		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

April 2023 | Vol. 101 No.8

Title:	OPTIMUM FEATURE SELECTION BASED BREAST CANCER PREDICTION USING MODIFIED LOGISTIC REGRESSION MODEL
Author:	D. VETRITHANGAM, P.SHRUTI, B. ARUNADEVI, R. HIMABINDU, P. NARESH KUMAR, A. RAMESH KUMAR
Abstract:	Patients with breast cancer are more likely to experience severe health issues and have a higher mortality rate. One of the main reasons for cancer-related deaths in women is breast cancer (BC). Early diagnosis of breast cancer enables patients to obtain proper care, enhancing their chance of survival. The main explanation could be that different breast densities and technical imaging quality issues cause radiologists to misinterpret concerning lesions, increasing the false-positive and negative) ratio. In this work, a new optimum feature selection-based model is developed to efficiently predict breast cancer using a modified logistic regression model. Our proposed model consists of two phases: a) feature selection and b) prediction. As a first step, preprocessing is done on the dataset to find the missing values and remove the unwanted noise, outliers, and so on. In this research work, the first dataset with 568 numbers of data and 30 numbers of features and the second dataset with 952 numbers of data and 26 numbers of features are considered for diagnosis and analysis. To select the features from the dataset's N features, an improved grey wolf population algorithm is used. Hence, 26 sets of features are selected for further processing. Our proposed model performed well on both datasets, with 92.9% and 93.38% accuracy for the first and second datasets, respectively. The novelty of this research work is to provide the best accuracy in disease diagnosis and prediction by selecting the optimum based on meaningful features.
Keywords:	Logistic Regression, Accuracy, Breast Cancer, Machine Learning, Prediction.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	INTERNATIONAL STUDENTS IN ONLINE LEARNING: A BIBLIOGRAPHIC ANALYSIS USING BIBLIOGRAPHY
Author:	HANNY HAFIAR, ANISSA LESTARI KADIYONO, KHOLIDIL AMIN, ARI AGUNG PRASTOWO, DAVI SOFYAN
Abstract:	This bibliometric study examines the distribution of publications about international students in online learning that have been published in reputable journals indexed by Scopus. The analysis concentrates on describing the characteristics and patterns of publications, authors, journals, countries, and author keywords. Four hundred fifty documents that have been retrieved from the Scopus database were analyzed. The phrases "international" and "learning" were used for searches. To create bibliometric maps, descriptive statistical techniques were applied, and Biblioshiny, an R-based program, was used for bibliometric analysis. The year 2022 saw the highest number of documents published, with 101. Articles have the most publications, with a total of 273 publications. "Journal of International Students" is the most productive journal, with 11 published documents. Chew, E. (United Kingdom) and May, D. (Georgia) are the most prolific authors with four documents. "International student" was the most used term, with 110 occurrences, followed by "online" (63) and COVID-19 (57). This study provides information for academics specializing in the field of international students and learning by providing an overview of the most popular keyword trends, journals, and authors on the issue of international students in online learning, which has been a theme that is quite popular in the world. This idea can be developed and carried out through further research in the future.
Keywords:	International Student, Online Learning, Bibliometric, Biblioshiny, Scopus
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	ANALYSIS OF FACTORS AFFECTING REPURCHASE INTENTION IN LIVE STREAMING E-COMMERCE
Author:	WILLIAM BUSTONI, VIANY UTAMI TJHIN
Abstract:	There is an emerging trend of purchasing online goods, which is currently popular through live-streaming social media applications called Live Streaming E-Commerce. The reason Live Streaming E-Commerce has become popular to use is that Live Streaming E-Commerce can create a real-time shopping environment and provides complete product information from multiple dimensions to help the buyer's decision-making process. However, from the Preliminary Research conducted, it Is found that respondents who have shopped through live streaming via Instagram Live before do not want to shop again. Therefore, the goals of the thesis were to determine factors that affect customer Repurchase Intention in shopping through live streaming via Instagram Live. The data was collected through an online questionnaire shared through social media and obtained from 415 respondents. The data processing results using SmartPLS show that Information Quality, Perceived Interactivity, Perceived Value, Effort Expectancy, and Satisfaction significantly affect Repurchase Intention. Not only that Satisfaction is also found to have a mediating effect between Information Quality, Perceived Interactivity, Perceived Value, and Effort Expectancy against Repurchase Intention.
Keywords:	Instagram Live, Live Streaming E-Commerce, Repurchase Intention, Satisfaction, Partial Least Square
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	MASTER DATA MANAGEMENT ANALYSIS FOR TODAY’S COMPANY: A LITERATURE REVIEW SYSTEM
Author:	WILLIAM EDEL, INDRAJANI SUTEDJA
Abstract:	Data is one of the most important things in a company. Data can be processed into information that can help a company decide on something important. With a very large amount of data, a company should be able to manage their data. Unfortunately, there are many companies that have no ability to manage their data. Therefore, their company will be affected, and their performance will drop. The trouble can be solved with the implementation of master data management. When a company implements the master data management system, they can more easily manage the valuable data, which will help the company improve their business processes and efficiency. From the results, we can see that each company faces a variety of data related issues, which become the background of each company’s implementation of the master data management system. But there are also a few problems after the company implemented master data management. Based on the research, we can conclude that each company employs a unique set of master data management implementation approaches and tools based on their needs. The purpose of this paper is to find out the uses of master data management in a company and the tools that companies use to implement master data management. The research used in this paper was done by reviewing 20 papers that discuss master data management. This paper is intended to find out more information about the tools and uses of master data management in a company.
Keywords:	Master Data Management, data, Master Data Management Tools
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	DEVELOPING AN INTELLIGENT INFORMATION SYSTEM TO SOLVE THE TASKS OF HEAT AND MASS TRANSFER PROCESSES IN SOILS IN THE DESIGN OF LOGGING ROADS
Author:	ANDREY NIKOLAEVICH BRYUKHOVETSKY, ALEKSEY VASILYEVICH SKRYPNIKOV, VYACHESLAV GENNADIEVICH KOZLOV, VLADIMIR ANATOLYEVICH ZELIKOV, GALINA ANATOLYEVNA PILYUSHINA, MARIA NIKOLAEVNA KAZACHEK, IGOR ALEXANDROVICH VIKULIN, VLADIMIR IVANOVICH KLEVEKO
Abstract:	The durability, reliability, and longevity of the roadway and surface of logging roads, as well as the quality and efficiency of their construction, largely depend on the heat and mass transfer processes, which occur inevitably during their construction and operation. The depth of theoretical research on heat and mass transfer processes and the degree of its practical utilization in road construction are determined mainly by the reliability of methods of determination and knowledge of thermal and moisture properties of highway soils and surface layers. In this connection, substantiation of methods for the assessment and study of the thermal and moisture characteristics of soils is a relevant task in the construction of roads in general and logging roads in particular. Thus, the study aims to develop an intelligent information system to address the processes of heat and mass transfer processes in soils for different calculation schemes in computer-aided design systems for logging roads. The developed heat and mass transfer calculation schemes enable the analysis of heat diffusion and moisture migration, as well as their mutual impact on each other. Based on the analysis of the considered physical nature of heat and mass exchange processes, the study offers a hypothesis on the heat and mass transfer processes occurring in the construction and operation of roads that can be studied via samples in compliance with the conditions of unambiguity, which allows determining the heat and mass transfer processes in soils. A general structural scheme for the study of heat and mass transfer properties of soils is developed, which makes it possible to substantiate the most rational methods of measuring moisture, thermal fluxes, coefficients of heat and temperature conductivity, moisture conductivity, and the thermogradient coefficient.
Keywords:	Soil, Moisture, Heat Flux, Thermal Conductivity, Moisture Conductivity.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	A SYSTEMATIC REVIEW OF VARIOUS NONLINEAR DIMENSIONALITY REDUCTION TECHNIQUES FOR ANALYSIS OF BIG DATA
Author:	OLAIYA FOLORUNSHO, TINY DU TOIT
Abstract:	The recent advancement in data-driven computing technologies in various disciplines has resulted in massive dimensional data being collected from multiple information sources. Many machine learning problems require processing a large set of features, finding it challenging to analyse the training set and find a suitable solution that maximises predictive power for the classifier performance. Therefore, it has become imperative to reduce massive features to the most significant ones for accurate data analysis from computation devices for predictive purposes. Over the years, researchers have developed several linear dimension reduction methods to reduce data dimensionality and identify data points with the highest possible variance. However, such techniques could not effectively handle data with a nonlinear relationship among the variables. Therefore, this paper presents state-of-the-art nonlinear dimensionality reduction methods for modelling complex nonlinear structures. The paper is presented in four folds: The first step involves discussing the most used nonlinear dimensionality reduction techniques. Second, a summary of the scope of application areas where dimensionality reduction methods have been applied is presented. The third fold compares various techniques based on their challenges and advantages. Finally, the performance evaluation of each approach in terms of its suitability for various applications will be discussed. The paper concluded that the autoencoder is an excellent technique for the dimensionality reduction of nonlinear high-dimensional data based on its tendency to accurately reconstruct data if there is a nonlinear connection in the feature space, also acurately capture the manifold's topology, and it tends to capture more of the global properties than other global techniques.
Keywords:	Big Data, Data Analysis, Dimensionality Reduction, Features, Nonlinear Techniques. Techniques.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	PREDICTING THE POSITION OF MILITARY PERSONNEL IN A CAREER PATTERN WITH TOPSIS ALGORITHM AND RECOMMENDATION SYSTEM
Author:	LELI SETYANINGRUM, EDI ABDURACHMAN, HARCO LESLIE HENDRICS SPITS WARNARS, JUNEMAN ABRAHAM
Abstract:	A career pattern is required in the context of a long-term career in a military organization. A decisive stage runs from hiring to termination for the accomplishment success of organizational tasks. To place positions in military organizations, the TOPSIS algorithm and recommendation system are beneficial in identifying career trends. TOPSIS ranks each employee's job proposals. The system employing collaborative filtering generates suggestions based on the rank data given the criteria of position placement. Determining military personnel's careers following their professions and areas of competence will be considerably aided by calculating the TOPSIS algorithm and recommendation system. It will make it easier for decision-makers to place the right man in the right places.
Keywords:	Military Personnel, Career Pattern, Recommendation System, TOPSIS, Personnel Positioning
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	INTERNET OF THINGS DESIGN ARCHITECTURE DEVELOPMENT FOR CONTROLLING AND MONITORING HYDROPONIC PLANTS
Author:	MUHAMMAD WILDAN, RIYANTO JAYADI
Abstract:	This research focuses on creating an Internet of Things (IoT) system that can monitor temperature, pH, humidity, and water flow in and out, increase flow strength, and measure the intake of nutrient solutions in the nutrient intake system in hydroponic systems. There are many problems found by researchers, such as 1) the difficulty of monitoring plant nutrition when not on the farm; 2) not being able to know whether the water level in hydroponic plants is normal or not; 3) when the water flow is abnormal, it cannot be controlled remotely; 4) not being able to monitor the temperature in hydroponic plants. To overcome these problems, we can utilize the Internet of Things (IoT) for control and monitoring in smart agriculture. IoT has proven to be very influential in the agricultural sector. by using the design thinking method and an object-oriented approach and creating a unified modeling language. An initial design was produced in the form of a smart farming system to control and monitor hydroponic plants using the Internet of Things (IoT). Hydroponic plants can be controlled and monitored with a mobile application to record the nutritional conditions of plants by measuring the pH of the water, the temperature of the plants, and the normal status of water flow. Hopefully, this technology will help advance hydroponic farmers while also attracting a large number of people to agriculture.
Keywords:	Hydroponics, Smart Farming, Internet of Things, Systems Design, Mobile apps.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	IMPROVING STUDENTS MATHEMATICAL PROFICIENCY THROUGH SYNCHRONOUS AND ASYNCHRONOUS APPROACHES USING DIGITAL MODULES
Author:	PURNOMO SAPUTRO, WAHYUDIN, TATANG HERMAN
Abstract:	The covid pandemic resulted in students losing knowledge about learning that had been obtained in previous meetings. Students' mathematical prowess as a prerequisite ability to be used in subsequent learning is weakened. The purpose of this research is to know the effect of implementing synchronous and asynchronous learning assisted by digital modules on increasing students' mathematical skills by paying attention to the level of learning loss. This study used a quantitative method with a quasi-experimental nonequivalent pretest posttest control group design. The sample consisted of 48 elementary school students. The test instrument is used as the primary means of data collection. The test instrument was tested for validity and reliability before the instrument was tested on students. Paired sample t-test analysis and independent t-test were used to answer the research hypothesis. The results of the study concluded that learning using synchronous and asynchronous models assisted by digital modules has a significant effect on students' mathematical skills. Students who get asynchronous learning get a higher influence when compared to students who learn synchronously. The research findings on the use of digital modules are expected to be able to provide alternative learning models in distance learning. This research is also a recommendation for future researchers to develop digital modules at the secondary education level.
Keywords:	Mathematical Proficiency, Synchronous, Asynchronous, Digital Module
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	IMPROVING ACCURACY IN SENTIMENT ANALYSIS FOR FORMAL AND INFORMAL MALAY LANGUAGE USING SEMANTIC INFORMATION
Author:	NURUL AIDA OSMAN, DUC NGHIA PHAM
Abstract:	This paper presents a lexicon-based sentiment analysis model that is specifically designed for analyzing sentiments in formal and informal Malay language texts. The main challenge when dealing with Malay language is handling noisy texts and sarcasm. To overcome this hurdle, we propose a method to enhance the lexicon by incorporating semantic information and gloss information from Kamus Dewan and synonym chains from WordNet Bahasa to obtain sentiment terms. The goal is to utilize these semantic information and sentiment terms to enhance the accuracy of sentiment analysis in both formal and informal Malay language. The proposed model generates a semi-supervised Malay sentiment lexicon for both formal and informal Malay language and utilizes semantic information to further enhance its performance accuracy. We manually annotated two evaluation datasets, one in formal Malay and one in informal Malay, with sentiment values. We then conducted experiments on two models corresponding to formal Malay language and informal Malay language using these datasets. The results demonstrated that the proposed approach achieved an average accuracy of 90.0% and 88.4% for formal and informal Malay language, respectively. This confirmed that semantic information can effectively boost the performance accuracy of sentiment analysis model (in comparing with existing models) for Malay language.
Keywords:	Sentiment Analysis, Opinion Mining, Lexicon Based Sentiment, Malay Lexicon, Informal Malay Lexicon, Formal Malay Lexicon
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	PATTERN RECOGNITION AND CLASSIFICATION OF EEG SIGNALS FOR IDENTIFYING THE HUMAN-SPECIFIC BEHAVIOUR
Author:	GUNAVATHIE M A, S. JACOPHINE SUSMI
Abstract:	Analyzing human emotions is a nascent research area that is possible by the analysis of facial expressions in visual, spoken sentences from audio recordings, written content from textual messages, etc. This concept has a vast range of applications, such as monitoring the improvement in psychiatric patients, assisting robots in interacting more intelligently with people, and monitoring signs of attention while driving to enhance driver safety. Information can be aggregated from the emotions communicated through an online platform, including the number of likes and positive or negative reviews that it attracts. To detect the emotion of people for the above application, Electro Encephalogram (EEG) signals are used. Three major emotions of Anger, Sad and Happy can be detected by visualizing the data. All of them are classified depending upon their intensity after transforming the data by Continuous Wavelets. Convolutional Neural Networks are used to train the images generated from the EEG files. The Dataset created is thus trained to later test new signals. In comparison to the other Models, CNN offers better performance since it can do not require several hyperparameters. This is a novel approach of feeding raw EEG signals for Emotion Detection which can be used in multiple fields.
Keywords:	EEG, CNN, Hyperparameters, Human Scientific Behavior, Classification
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	A MODEL FOR THE BUSINESS INTELLIGENCE SYSTEM ACCEPTANCE IN THE SOUTH AFRICAN BANKING SECTOR
Author:	ARNET ZITHA, DR. OLUSEGUN ADEMOLU AJIGINI
Abstract:	Due to the rapid growth of new technologies, there is a substantial growth in the Business Intelligence (BI) market caused by the competitive forces making the organizations to adopt their offerings to the needs of the customer. Consequently, the adoption of Business Intelligence system has led to important technological and organizational innovations in modern organizations by promoting knowledge diffusion, and cornerstone of business decision making processes. There are few articles in this research area and this article is intended to fill this gap. Thus, the focus of this research is the development of a model for the BI system acceptance within the banking sector. using the Cronbach Alpha and they were found to be good. BI Systems Acceptance has the highest Cronbach Alpha. The reliability of the constructs was measured value of 0.865. Moreover, the convergent validity of the constructs is satisfied and also the discriminant validity is confirmed for all the constructs. The following variables determine the behavioral intention towards BI system: performance expectancy, effort expectancy, social influence, facilitating conditions and hedonic motivation with effort expectancy being the variable with the highest contribution (β = 0.256). Multiple regression analysis was used to determine the variables contributing to the behavioral intention towards BI systems. Discriminant and construct validity were confirmed for all the variables and the data is free from multicollinearity (1.000 < VIF < 2.859) where VIF is the variance inflation factor. The behavioral intension towards BI was found to influence positively the BI systems acceptance.
Keywords:	Business Intelligence, Decision-making, Unified Theory of Acceptance and Use of Technology (UTAUT), Banking Sector, Regression Analysis.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	A HYBRID APPROACH FOR TEXT CLASSIFICATION
Author:	M.KAVITHA, Dr.P.PRABHAVATHY
Abstract:	On the internet, a huge amount of text data is collected, and segregating it based on a particular category is a crucial task. The data collected can be structured or unstructured. In the proposed method, machine learning algorithms and ensemble technique is used to handle the unstructured text data for classifying the text. The paper aims to evaluate the performance of the machine and deep ensemble classifiers. Ensemble classifiers provide solutions to numerous problems. There are various methods for the ensemble. General ensemble techniques are bagging, boosting, and stacking. In this paper, the bagging and boosting techniques are used to evaluate the performance of the models. Different voting schemes are available in the bagging method. The ensemble learner used in this paper makes predictions based on voting techniques.
Keywords:	Bagging, Boosting, Ensemble, Machine Learning, Deep Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	SOFTWARE SECURITY READINESS MODEL FOR REMOTE WORKING IN MALAYSIAN PUBLIC SECTORS: CONCEPTUAL FRAMEWORK
Author:	HALIMATON HAKIMI, MASSILA KAMALRUDIN, RAIHANA SYAHIRAH ABDULLAH, MOHD FAIZAL ABDOLLAH, SAFIAH SIDEK , NIK SUKI, DEWI OCTAVIANI, AERVINA MISRON
Abstract:	Resulting from the COVID-19 pandemic, which requires mankind to practice social distancing, companies and government agencies do not have any options but to send their workers home and practice remote working. With very limited guidance, workers are required to work remotely by utilizing various software facilitated by Internet. The increased dependence on the cyberspace opens up the organization to become highly vulnerable to cyber threats/crimes, which may affect their performance. Hence, organizations need to manage their cyber risk by ensuring that they are capable to manage software security. Therefore, this study aims to propose a new software security readiness model that is able to measure the level of organizational readiness for workers working remotely. The readiness model enables the organizations to take proactive actions for continuously improving their weaknesses related to cyber threats. Furthermore, the model can be used as guidance to develop policy for the organization specifically and for the country (Cybersecurity Malaysia) for ethical use of digital technologies especially for remote working.
Keywords:	Software Security, Readiness Model, Remote Working, Public Sector
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	ANALYSIS OF E-LEARNING IMPLEMENTATION IN PT.XYZ COMPANY USING UTAUT METHODHOLOGY
Author:	HAMDI EKA PUTRA, MUHAMMAD ZARLIS
Abstract:	PT XYZ has been using MyLearning e-learning for several years but has never evaluated the acceptance of the e-learning system. The use of e-Learning is very low and most of completion rate below 40% for training rolled out during year 2022. This research will examine the factors that influence the use of Mylearning application in PT XYZ company to find out the aspects of acceptance and use of e-Learning by employees. The results can be used as a planned evaluation material so that it can be used as a recommendation for the implementation of e-learning in the future. This research was conducted using quantitative method and analysis using modified UTAUT model by adding Work Overload variable and Management Effectiveness variable. Data collection was carried out using a questionnaire to all employees of PT XYZ. Data was analyzed using PLS-SEM obtained from survey results through questionnaires to 248 MyLearning application users at PT XYZ. From the results of the study, it was found that there were 6 hypotheses accepted and 1 hypothesis rejected from a total of 7 hypotheses tested. Effort Expectancy, Performance Expectancy, Management Effectiveness have a positive effect on Behavioral Intention, Work Overload variables, facilitating conditions are factors that influence the acceptance of technology use that can be taken into consideration in the implementation of eLearning in companies.
Keywords:	E-Learning Online learning, Learning Management Systems, Mylearning, Utaut
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	THE IMPACT OF GAMIFICATION ON CREATIVE AND INNOVATIVE SKILLS OF GRADUATE STUDENTS
Author:	SAWANAN DANGPRASERT
Abstract:	This study aimed to evaluate the effectiveness of a gamification design in enhancing creative and innovative thinking skills among graduate students. Five objectives were pursued: (1) to identify the factors of gamification that contribute to enhancing these skills, (2) to design learning outcomes for the gamification, (3) to develop the gamification for enhancing these skills, (4) to compare the pre-implementation and post-implementation results of graduate students' creative and innovative thinking skills, and (5) to investigate the correlations between these skills. The gamification design consisted of five elements: Exercise, Achievements, Reward Systems, Community Synchronization, and Result Transparency. Results of a factor analysis revealed that key factors that had an impact on creative and innovative thinking were Problem-Solving, Exploration, Risk-Taking, Brainstorming, Open-Ended Play, Diverse Perspectives, and Novelty, with a cumulative explanation of variance of 86.80%.Comparing the pre-implementation and post-implementation results of the graduate students showed a significant improvement (p < 0.01) in both their creative and innovative thinking skills. Correlations between the students' creative and innovative thinking skills were mostly significant (p < 0.01), indicating that the gamification design had a direct positive impact on their creative and innovative thinking abilities. In conclusion, this study provides evidence that a gamification design can enhance graduate students' creative and innovative thinking skills, and highlights key factors that contribute to this enhancement. These findings have implications for the design of effective gamification interventions in educational settings.
Keywords:	Gamification, Creative Thinking Skill, Innovative Thinking Skill, Graduate Student
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	AN ACCURATE HUMAN EMOTION RECOGNITION FRAMEWORK USING MACHINE LEARNING
Author:	HANI MOAITEQ ALJAHDALI
Abstract:	In advance phase of life, artificial intelligence plays a vital role to facilitate the end users by different aspects. From human body, emotion detection is one of those features that is involved in most of the application and action is performed accordingly. An accurate emotion detection is still challenge for AI approaches. This research paper presents how speech features are used to detect and recognize the emotions that human is trying to express in their speech. With the help of Gaussian-Mixture-Model (GMM) , First the feature is extracted using Mel-Frequency-Cestrum-Coefficients from the speech directly. In experiments, multiple parameters of MFCCs are evaluated by using the GMM method. While the implementation, we used Berlin-Emotional-Database considering variety of emotions including Anger , Disgust , Fear , Happy , Neutral and Sad . We also consider the gender based parameters, and detect the perspective emotions including Anger , Disgust , Fear , Happy , Neutral and Sad . The experimental results compared with existing methods hidden Markov-Model with the MFCC, delta-MFCC and speech energy; consequences showed that our proposed approach is more accurate as compare to existing state-of-the-art methods, and attained 94.45% accuracy level.
Keywords:	Gender-Recognition, Machine Learning, Face Recognition, Emotion Detection.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	TECHNICAL CHALLENGES REVIEW AND READINESS FOR ADOPTING SMART CITIES IN KUWAIT
Author:	ABDULLAH ALSHEHAB, THALAYA ALFOZAN, MOHAMMAD ALAHMAD, JASEM ALOSTAD, ABDULRAHMAN ALKANDARI
Abstract:	The trend towards smart cities is a growing phenomenon among governments worldwide, driven by the need to keep pace with the rapidly evolving technological landscape and the increasing demand for improved social services from citizens. In metropolitan areas across the globe, policymakers are investing heavily in technologies that enable the transformation of traditional cities into smart cities. To better understand the technical challenges facing smart city initiatives in Kuwait, a research study was conducted that analyzed more than 100 papers in an attempt to identify the technical challenges that could potentially hinder the successful implementation of smart city projects in Kuwait. The experiment was carried out through a focus group session that was held with six experts in ICT. During the session, the experts rated the readiness of each of the identified technical challenges, providing valuable insights. The outcome indicated that the level of readiness for smart city initiatives in Kuwait needs to be increased were the top challenges that were identified (i) Blockchain, (ii) AI, and (iii) Cybersecurity. The study suggested that this could be achieved through a comprehensive and well-defined national ICT scale strategic vision. The study suggested that smart cities’ initiatives could be achieved through a comprehensive and well-defined national ICT scale strategic vision. The findings of this study can be used to inform future policy decisions and guide the development of smart city projects in Kuwait.
Keywords:	Smart Cities, Technology Challenge, Digital Transformation, IoT, Blockchain, Cybersecurity.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	ANALYSIS OF PRICE AND MARKET CAPITALIZATION OF ALTERNATIVE COIN AS A CRYPTOCURRENCY MARKET EDUCATION FACILITY IN INDONESIA
Author:	MEIRYANI, SHI MING HUANG, ZALFA ANNASYA Z, AGUNG PURNOMO, GAZALI SALIM, MICHAEL ANGELUS, FANY INASIUS
Abstract:	This study aims to describe altcoins and provide understanding and education to the cryptocurrency market community. Data collection is secondary data that is public, namely from the publication of scientific papers, research results, writings from websites, internet sites, and news articles. This research method uses descriptive-analytic, the process of data analysis to get an overview of the data that has been collected. The findings obtained are that there are altcoins that are stablecoins and that each altcoin has a consensus mechanism, which is Proof of Work (PoW) and Proof of Stake (PoS). The finding reveal that almost all cryptocurrencies have decentralized characteristics, meaning that they are not controlled by a central government or Central Bank. This study analyzes the undervalue of altcoins, altcoins that have a low value but have a high market cap, which means that even low-value altcoins can be considered a safe investment. In Indonesia, cryptocurrency has not been recognized as a legal currency, but is recognized as an investment alternative.
Keywords:	Cryptocurrency, Altcoin, Education, Facility, Martket.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	AN INTELLIGENT MORE METHOD FOR PRIVACY -PRESERVING TRAINING TECHNIQUE IN CLOUD ENVIRONMENT
Author:	R. HARI KISHORE, A. CHANDRA SEKHAR, PRAMODA PATRO, PRAGATHI CHAGANTI
Abstract:	For internal computations and training with huge data in an acceptable period of time, traditional machine learning modelling needs a lot of computer power. Cloud computing has made this procedure easier in recent days, but it has also introduced new security risks such as data leaks. Owing to its capacity to conduct operations over ciphertext, the previous research effort offered a unique homomorphic encryption architecture. Nevertheless, the data given by one party is not always sufficient to construct a capable system using machine learning in this technique. It permits a non-trustworthy third-party resource to handle encrypted data without revealing sensitive information. MORE (Matrix Operation for Randomization and Encryption), a privacy-preserving training technique using the encryption technique suggested in this work, allows calculations inside a modified deep neural network approach to be directly conducted on floating-point data having comparatively low operational cost. Using a popular MNIST digit identification issue to assess the viability of the suggested method while modified deep learning is used to MORE homomorphic information, efficiency does not suffer. Finally, the experimental outcomes states that the proposed method obtains increased security compared to existing algorithms.
Keywords:	Classification Problem, Homomorphic Encryption; MNIST Digit Recognition Problem; MORE (Matrix Operation For Randomization And Encryption); Modified Deep Learning Model; High Security.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	USING 3D MODELING SYSTEMS TO CREATE A SMALL PORTABLE MILLING MACHINE CONTROLLED BY AN INDUSTRIAL CLOUD
Author:	AMER TAHSEEN ABU JASSAR
Abstract:	This paper describes the concept of unified modeling of analysis tools, as modeling is regarded as useful method for the mechanism planning of devices, machines, individual parts, and assemblies used in mechanical engineering. Modeling is one of the analysis tools that permits to preliminarily study some objects, methods, or developments at given properties; accordingly, modeling tends to understand the nature of those characteristics and then re-creates an object, process, or phenomenon that has a degree of common relationship. Thus, modeling is the process of reflecting and learning some properties with the aim of further recreating these properties and improving them if necessary. On the investigated model of the 3D model for a small-sized portable portal miller, the selection of individual parts of such a tool is shown and justified. Moreover, a diagram of a conveyable portal edge machine with Computer Numerical Control (CNC) has been generalized and developed. Through investigating the modeling and designing the necessary devices and mechanisms, a variety of systems have been studied to explain the reason for choosing the SolidWorks system for modeling types. The choice of individual components of a small-sized portable portal milling machine is demonstrated and justified using the example of making a 3D model. In addition, a generalized and developed block diagram of a portable portal milling machine with CNC has been created, where each element of such a block diagram is described and a recommended selection is made. Finally, individual components of a portable portal milling machine were modeled with CNC and the results are displayed for a detailed 3D model of the milling machine's top portal assembly with the G-PENNY MACHINE spindle fitted is also displayed.
Keywords:	Computer Numerical Control (CNC), 3D parametric modeling, Automatic Tool Change (ATC), Line Print Terminal (LPT), Universal Serial Bus (USB)
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	MACHINE LEARNING APPLIED IN MEDICINE SECTOR : THE CHALLENGES AND PERSPECTIVES
Author:	RANYA KHADDOR, MAHACINE AMRANI, JAMAL BRIGUI
Abstract:	In this study we address the application of Machine learning for medical diagnosis. A thorough analysis of various scientific articles in the domain of intelligence artificial application in the medical field has been conducted. However, to promote bioinformatic studies and research, several companies and scientific research development are keeping the challenge by improving and designing new useful applications applied on the selected sector fields. In this paper we hope to present the art of state of several works corresponding to the medicine field. Then, we aim to showcase the current state-of-the-art in various works pertaining to medicine. Our study resumes the analysis of the existing works of intelligence artificial applied to medicine and bioinformatics fields. Despite progress, significant challenges remain in various sectors and research domains. By conducting a comparative analysis of select works, we identify common characteristics and present our findings through a detailed discussion.
Keywords:	Medicine, Machine learning, Deep learning, Design, Classification, Bioinformatics, Healthcare
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	FACTORS AFFECTING THE USE OF TABLETS IN THE LEARNING PROCESS OF PRIMARY SCHOOL STUDENTS IN SAUDI ARABIA
Author:	GHAZI ALRAKAS, NURULLIZAM JAMIAT
Abstract:	In the current digital era, distance learning has become the first trend that has dominated all other educational trends. The COVID-19 pandemic has drastically changed teaching and learning methods. Due to social distancing, students have become accustomed to distant learning via digital platforms. One of the most difficult challenges students confront is the lack of engagement in the educational process. This paper explores the problem of lack of engagement in distance learning and investigates the relationship between tablet use and student engagement. A survey questionnaire was developed and distributed among 279 primary school students in Saudi Arabia using a quantitative methodology. The results reveal that hedonic motivation is the most significant factor affecting student engagement, followed by the facilitating condition factor, while performance expectancy has the least effect. These findings can inform policymakers in the Saudi educational sector about the importance of appropriate human resource management practices to improve student performance. Furthermore, the study suggests exploring the moderation effect of major groups such as students' study course, age, gender, and study phase on the relationship between the studied factors and students' engagement in the learning process. Overall, this study highlights the importance of using digital platforms to engage students in the learning process, especially in the current distance learning era.
Keywords:	Students Engagement, Education, Technology, Distant Learning, Hedonic Motivation, Saudi Arabia, Tablet, COVID-19
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	APPLICATION OF THE KANSEI ENGINEERING METHOD IN THE DEVELOPMENT OF E-LEARNING SCHOOL OF HARUM SENTOSA BARUS FOUNDATION
Author:	FUZY YUSTIKA MANIK, DEWI SARTIKA BR GINTING, ANANDHINI MEDIANTY NABABAN, UMAYA RAMADHANI PUTRI NASUTION, T. HENNY FEBRIANA HARUMY
Abstract:	E-learning applications are now widely available on various platforms, both paid and free. However, the school needs a private e-learning application that can be managed and customized by the school and of course requires features according to school needs. Several institutions have developed E-Learning. However, most of them only focus on the developer's perspective without considering what kind of E-Learning the learner really wants. Preferably, E-Learning products should not only focus on the technical part such as convenience, advantages or other features, but the point is how to psychologically entice users to use the product. To create an e-learning website that is user-friendly and has a high level of usability, a software development method is needed, one of which is the Kansei Engineering method. This research resulted in several emotional factors that must be considered in designing e-learning displays. The research proves that there is a relationship between the interface and the user's feelings, the relationship between Kansei words which affects the appearance of the desired interface. The three methods of multivariate analysis are like CCA proved to be an effective method for determining relationship between Kansei words. FA effectively determines the power of Kansei's words to e-learning interface so it can be determined which Kansei words to consider in choosing and implementing e-learning, especially using open source LMS for schools. The results show that the user's emotional factor influence behavior, while the most influential only one, namely modern. The Kansei word modern has a very strong relationship with two Kansei words like "Interesting" and "Informative". The concept of Kansei words can be used to build applications according to the user's feelings. However, aspects of ease of access, effectiveness, and not loading for a long time are also things that must be considered. Although not all kansei word design principles are accommodated, interaction design elements are able to produce application designs that have good usability. In addition, determining the type and size of the font also considers legibility by the human eye. In terms of coloring, the use of a gray background color and a blue top menu color is expected give the impression of modern, interesting and informative for user. Expected, the use of color the right one can make it easier for the user identify the information contained inside it. Even though the aesthetic appearance has a modern impression, Information that presented along with the flow of information made with a simple systematic. Besides that, some of the terms used on this application adapted to the reality in real life. It makes it easy the user understands the intent of the application.
Keywords:	E-learning, Emotional, Kansei Word, User Interface
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	FACTORS THAT INFLUENCE THE SELECTION OF A MOBILE STOCK TRADING APPLICATION
Author:	JULIUS HERMANTO, TOGAR ALAM NAPITUPULU
Abstract:	The public may select from a plethora of competing mobile stock trading application. Everyone's perspective on a certain application is further differentiated by the benefits and disadvantages that each one has to offer. Therefore, this study aims to examine the variables that impact an individual's choice when selecting a mobile stock trading application that they opt to use or currently utilizing. This study offers an integrated theoretical framework employing a modified Technology Acceptance Model and survey data from 109 Indonesian users of mobile stock trading applications using the structural equation modeling method. Six constructs—ease of use, user interface experience, perceived advantages, security and privacy risk, social impact, and trust—are included in the recommended model. According to the findings, social influence and trust significantly impact how mobile stock trading applications are chosen in Indonesia. Companies should concentrate on factors that encourage app adoption, such as social impact strategies, transparency, and top-notch customer service, in order to improve app utilization. The study is restricted to users who reside in Indonesia, however future studies may cover a larger audience and additional samples.
Keywords:	Mobile Stock Trading Application, Intention, User Behavior, Retail Investors, Choice
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	MARKETING AND LOGISTICS IN THE ADAPTIVE MANAGEMENT OF ENTERPRISES IN THE CONDITIONS OF DIGITALIZATION
Author:	SERHII AREFIEV, VOLODYMYR LAGODIIENKO, VALERY TKACHEV, SERHII STAVROIANI, OLEG SHEVCHENKO
Abstract:	Modern globalization challenges of the formation of a post-industrial society, changes in the processes of economic systems at various levels caused by the Covid-19 pandemic necessitate the development of conceptual principles for the application of marketing and logistics in the adaptive management of enterprises in the conditions of digitalization. The purpose of the study is to substantiate theoretical and methodological principles of evaluating the functioning of marketing and logistics processes at the enterprise in the conditions of digitalization. In terms of evaluating the functioning of marketing and logistics processes at the enterprise in the context of the implementation of the adaptive management principles in the conditions of digitalization, traditional functional roles of these management areas are taken into account, in particular, marketing as a system for organizing effective interaction of the enterprise as a market entity and logistics as a system for establishing effective movement of material and information flows in their time and cost dimensions relative to the compiled production program and the market situation. To evaluate the functioning of marketing and logistics processes at the enterprise in the conditions of digitalization, it is proposed to apply the method of stochastic factor economic-mathematical analysis through the analysis of the main components using the Varimax and Bartlett method. The proposed approach was tested in relation to the activities of ArcelorMittal Kryvyi Rih PJSC. The proposed method of stochastic factor analysis makes it possible to identify groups (components) of the most influential factors affecting relevant performance indicators, provide their quantitative assessment and assess the degree of interrelationship of these factors within individual component.
Keywords:	Marketing, Logistics, Adaptive Management, Digitalization Stochastic Factor Analysis, Principal Component Analysis Method
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	UNHEALTHY PLANT REGION DETECTION IN PLANT LEAVES USING ADAPTIVE GENETIC ALGORITHMS
Author:	DR. SURYA PRASADA RAO BORRA, DR.M.V.GANESWARA RAO, DR P.RAVI KUMAR, DR.SRINU PYLA, DR.K. VIDYA SAGAR, DR A GEETHA DEVI, KOTESWARA RAO KODEPOGU
Abstract:	The major issue faced by the farmers is crop diseases, which is causing a significant reduction in both the quality and quantity of the yield and hence, it needs to be addressed. The emergence of new and accurate techniques in the field of leaf-based image classification has shown impressive results. This paper shows the use of Random Forest in identifying between healthy and unhealthy leaves from the data sets created. Also, this paper consists of various phases of implementation namely dataset creation, feature extraction, training the classifier, masked cells, neural networks, k-means clustering, SGDM Matrix Generation. The created datasets of diseased and healthy leaves are collectively trained under Random Forest to classify the diseased and healthy images. Overall, using machine learning to train the large datasets available publicly gives us a clear way to detect the diseases present in plants.
Keywords:	Healthy leaf, Random forest, machine learning, k-means clustering, Feature extraction, Training, Classification
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	ANOMALY DETECTION IN CYBER-PHYSICAL SYSTEMS USING EXPLAINABLE ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
Author:	SHERIF KAMEL HUSSEIN , MOHAMED A. EL-DOSUKY
Abstract:	Cyber-Physical Systems (CPS) embrace integration between digital & physical components of production environments. Data analysis approaches operate on big data, which makes them somewhat limited in industrial applications. Not all of anomaly detection techniques are applicable in ensuring security of CPSs. These techniques face huge volumes of data and require domain-specific knowledge, which necessitates the invention of solutions that integrate advanced AI technologies and models. This paper utilizes Explainable Artificial Intelligence (XAI) & Machine Learning (ML) approaches for detecting the anomalies in CPS. The proposed model improves our understanding of the complex phenomena in CPSs by analyzing the extracted features using feature engineering selection and detecting the outliers of each class labels. Hence, the main motivation of this paper is to scrutinize challenges and emerging trends in Anomaly Detection for CPSs. Furthermore, studying the outlier detection algorithms such as Angle-based Outlier Detection (ABOD) and Clustering Based Local Outlier Factor (CBLOF) to be compared with the proposed approach. Neither of ABOD nor CBLOF succeeds in distinguishing the outlier class. Therefore, the proposed approach attempts to handle the outlier detection by using feature engineering and XAI approaches. Moreover, ML based Random Forest (RF) achieves better results than Support Vector Machine (SVM), Naïve Bayes (NB), and multi-layer perceptron (MLP).
Keywords:	Anomaly Detection, Machine Learning, Cyber-Physical Systems, Explainable Artificial Intelligence, Outlier Detection
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	USABILITY ANALYSIS ON MOOC PLATFORM
Author:	ANGELINA GRACIA EDDYPUTRI BURHAN, DIYURMAN GEA
Abstract:	MOOC (Massive Open Online Course) is one of the alternative learning media that offers online learning facilities. This study explores the reasons why the use of MOOCs, especially Coursera, in Indonesia is relatively low. The purpose of this study is to examine usability on the Coursera web so that the use of this web can be maximized in a better way and following consumer desires. The research method used is by using a questionnaire and reviewing the literature. Data were collected from 101 respondents, and the results showed that the Coursera web has an average SUS score of 72.8, rating acceptability ranges in the high category, grade scale in category C, and adjective ratings in the good category. Coursera website is already included in a good category according to its users. Things that need to be improved are system complexity, assistance in using the system, and consistency in the system.
Keywords:	Usability, MOOC, Web Course, Evaluation, System Usability Scale
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	PREDICTION OF COMORBID MALIGNANCY PATIENT SURVIVABILITY - EMPIRICAL PERSPECTIVE
Author:	DR Y PADMA, DR NIDAMANURU SRINIVASA RAO, MR. PAVAN KUMAR KOLLURU, DR C ASHOK KUMAR MS. SHAIK SALMA BEGUM, DR. SURESH CHANDANAPALLI, KODEPOGU KOTESWARA RAO
Abstract:	Modeling the survivability of comorbid cancer patients has both theoretical and practical implications. Cancer is one of the leading causes of death worldwide. Stomach, Liver, Thyroid, Lung and Skin Cancers are some of the most frequent cancers. The detection and prevention of these malignancies are crucial goals. According to recent discoveries, some people have cancer comorbidity. A number of studies have shown poorer survival among cancer patients with comorbidity. Several mechanisms may underlie this finding. The majority of studies found that cancer patients with comorbidity had a lower 5-year survival rate than those without, with hazard ratios ranging from 1.1 to 5.8. Only a few studies looked into the impact of specific chronic illnesses. Comorbidity does not appear to be linked to more aggressive cancers or other abnormalities in tumor biology in general. Another conclusion was that patients with comorbidity are less likely to obtain standard cancer therapies such surgery, chemotherapy, and radiation therapy, and their chances of completing a course of treatment are reduced. Predicting cancer survival may help with clinical decision-making and tailored therapy. Large data sets appropriate for machine learning analysis are available through the Surveillance, Epidemiology, and End Results (SEER) program. We regard survival prediction to be a two-stage problem in our study. The first is to forecast a patient's five-year survival rate. The second stage calculates the remaining survival time for individuals whose anticipated outcome is 'death.' The SEER database was used to identify and label male and female comorbid cancer cases (Stomach, Lung, Liver, Thyroid and Skin Cancers). The dataset was handled utilizing CHI2- based feature selection throughout the classification stage. These two solutions tackled the problems of a skewed data set.
Keywords:	CHI2,SEER, COMORBID, Survivability, Empirical Study
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	ENSEMBLE OF DEEP LEARNING MODELS FOR CLASSIFICATION OF HEART BEATS ARRHYTHMIAS DETECTION
Author:	S.JAYANTHI, DR.S.PRASANNA DEVI
Abstract:	Arrhythmias are one of the top causes of death worldwide, and due to changing lifestyles, their prevalence is rising dramatically. Due to their non-invasive nature, ECG signals have often been used to detect arrhythmias. The manual technique, however, takes a long time and is prone to error. Utilizing deep learning models for early automatic identification of cardiac arrhythmias is a preferred alternative to improve diagnosis and management. This paper proposes a unique ensemble deep structured learning model for categorizing arrhythmias that integrates attention mechanisms, bi-directional long short-term memory, and a convolutional neural network. It classifies beats into five categories: non-ectopic (N), supraventricular ectopic (S), ventricular ectopic (V), fusion (F), and unknown (Q). MIT-BIH and St. Petersburg data sets are integrated as multi-model datasets for training, validating, and testing the suggested model. The model's performance was also tested with the f1-score, recall, accuracy, and precision. Based on the ensemble of all of these approaches, this model is 99% accurate.
Keywords:	Artificial Neural Networks, Deep Structured Learning Models, Arrhythmia Detection, Ensemble Models
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	THE INFLUENCE OF UTILITARIAN VALUE AND HEDONIC VALUE ON OMNI-CHANNEL SHOPPING INTENTION THROUGH TAM PERCEIVED USEFULNESS AND PERCEIVED EASE OF USE
Author:	YOSUA GIOVANN WIDJAJA, IDRIS GAUTAMA SO, RINI SETIOWATI, ASNAN FURINTO
Abstract:	This study aims to determine the effect of Utilitarian Value and Hedonic Value on Omni-Channel Shopping Intention through TAM Perceived usefulness and Perceived ease of use in Indonesia. This technological advancement gave rise to many new phenomena that have been very pronounced lately. The invasion of e-commerce became the starting point for the use of internet facilities in retail business activities. The sample for this study was 250 respondents consisting of retail users who had implemented an omni-channel strategy in selling their products. The analytical method of this research uses quantitative methods using SEMPLS. The results of this study found that Hedonic Value had no statistically significant effect on the Perceived usefulness construct, Hedonic Value had a positive and statistically significant effect on the Omni-Channel Shopping Intention construct, Utilitarian Value construct had a positive and statistically significant effect on the Perceived ease of use construct, Utilitarian The construct value has a positive and statistically significant effect on the Omni-Channel Shopping Intention construct, the perceived usefulness construct has a statistically significant effect on the Omni-Channel Shopping Intention construct and the Perceived ease of use construct has a statistically significant effect on the Omni-Channel Shopping Intention construct. The recommendation from this study is the use of TAM is a source of success for Omni-Channel business.
Keywords:	Hedonic Value, Utilitarian Value, Omni-Channel Shopping Intention, Perceived Ease Of Use, Perceived Usefulness
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	SEVERITY PREDICTION FOR TRAFFIC ROAD ACCIDENTS
Author:	AYOUB ESSWIDI, SOUFIANE ARDCHIR, ABDERRAHMANE DAIF, MOHAMED AZOUAZI
Abstract:	Automobile manufacturing, transport and other social and economic fields are impacted by road security. So, the number and the severity of traffic road accidents are problems faced by all these fields to continue their development, this problem can be considered also as an obstacle that slows down the development of countries. Regarding the fast development of data science, those in charge of road management must use this science to minimize the number of accidents or reduce their severity. This study employed exploratory data analysis (EDA) and machine learning (ML) algorithms to predict traffic road accident severity and show the factors that affect them. To this end, we used a dataset proposed by the department for transport in the United Kingdom (UK). This dataset contains information about almost 91200 accidents within more than 70 features in 2020. It was collected by each police force independently, and it is distributed on three CSV files; data about accidents, data about the casualties and data about vehicles crushed. the tasks were, firstly, exploring data and giving insights. Secondly, cleaning and preparing the data for machine learning algorithms, then building and evaluating models using four ML algorithms, and finally, comparing these models to choose the accurate one. As a result, artificial neural networks (ANN) demonstrate their performance. In which, the accuracy reached 0.83 with an average precision of 0.76 and an average f1-score of 0.77 based on the 26 most significant factors.
Keywords:	Traffic Road Accidents, Severity Prediction, Gravity of Accidents, Machine Learning.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	IMPROVING E-LEARNING WITHIN ORGANIZATIONS USING MACHINE LEARNING
Author:	M. EZZAKI, S. BOUREKKADI , Y. FAKHRI , S. KHOULJI
Abstract:	This article discusses the issue of improving the occurrence of E-learning professional training within organizations to provide guidance for improving staff efficiency using machine learning. The proposed methodology is based on the statistical learning of a model of evolution of qualifications from available information considered and observations of practices within organizations. The main originality consists in representing the evolution of careers through the specific process of vocational training within companies. This representation will be used in particular to group the types of activities into similar behaviors and to construct a common model for each of the behaviors identified. We then implement a method of automatic learning of a model of evolution of skills using distance professional training (e-learning). This model makes it possible to provide a predictor of the occurrence of the need to set up professional training in e-learning over a given future period and therefore to give advice for training freely at any time and from any place for employees.
Keywords:	Machine Learning, E-Learning, Prediction, Organisations Improving.
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text

Title:	FACTORS AFFECTING PADDY FARMERS IN USING DRONES
Author:	MOHD SAZILI SHAHIBI, NORHAYATI HUSSIN , ZAHARUDIN IBRAHIM3 , AMER SHAKIR ZAINOL ,MUHAMMAD ZAFFRI MOHD ZAZMI
Abstract:	In Malaysia, the agriculture industry is the most promising, but it is now facing several issues, one of which is the scarcity of the workforce for farming. Extreme weather conditions, an inadequate supply and ineffective fertilizer application, infections, diseases, allergies, and other health issues brought on by chemical applications (fungicides, pesticides, insecticides, etc.) or insect or animal bites are additional issues or difficulties. Drones have shown to be one of the approaches that enable quick and non-destructive examination of the air quality, physical characteristics of the components of soil, or crop growth to address some of the difficulties faced in agriculture through the use of sustainable ICTs. As a result, farmers are turning to cutting-edge drone technology to solve these issues quickly and effectively. Drones can gather information on various topics, including crop yields, livestock health, soil quality, nutrient assessments, weather patterns, and rainfall totals. However, there is none of the literature focused on the advantages of drone usage among paddy farmers in Malaysia. Therefore, this research aims to identify the factors affecting Malaysian paddy farmers using drones. This research collects data from interviews with ten paddy farmers who own agriculture drones to accomplish this objective. The farmers have been selected from Tanjung Karang to Sabak Bernam, where paddy cultivation is encouraging, especially in Selangor, Malaysia. Government agencies can then utilize the information from this research and local authorities to map out any suggestions to paddy farmers on the advantages of using drones in paddy farming. Other than that, the government also can find out ways to help the y farmers in terms of finances to buy more drones.
Keywords:	Agriculture Drone, Spraying, Paddy Fields, DJI Drone, Paddy Farmers
Source:	Journal of Theoretical and Applied Information Technology 30^th April 2023 -- Vol. 101. No. 8-- 2023
Full Text