of testing accuracy and the performance matrices on both datasets. Finally, the vgg19 model was trained on a smaller number of images than the related work by 10 times, which proved that the choice of data aug-mentation techniques played an important role in achieving better results. That would reflect on reducing the training time, memory consumption and the calculation complexity.
Keywords:	Cancer, Skin Cancer, Melanoma, Deep Transfer Learning, Convolutional Neural Network.
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	CULTURE AND DIGITAL DIVIDE INFLUENCE ON E-GOVERNMENT SUCCESS OF DEVELOPING COUNTRIES: A LITERATURE REVIEW
Author:	KINN ABASS BAKON, NUR FAZIDAH ELIAS, GHASSAN A. O. ABUSAMHADANA
Abstract:	Developing countries invest heavily in e-government systems mainly to deliver prompt and better service to citizens, engage them in decision-making processes, enhance transparency and accountability of institutions towards policymaking, and to minimise the prospects of corruption. Despite widespread enthusiasm and progress in e-government development in developing countries, their implementations are not as successful as their counterpart in developed economies. In an extant study, a mere 15% of e-government systems were found to be successful in developing countries. In the latest United Nations (2018) E-government Development Index (EGDI) data, the average EGDI of African countries in the survey is 0.3423 whereas the EGDI average of European countries is 0.7727. In spite of this huge gap, factors impeding the successful implementation of e-government in developing countries are greatly misunderstood as empirical studies of e-government success in developing countries are very difficult to find. Without empirical evidence, the digital divide and cultural factors are perceived to influence the e-government success in developing countries. This paper gives an overview of the available research on the digital divide, culture, and e-government success. A literature review was conducted covering empirical studies on the digital divide, culture, and e-government success. Result shows that (1) empirical studies of e-government success in developing countries are rare; (2) most research on digital divide were conducted in developed countries and focused on ICT access, instead of multi-dimensional approach; (3) studies that investigate different dimensions of the digital divide influence on e-government successes in particular are almost non-existent; (4) in IS culture studies, the impact of cultural dimensions on e-government success in particular is missing; and (5) the study of individual level cultural dimensions influence on e-government success receives little attention from researchers. This review calls on research attention to the influence of culture and the digital divide on e-government success. The major gaps identified could offer researchers the potential directions for further research.
Keywords:	Countries Individual-Level of Culture, Developing, E-Government Success, IS & Culture Digital Divide
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	ASSESSMENT OF CREDIT LOSSES BASED ON ARIMA-WAVELET METHOD
Author:	JAMIL J. JABER, NORISZURA ISMAIL, SITINORAFIDAHMOHD RAMLI, S. AL WADI, DALILA. BOUGHACI
Abstract:	The aim of this paper is to estimate and forecast the loss-given defaults (LGD) using a sample data of credit portfolio loan collected from a bank in Jordan for the period up from January 2010 to December 2014. We use a wavelet-inspired analysis to convert the original observations into a time-scale domain. Then, we combine the wavelettransform with the ARIMA (Auto-Regressive Integrated Moving Average) model to get an ARIMA-WT new model to forecast the LGD data time series.We evaluate four wavelet functions, which are Haar (Haar), Daubechies (d4), least Asymmetric (La8), and Coiflet (C6). The numerical results show that the ARIMA-WT is more accurate than the pure ARIMA and the other considered ARIMA-Wavelet transform based models. We consider several metrics (MAPE, MASE, RMSE, AIC, AICs and BIC) to measure the performance of our proposed model. The combination between ARIMA-WT and La8 function improves highly the forecasting accuracy. According to our findings, we can say that the resulting forecast model is able to produce a high quality result.
Keywords:	CREDIT RISK, LGD, WT, ARIMA, FORECASTING.
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	REAL-TIME APPROACH FOR ACCURATE PEDESTRIAN LOCALIZATION IN CROWDED SCENES
Author:	HOANH NGUYEN
Abstract:	Detection of pedestrians in a crowded scene is a difficult problem since pedestrians usually gather and occlude each other. In addition, due to the complexity of crowded scenes, current deep learning-based approaches for pedestrian detection still require high computational cost. This paper addresses above problems by introducing a deep learning-based approach for fast and accurate pedestrian detection in a crowded scene. To reduce computational cost and increase inference speed, a reduced ShuffleNet network based on ShuffleNet architecture is first adopted as the base network to generate the base convolution layers. ShuffleNet architecture is built on ShuffleNet units and Strided ShuffleNet units, which include pointwise group convolution layers and channel shuffle operations to greatly reduce computation cost while maintaining detection accuracy. To solve the issue of highly overlapped pedestrian in crowded scenes, an improved non-maximum suppression algorithm is developed based on density score map generated by density prediction sub-network. The improved non-maximum suppression algorithm proposes a dynamic suppression strategy, where the threshold value for suppression rises as pedestrian instances gather and occlude each other and decays when pedestrian instances appear separately. Experimental results on CityPersons dataset and CrowdHuman dataset show the effectiveness of the proposed approach on pedestrian detection in crowded scenes.
Keywords:	Pedestrian Detection, Deep Learning, Non-Maximum Suppression, ShuffleNet Network, Channel Shuffle
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	A SINGLE-STAGE PEDESTRIAN DETECTOR BASED ON SSD WITH MULTI-SCALE FEATURE EXTRACTION AND RESIDUAL BLOCK
Author:	HOANH NGUYEN
Abstract:	Pedestrian detection is a key problem in many intelligent transport systems. In driving environment, apart from the detection accuracy, the inference speed is also a large concern. Although popular two-stage object detectors such as Faster R-CNN have achieved significant improvements in pedestrian detection accuracy, it is still slow for real-time pedestrian detection in driving environment. On the other hand, popular one-stage object detectors such as SSD have not achieved competitive detection accuracy on pedestrian detection benchmarks. This paper proposes a one-stage detector for real-time pedestrian detection in driving environment. The proposed approach is based on popular SSD framework. To improve the detection accuracy, the backbone network in original SSD framework is replaced by the backbone sub-network based on DenseNets structure, which includes stem module, dense blocks, and transition layers. With dense connection in DenseNet architecture, the proposed approach can achieve higher accuracy with fewer parameters compared with ResNet architecture. In the detection sub-network, enhanced feature extraction subnet takes convolution layers generated by the backbone sub-network to generate enhanced feature maps by fusing operation, atrous convolution and deconvolution operation. Enhanced feature maps can enhance the detection performance of multi-scale pedestrian detection. In addition, residual blocks are added before each prediction layer to reduce the computational cost and improve the detection accuracy. Experimental results on Caltech and CityPersons dataset show that the proposed approach achieves better accuracy compared with popular two-stage detectors while being faster.
Keywords:	Single-Stage Detector, Two-Stage Detector, Pedestrian Detection, Deep Learning, Feature Extraction
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	ANALYZING INFORMATION SYSTEM NEEDS IN IMPLEMENTING INTERNAL QUALITY ASSURANCE SYSTEM: A STUDY ON HIGHER VOCATIONAL EDUCATION IN WEST SUMATERA, INDONESIA
Author:	YULHERNIWATI, JALIUS JAMA, GANEFRI, AIDIL IKHSAN
Abstract:	The increasing demand of qualified skilled labor encouraged Indonesian government to improve the number and quality of vocational education in Higher Education Institutions (HEIs), in the form of diploma study programmes. However, the overall qualities of diploma study programs are still low, even though quality assurance (QA) system has been an imperative to all HEIs. It can be seen from 1) the number of accredited diploma study programs with â€œAâ€ marks which is small (only 5.67%, nationally; and 3.85% within West Sumatera Province) and 2) the accreditation marks have not continually improved year to year as expected. Several studies about QA in Indonesia show that Internal Quality Assurance System (IQAS) has not been implemented properly by most of HEIs. Some other literatures encouraged IS utilization to support IQAS implementation, but have not indentified the specific requirement of IQAS information system (IQAS-IS) for proper IQAS implementation. This study aimed to perform information system needs analysis in IQAS implementation and IQAS-IS requirement specification. Surveys and interviews were conducted to collect data about the problems in implementing IQAS, and the solutions purposed by respondents. Then, the data analysis is conducted using fault tree analysis followed by five whys technique. From this study, it is concluded that the root causes of the IQAS improper implementation are 1) lack of leaderâ€™s commitment; and 2) lack of well designed information systems. Those two factors should be developed simultaneously. This study gives contribution in IT research by identifying needs for IQAS-IS, and its requirement specifications, they are namely: supporting IQAS implementation as an integrated process management (a continous full cycle of processes that consist of IQAS planning, implementing, evaluating, controlling and improving), enabling interoperability between different system, and facilitating real time data processing and information retrieval. Thus, by proper IQAS implementation hopefully HEIâ€™s will gain quality improvements.
Keywords:	Needs Analysis, Internal Quality Assurance System, Information System, Higher Vocational Education, Interoperability, Integrated Process Management, Automated Data Collecting, Real Time Data Processing
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	DETECTION AND ELIMINATION OF DISCREPANCIES IN BIG DATA AT TRANSPORT APPLYING STATISTICAL METHODS
Author:	AZAT TASHEV , JANNA KUANDYKOVA , DINARA KASSYMOVA, AINUR AKHMEDIYAROVA
Abstract:	An article herein considers the problems of discrepancies detection and elimination upon processing the big data at transport. Tasks of detecting and eliminating the discrepancies in the data has been solved by means of Grabbs method. To obtain trip time design characteristics values there have been applied statistical methods, which allow correct their prescheduled values. The given methodology is used the big data processing at transport in real time mode.
Keywords:	Smart Transport System, Discrepancies, Big Data
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	A HYBRID WORD EMBEDDING MODEL BASED ON ADMIXTURE OF POISSON-GAMMA LATENT DIRICHLET ALLOCATION MODEL AND DISTRIBUTED WORD-DOCUMENT-TOPIC REPRESENTATION
Author:	IBRAHIM BAKARI BALA, MOHD ZAINURI SARINGAT, AIDA MUSTAPHA
Abstract:	This paper proposes a hybrid Poisson-Gamma Latent Dirichlet Allocation (PGLDA) model designed for modelling word dependencies to accommodate the semantic representation of words. The new model simultaneously overcomes the shortcomings of complexity by using LDA as the baseline model as well as adequately capturing the words contextual correlation. The Poisson document length distribution was replaced with the admixture of Poisson-Gamma for words correlation modelling when there is a hub word that connects words and topics. Furthermore, the distributed representation of documents (Doc2Vec) and topics (Topic2Vec) vectors are then averaged to form new vectors of words representation to be combined with topics with largest likelihood from PGLDA. Model estimation was achieved by combining the Laplacian approximation of log-likelihood for PGLDA and Feed-Forward Neural Network (FFN) approaches of Doc2Vec and Topic2Vec. The proposed hybrid method was evaluated for precision, recall, and F1 score based on 20 Newsgroups and AGâ€™s News datasets. Comparative analysis of F1 score showed that the proposed hybrid model outperformed other methods.
Keywords:	Poisson-Gamma Distribution, Topic Model, LDA, Word2vec, Doc2vec, Topic2Vec
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	AN IMPROVED MACHINE LEARNING-BASED APPROACH FOR PREDICTING TRAVELERS MODE CHOICE IN MOROCCO
Author:	MOHAMED EL HADRAOUI, FOUZIA GHAITI
Abstract:	Predicting the travel mode choice is an important task of transportation planning and policy making to understand inter-urban mobility. It enables the enhancement of the third step of the widely used four-step model. While advances in machine learning have led to numerous powerful predictive models, their usefulness for modeling travel mode choice remains none widely explored. The aim of this paper is to fill in this gap by proposing an advanced machine learning approach tailored to this problem. That is, using extensive Moroccan travel diary data in the year 2016, enriched with numerous individual and household features, our contribution consists of investigating the importance of applying the feature selection approach while using support vector machines (SVM) as a predictive model. The experimental results show that the adopted approach outperforms both native SVM and the artificial neural network, which are the most common data-driven techniques of dealing with such a problem.
Keywords:	Travel mode choice prediction, Support vector machines, Feature selection, Inter-urban mobility
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	STUDENTS FROM DIVERSE CULTURES IN THE MULTICULTURAL ONLINE CLASSROOM: ISSUES AND SUGGESTIONS
Author:	MAJED ALHARTHI
Abstract:	Cultural diversity is an important element in education that should not be neglected, given that it can lead to subtle differences in the nature of classroom discussions, student and teacher expectations, and overall classroom etiquette, as well as the degree of acceptance of technology. This study was carried out at the Saudi Electronic University, an online tertiary institution, with a sample of 128 first-year and 142 fourth-year students together with 65 teachers. It focused on discovering students' satisfaction with how cultural diversity was addressed, as well as measuring teachers' awareness of cultural diversity issues at the University. The findings indicated a lack of satisfaction among students with how cultural diversity was addressed, and that teachers did not have sufficient experience with issues of cultural diversity in the online classroom. The study concluded with a discussion of appropriate strategies for addressing cultural diversity in the online classroom, in addition to some design strategies for multicultural online courses through using computer-supported collaborative learning environments and social network learning communities. Hence, this study might help in creating online classrooms for all through using strategies like these to overcome students cultural diversity.
Keywords:	Culture, Cultural Diversity, Multicultural Classroom, Cultural Adaptation, Cultural Context.
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	DETERMINANTS OF M-COMMERCE ADOPTION: AN EMPIRICAL STUDY
Author:	NAHIL ABDALLAH, HENA IQBAL, HAMZAH ALKHAZALEH, AMER IBRAHIM, TAWFIK ZEKI, MOHAMAD HABLI, ODEH ABDALLAH
Abstract:	M-commerce has very rapidly developed into a very powerful way of reaching out to the consumer. M-commerce has been a massive success in terms of usersâ€™ adoption in some markets like Japan, while, astonishingly, not as thriving in others. However, its acceptance and level of adoption are low in Palestine compared to other countries. The research main objective is to classify the key variables that influence the acceptance of M-commerce among higher education students in Palestine by developing an M-commerce adoption Model based on an extension of the Technology Acceptance Model (TAM). A total of 430 questionnaires were collected and analyzed using Structural Equation Modelling (SEM) technique. The findings revealed that perceived usefulness, perceived ease of use, personnel innovation, security and privacy, subjective norms, and perceived trust are found to have an important effect on consumer behavioral intention to adopt M-commerce. These results will benefit stakeholders involved in M-commerce activities such as service providers, retailers, consumers, academicians, and students.
Keywords:	M-Commerce, TAM, Personnel Innovativeness, Perceived ease of use, Perceived usefulness, Subjective norms, perceived security risk
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	CONSUMER ATTITUDES TOWARDS ONLINE SHOPPING: AN EMPIRICAL STUDY AMONG MALAYSIAN COLLEGE STUDENTS
Author:	MARZIEH ZENDEHDEL, MOHAMAD FAZLI SABRI, RUSITHA WIJEKOON
Abstract:	This study analyses the factors foreseeing university studentsâ€™ e-commerce attitude, and intention at universities of Klang Valley region in Malaysia. In this research, cluster sampling method was utilized, and further, examined the moderating effect of collectivism/individualism as a measurement of culture on the association between attitude, and other variables for example; attribute of innovation (relative advantage, compatibility, and complexity), Trust (integrity, benevolence, and ability), perceived risk, and subjective norm. The outcomes of structural equation modelling demonstrated that the degree of intention of online shopping was comparatively higher in university students, and pathway of attitude towards the e-shopping has significantly positive among them. Furthermore, a noteworthy moderation effects on the association between attitude, and subjective norm, compatibility, and relative advantage were observed.
Keywords:	Collectivism, Individualism, Innovation Diffusion Theory, Theory of Planned Behaviour, Theory of Reasoned Action.
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text

Title:	RISK FACTORS TAXONOMY IN SOFTWARE DEVELOPMENT PROJECTS: STUDY FROM KUWAIT
Author:	ABDULLAH ALSHEHAB, THALAYA ALFOZAN, HESHAM GADERRAB
Abstract:	The objective of this research is to develop a taxonomy of software development projects risk factors in Kuwait. An intense review of more than 30 papers published in peer review journals in the field of information technology area in the period of 2000-2018. A number of 59 risk factors from the literature were collected. Seven IT experts from Kuwait validated these risk factors in two focus group sessions. The outcome of this research produced taxonomy of 28 risk factors that applies to Kuwait.
Keywords:	Software Development Projects, Risk Factor, Risk Management, Risk Taxonomy, Focus Group
Source:	Journal of Theoretical and Applied Information Technology 15^th May 2020 -- Vol. 98. No. 09 -- 2020
Full Text