		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
October 2022 | Vol. 100 No.20

Title:	GAMIFICATION TO IMPROVE SCRUM ADOPTION: A CASE STUDY AT POULTRY STARTUP IN INDONESIA
Author:	AHMAD SYAIFULLOH IMRON, TEGUH RAHARJO, BOB HARDIAN, TIARMA SIMANUNGKALIT
Abstract:	Agile methodology offers software development flexibility to respond to changes quickly. Agile methods are better than traditional ones, especially in terms of reducing costs much more efficiently. One of the Agile approaches is Scrum which involves a small team to make a Sprint in the process. Agile and Scrum are not without gaps; there are challenges in adopting them. Among the challenges are poor communication, lack of team motivation, and lack of support from the senior development team. All of Scrum’s adaptation challenges stem from the human factor running it. Applying the concept of gamification in Scrum can address these challenges. Gamification can enrich non-gaming processes by making them more enjoyable and increasing the productivity of the development team. This study focuses on investigating the Scrum team at the poultry startup that applies the Scrum approach to adapting to changes quickly. Jira application is used to manage scrum within the company. Jira Software has “Trophies for Jira Dashboard” application for gamification implementation on the development team. The application of gamification will make the development team feel happy, like they are running a game in a work environment with healthy and fun competition. By implementing gamification, development team experiences personal growth, more motivation at work, increased efficiency, and early issue resolution, leading to improved productivity and enhancing agile success rate. As a result of this research, gamification process impacts 69% of Agile success, indicating that the company will have benefit by applying gamification without significantly increasing its costs.
Keywords:	Gamification, Agile, Scrum, Software Development, Poultry Industry, Startup.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	CRITICAL FAILURE FACTOR USING TOPSIS METHOD – A CASE STUDY OF AN INDONESIAN POULTRY AGROTECHNOLOGY STARTUP
Author:	RAHMI JULIANASARI, TEGUH RAHARJO, BOB HARDIAN, TIARMA SIMANUNGKALIT
Abstract:	CFF, Agile, Scrum, Agro Technology, Startup, TOPSIS Agile is viewed as a strategy to hasten the development of new products since it is flexible, practical, and cost-effective. The startup firm where the case study was conducted is a poultry retail agrotechnology startup. However, there are several difficulties in practice. One of the company's main products is IoT-based poultry technology solutions and livestock management software. The product development has been using Scrum since January 2022. However, there are still issues with the implementation, such as projects not being finished on schedule, workload being distributed unevenly, and incorrect documentation and reporting on team and company performance. Expectations for project completion might be as high as 80%. However, only 50% of projects are completed. The work process is still ineffective, especially when gathering requirements and reviewing products. The purpose of this research is to identify the critical failure factors that contribute to the failure of Scrum implementation in the company and provide a recommendation to be a strategy to improve Scrum implementation in the company to solve the issues. The TOPSIS approach was employed in the research. The lack of a complete set of agile practices, lack of project management capabilities, lack of agile progress tracking, the organization is too political, and lack of management commitment were the most relevant factors to the implementation failure. Resistance from groups or individuals, lack of customer relationships, and ill-defined customer roles are the ones that have the most negligible impact. Recommendations have been arranged for the company for a strategy to improve the implementation of Scrum.
Keywords:	CFF, Agile, Scrum, Agro Technology, Startup, TOPSIS
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	SVM TECHNOLOGY CLASSIFICATION FOR KNOWLEDGE MANAGEMENT AND CRS
Author:	ASMAE OURDI ABDELLATIF TAGHZOUTI, IKRAM BOUDALLAA, RACHID ELKACHRAD, ABDILLAH KADOURI
Abstract:	The method of support vector machines, also called large margin machines (SVM), is a derivative of computer learning, a solid theoretical basis different from its ancestor of neural networks. The SVM method is known as a very interesting advance in its principle, its implementation and its extension to multiclass problems. Over the past decade, research has focused on adapting the method to particular problems such as novelty detection and clustering as well as improving its performance (optimization and parallelization) and its application. in different domains. such as imaging, sound, banks, biology, management and knowledge management. As a result, several applications have experienced real success with the use of SVMs. In this article, we have highlighted in depth the correlation of SVMs especially on knowledge management as well as the companies implemented Corporate Social Responsibility (CRS). The purpose of the classification is to apply the variables according to the proposed method based on SVM improves the classification accuracy of the classifiers compared to the simple term-based data classification method in order to simplify and facilitate the decision making .
Keywords:	Support Vector Machine , Classification, Technology, Knowledge management and CRS
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	ENHANCED PARTICLE SWARM OPTIMIZATION BASED PILOT DESIGN WITH HYBRID BEAMFORMING POWER TRANSFER IN WSN-IOT APPLICATIONS
Author:	REGINALD JUDE SIXTUS J, TAMILARASI MUTHU
Abstract:	The major concern in IoT is that even if one of the sensors in the interconnection terminates connectivity due to its battery depletion, the whole IoT network suffers a failure. By employing a combination of novel techniques like simultaneous wireless information and power transfer (SWIPT) with non-orthogonal multiple access (NOMA) systems, achieving energy efficiency and spectrum efficiency become a reality without much complexity even with humongous users. Transmission power reduction in a multi-antenna wireless powered communication network (WPCN) using heterogeneous modulation schemes is investigated in this paper. A hybrid access point (H-AP), featuring several transmitters and receivers are utilized. In downstream, the H-AP transmits a power through power directional antennas which enhances the transmission efficiency. While transmitting the transmission power at the H-AP, the allocation time for downlink is determined to perform wireless energy transfer (WET). An innovative interference cancellation scheme using enhanced particle swarm optimization (PSO) algorithm is applied to avoid pilot allocation time for downlink is determined to perform wireless energy transfer (WET). An innovative interference cancellation scheme using enhanced particle swarm optimization (PSO) algorithm is applied to avoid pilot contamination. The proposed method is termed as PSO with hybrid beamforming power transfer (PSO-HBPT) and the parameters are validated. From the comparative analysis between the considered parameters it is observed that PSO-HBPT outperforms the existing, joint optimization sub-band expediency based Scheduling (JO-SES) method.
Keywords:	Enhanced particle swarm optimization, NOMA, SWIPT, hybrid access point
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	DETECTING ANOMALIES IN AOA DATA MEASURED FOR INDOOR POSITIONING TO IMPROVE ACCURACY
Author:	HYEONGSEOL SHIN, QIANFENG LIN, JOOYOUNG SON
Abstract:	Ships are made of steel. The space of ship’s environments is generally narrow. In the ship’s environments noises are included in the signal. Accurate indoor positioning technology can contribute to preventing infectious diseases by identifying and locating infected people at an early stage. As a method, this paper makes the Angle of Arrival using Bluetooth 5.1 to locate infected people. The function of Anomaly Detection methods as filters may be used to eliminate outliers in elevation and azimuth angles when measuring the Angle of Arrival. Three different Anomaly Detection methods are evaluated in this paper, they are Generalized Extreme Studentized Deviation, LevelShift, and Persist. As a result, LevelShift shows an improvement by 14% in Root Mean Square Error (RMSE) and Generalized Extreme Studentized Deviation shows by 5%. Persist, however, gets worse by 2%.
Keywords:	Indoor Positioning, Bluetooth 5.1, Angle of Arrival, Anomaly Detection
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	INFORMATION TECHNOLOGIES FOR VISUALIZATION OF DIAGNOSTIC RESULTS OF FUTURE ENGINEERS COMPETENCES IN MULTIDIMENSIONAL NON-METRIC SPACES
Author:	OLEKSII CHORNYI, LARYSA HERASYMENKO, LIUDMYLA HOLUBNYCHA, LIUDMYLA ZELENSKA, NATALIIA DZYNA, VALERII TYTIUK
Abstract:	The problem of using information technologies to visualize the results of diagnostics of professional competences development on the example of students of engineering specialties is topical. The purpose of the manuscript is to identify the possibilities of information technologies for data visualization in multidimensional non-metric spaces using the example of identifying the level of formation of individual competencies of future electrical engineers. Methods for achieving the stated purpose were the following: theoretical (analysis and synthesis) ones facilitated the development of the “Chernoff face” designer program based on the MATLAB software package; empirical (expert assessment and surveying) ones helped to identify criteria and means of diagnosing the formation of professional competencies and create the most optimal image of the “Chernoff faces”. The results revealed that in educational process visualization is capable of ensuring emotionality, ease and speed of perception of the necessary information by students; structuring data into a coherent image; analysing the visualized information according to specific criteria and indicators; demonstrating the relationships between the various analysed indicators; preventing information overload; supporting attention, activating thinking and memory. Moreover, various methods of visualizing the level of competence formation increase the effectiveness of the perception of diagnostic results and the possibility of adjusting educational and methodical trajectories. The authors have developed a designer program and have proposed fragments of the program code for creating “Chernoff faces” based on the MATLAB software package, which allow students to visualize the level of formation of professional competences and provide the possibility of developing a strategy for their improvement.
Keywords:	Visualization information technologies, Professional competences, Multidimensional non-metric space, Professional training of engineers
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	DO AGE AND GENDER AFFECT WILLINGNESS TO LEAVE REVIEWS ON E-COMMERCE PLATFORMS?
Author:	VINCENTIUS, VIANY UTAMI TJHIN
Abstract:	Product reviews play an important role where the buyer can express their honest opinion toward the product that the customer bought. Online reviews provide social proof to potential customers and gives them confidence to buy the products, where online reviews support customer purchasing decision. Surveys have shown that not all customers that bought products will review them, where most customers that didn’t leave a review says that they’re too lazy to review, too hard to use the feature and etc. This research aims to learn which factors influence the user to review the product they bought in E-commerce marketplace, where author will also try to see if gender and age will have a different opinion on motivating factors for leaving reviews. This research is quantitative research, where the factor used for the research is customer satisfaction, reward, motivation, and attitude. The research relies on a survey data from users that use top 3 marketplace in Indonesia and a structural equation modeling using SmartPLS 3. The result has shown that attitude and motivation have a positive and significant effect to influence users to leave reviews on the product they bought. Meanwhile, reward and customer satisfaction does not have a significant effect towards user Willingness to Leave Review. Results also shown that gender and age does not influence user Willingness to Leave Review.
Keywords:	E-commerce, Willingness, Online Reviews, Gender, Age, Marketplace
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	MARKETING STRATEGY WITH PATH ANALYSIS IN INCREASING COMPETITIVE ADVANTAGE IN TOURISM INDUSTRY SMES IN EAST JAVA
Author:	ADYA HERMAWATI , ABHIMANYU TUWUH SEMBHODO
Abstract:	This study aims to identify the marketing performance of the East Java tourism industry SMEs in particular related to the marketing strategy and model the determinants of the marketing success of the East Java tourism industry SMEs in the marketing strategy sector. This study uses quantitative analysis in the form of path with the analyzed data obtained from the results of the questionnaire. Data were obtained from 11 regions in East Java, 40 SMEs were taken from each region and 3 UKM employees were taken from each SME as research respondents. The results showed that the marketing strategy variables for the entire region in East Java, namely Spiritual Marketing (X1), Market Orientation (Y1) and Competitive Advantage (Y2) variables can significantly affect Marketing Performance (Y3). Knowing the influence of marketing strategy on marketing performance that can achieve better development and strengthening of tourism industry SMEs in East Java.
Keywords:	Competitive Advantage, Marketing Strategy, SMEs, Path, Tourism Industry
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	STEM LEARNING SYSTEM WITH THE INTERNET OF THINGS THROUGH CLOUD LEARNING TO DEVELOP THE DIGITAL LITERACY AND CREATIVE PRODUCTS OF HIGHER EDUCATION STUDENTS IN THE 21ST CENTURY
Author:	SUNTI SOPAPRADIT
Abstract:	This research aimed to study the demonstration of STEM Learning System with the Internet of Things through cloud learning in three different objectives: 1) a comparison of the ‘Digital Literacy’ scores of students before and after the class, 2) a comparison of the ‘Creative Product’ scores of students with the standard (60 percent), and 3) a comparison of the ‘Digital Literacy’ scores of students before class, after class and after taking a 1-month class. The target of this research was a group of students who registered for the ‘Embedded System and Application’ subject in the 1st semester of the academic year 2021. A class of students registered for the 16-week at Southeast Bangkok College. The measures used in this research were ‘Mean’, ‘Standard Deviation (S.D.)’, One Sample t-test, Paired Sample t-test, and One Way Repeated Measure ANOVA. The research findings revealed that 1) Students had a higher mean digital literacy score of 5.667 after the class compared with before, at a significance level of .05. 2) Students had a mean higher creative product score of 8.306 compared with the standard score at a significance level of .05. 3) Students had higher digital literacy scores after completing 1-month class and after class than before taking the class, at a significance level of .05
Keywords:	STEM, Internet of Things, Cloud Learning, Digital Literacy, Creative Product.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	A HYBRID APPROACH FOR OPTIMIZED VIDEO COMPRESSION USING DEEP RECURRENT AUTO ENCODERS (DRAE) TECHNIQUE
Author:	Mr. KOMMERLA SIVA KUMAR, Dr. P. BINDHU MADHAVI, Dr.K. JANAKI
Abstract:	Presently, the data traffic is increasing for video conferencing, online education, gaming and watching videos on Netflix, Amazon Prime, YouTube and other OTT platforms. And, the service users are always demanding high definition and high-quality video facilities day by day. However, in order to transmit video data across the Internet's constrained bandwidth effectively, video compression is a necessary task. In last few decades, various video compression algorithms, such as non-learning and learning were standardized. But still some improvements are needed for effective video related services. We propose a deep learning based Deep Recurrent Auto Encoders (DRAE) approach which contain various modules for implementing an efficient video compression technique. The experimental outcome shows our model achieves state-of-the-art learned video compression performance in terms of both PSNR and MS-SSIM.
Keywords:	Video, Compression, Deep Neural Networks, Recurrent Auto Encoders.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	HYPERPARAMETER OPTIMIZATION BASED DEEP LEARNING MODEL FOR MEDICAL DATA CLASSIFICATION IN INTERNET OF THINGS ENABLED CLOUD ENVIRONMENT
Author:	RAGUPATHI T, GOVINDARAJAN M, PRIYARADHIKADEVI T
Abstract:	Recently, the integration of internet of things (IoT) and advanced medicinal sensors can be contributed to improving the quality of healthcare services. In this way, the cloud and IoT technologies are completely utilized to design intelligent healthcare systems which can support real time applications by the use of artificial intelligence techniques. The recently developed deep learning (DL) approaches pave the way to design effective medical data classification models to diagnose diseases. With this motivation, this paper presents a new hyper parameter optimized DL technique for medical data classification in IoT enabled cloud environment. The proposed model enables the IoT devices to collect healthcare data and diagnose diseases in the cloud server. Primarily, the IoT devices are used for data acquisition and data preprocessing takes place to enhance the data quality. In addition, a convolutional neural network-long short term memory (CNN-BILSTM) method is employed for classification purposes, which identifies the presence of diseases or not. For boosting the classification performance of the CNN-BILSTM model, a black widow optimization (BWO) technique is applied to determine the optimal learning rate of the CNN-BILSTM model. A wide range of simulations take place on three benchmark medical datasets and the experimental results highlighted the promising efficiency of the proposed method over the other techniques.
Keywords:	Healthcare, Data classification, Cloud computing, IoT, Remote diagnosis, Deep learning, Learning Rate
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	DETECTION OF FAKE NEWS IN THE SPANISH LANGUAGE USING MACHINE LEARNING TECHNIQUES
Author:	SYOMIRA CHAMBI-APAZA, ROXANA FLORES-QUISPE
Abstract:	Nowadays, fake news has become a huge problem that causes damage around the world, especially in the social, political, and economic spheres. Due to the large amount of news generated every day, it is difficult to verify manually all the information to determine if a news item is real or fake. As a result, expert-based manual fact-checking, such as editors and journalists, need new tools that can perform the verification process efficiently. On the other hand, there are many studies focused on the detection of fake news in the English language, however, in the Spanish language, there are only a few researches that address this issue. For that reason, this proposed research explores different machine learning techniques to detect fake news in the Spanish language considering three feature extraction techniques: TF, TF-IDF, and Count Vectorizer; and five machine learning techniques: Logistic Regression, Stochastic Gradient Descent, Gradient Boosting, Random Forest and Support Vector Machine, were investigated and compared between them in order to achieve the classification task. Finally, the experimental results show the best performance with an accuracy rate of 87.18% using Random Forest as a classifier and TF as a feature extractor.
Keywords:	Fake News, Automatic Detection, News Verification, Disinformation, Machine Learning.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	EXPLORING AUDIO CHAT-IN APPLICATION INFLUENCE FACTOR USING MODIFIED TECHNOLOGY ACCEPTANCE MODEL: THE CASE OF CLUBHOUSE IN INDONESIA
Author:	KEVIN BUDIMAN, SFENRIANTO
Abstract:	The rapid advancement of technology has not only improved the quality of people's lives but has also changed how we communicate with each other. During this COVID-19 Pandemic, a new social media emerged and revolutionized how to communicate during this pandemic with the theme of a concept like "Podcast" named Clubhouse. The use of clubhouses, which has experienced a rapid increase, has created a new trend phenomenon that has caused Clubhouses to become a topic of conversation. However, there aren’t many research that uses Clubhouse as its subjects. This study was conducted to find out which factors that ultimately affect the acceptance of Clubhouse applications which taken with the background of rapidly increase of popularity of the application. This study is uniquely researched by combining Trend and Experiences as its external variables which combined with a TAM model that’s been modified. Research conducted on 100 respondents using Modified TAM as its model framework. Based on the analysis, it is found that Trend, Experience, Perceived Ease of Use, and Perceived Usefulness are the factors that affect Clubhouse application acceptance.
Keywords:	Social Media, Technology, Application, TAM, Clubhouse
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	MULTICAST PROTECTION WITH GROOMING BACKUP PATH IN ELASTIC OPTICAL NETWORK
Author:	BODJRE AKA HUGUES FELIX, ADEPO JOEL, KEUPONDJO SATCHOU GILLES ARMEL, COULIBALY ADAMA, BABRI MICHEL
Abstract:	The protection of connections in very high-speed networks such as elastic optical networks is an effective solution to limit the damage due to failures on the links in the network. We have therefore proposed a protection approach that uses backup path bundling to solve the problem of protection with connection bundling in EONs. The proposed algorithm makes it possible to build the primary path and the backup path of the connections by grooming the primary and backup paths which share links in common. Thus, this algorithm reduces the resources used such as spectral resources and transponders. The simulation results reveal that the proposed approach yields better performance in terms of blocking probability, transponder cost and spectrum utilization rate compared to the shared protection method without connection bundling.
Keywords:	Multicast, Shared Protection, traffic Grooming, Elastic Optical Networks
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	FACTORS AFFECTING THE USE OF YOUTUBE AS A MEDIA SUPPORTING STUDENT LEARNING PERFORMANCE
Author:	YULIUS YUS, RIYANTO JAYADI
Abstract:	The purpose of this study was to determine whether using YouTube as a medium to support student learning can improve learning performance by identifying the factors that encourage students to use YouTube as a medium to support learning. Therefore, this research was conducted by combining the Technology Acceptance Model (TAM) and the Unified Theory of Acceptance and Use of Technology (UTAUT). This research was conducted using a survey method. This research was conducted on 906 respondents, with results showing that YouTube's perceived ease of use has a significant positive effect on perceived usefulness, YouTube's perceived ease of use has a significant positive effect on intent to learn, YouTube perceived ease of use has no effect on actual learning, perceived usefulness a significant positive effect on the intention to learn, perceived usefulness has a significant positive effect on actual learning, facilitating conditions have a significant positive effect on the intention to learn, intention to learn has a significant positive effect on actual learning, self-control has a significant positive effect on actual learning, and actual learning has a significant positive effect on significant positive on learning performance. The results of this study add to current knowledge about the importance of using YouTube as a medium to support student learning. Teachers can also use this to develop appropriate strategies to improve the quality of student learning with the support of learning media such as Youtube.
Keywords:	Learning Performance, YouTube, TAM, UTAUT
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	CHATBOT-SUPPORTED SMART LEARNING: ALGORITHMS AND IMPLEMENTATION
Author:	DALIA KHAIRY , MARWA F. AREED , MOHAMED A. AMASHA, SALEM ALKHALAF, RANIA A. ABOUGALALA
Abstract:	Recently, increasing numbers of chatbots have been used in diverse fields, using various languages and technologies. Designing an interactive smart chatbot based on query-response systems in education has emerged as an important challenge in managing online discussion with natural language. This paper presents the SCBHE, which can receive queries from students and deliver responses about educational and administrative support to improve communication and services while decreasing the huge workload in universities. The SCBHE depends on identifying students’ intents and extracting contextual information to deliver appropriate responses to students’ queries, the framework will assist with decreasing the work burden, as educators will no longer need to repeatedly answer the same questions and explain the same points to various students. The SCBHE was built based on Dialogflow, an artificial intelligence tool introduced by Google. The chatbot was developed using an algorithm with the eight following phases: GUI development, acquisition, preprocessing, extraction, response induction, updating, awareness , and authentication. In this study, handling the SCBHE context information is limited to implementing the first five phases of the proposed algorithm.
Keywords:	Educational Robotics, Artificial Intelligence, Context-aware Technology, E-learning.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	ANALYSIS OF THE EFFECT OF FEATURE SELECTION ON THE HANDWRITING AUTHENTICITY CHECKING SYSTEM THROUGH FISHER SCORE AND LEARNING VECTOR QUANTIZATION
Author:	DIAN PRATIWI, SYAFUDIN, TRUBUS RAHARDIANSYAH, MUHAMMAD ICHSAN, STEVEN SEN, AHMAD FAUZY
Abstract:	Handwriting is part of the authentic form that everyone has. The authenticity of the owner is often difficult to prove because it is easier to fake with the support of technology. This research was then carried out to develop a method to help verify the authenticity of the owner's handwriting, by applying the LVQ method and selecting the Fisher Score feature to analyze the use of the best number and types of features. The steps taken include processing the grayscale color and data size into 500x200 pixels, then segmentation, taking the features of the writing area based on the mean, variance, entropy, energy and contrast values. The feature is then analyzed by Fisher Score for each use of the feature with the highest score, and tested with LVQ to predict the owner of the article. From the test results, it is found that the use of a large number of features in the order of Fisher's highest score, the quality of accuracy is better than the use of a small number of features
Keywords:	Contrast, Energy, Indexing, Mean, Scoring
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	PUBLIC OPINION, CLUSTERS, AND STATISTICS OF COVID-19 VACCINATION: A TWITTER ANALYSIS
Author:	GHADA AMOUDI, ZELAL SHEARAH
Abstract:	The coronavirus disease (COVID-19) pandemic has drastically affected the entire world. Vaccinations have been developed to contain the spread of the virus and help humanity recover from the pandemic. However, people are often reluctant to adopt new medical interventions, and COVID-19 vaccines are no exception. Social media platforms like Twitter are flooded with discussions, opinions, and rumors about vaccines. Numerous people access news regarding COVID-19 vaccines on Twitter—rather than through official media channels—which offers a wealth of comments about news and medical breakthroughs. However, as people are panicked due to this alarming situation, they tend to share any information they receive without checking its credibility, creating more panic. Analyzing interaction between social media users provides insight into the spreading pattern of news, people's opinions towards a particular issue, who the influencers are, and how they influence others, among other findings. This study investigated opinions about COVID-19 vaccines by applying sentiment analysis and detecting communities on Twitter. We constructed an interaction network of discussions related to COVID-19 vaccines and applied social network analysis methods to find communities and nodes with high centrality measures. Next, we analyzed how these nodes affect the overall community opinion. Two main communities were detected, with the larger community displaying a higher positive sentiment ratio than the smaller one. Furthermore, the polarity of the high centrality nodes in each community was close to the average polarity of the community as a whole. These findings highlight the potency of the node's position in terms of centrality measures. In conclusion, analyzing discussion networks should not be overlooked when public health is concerned, as influencers are not necessarily those with high numbers of followers but rather those with high centrality measures within the interaction network regarding the topic being discussed.
Keywords:	Community Detection, Girvan–Newman, Sentiment Analysis, Centrality, Betweenness
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	INVESTIGATING TRUST IN MOBILE PAYMENT SERVICES IN INDIA: THE MODERATING ROLE OF GENDER
Author:	SUMEDHA CHAUHAN, POONAM KUMAR, YUVRAJ GAJPAL, LUVAI MOTIWALLA
Abstract:	The mobile payment (m-payment) services have enabled the users to make payment using mobile devices anytime and anywhere. There is a dearth of research that establishes an integrated model for investigating the factors influencing trust in m-payment services and the impact of trust on the behavioural intention to use m-payment services in India. Present study attempts to fulfil these gaps and takes a step further to identify how gender differences affect the relationship of different factors with trust in m-payment services. Survey data was collected from 373 individuals in India and analysed using the SmartPLS 3 software. Results show a positive influence of mobility, social influence, and reputation, while a negative effect of perceived risk on trust in m-payment services. Additionally, multigroup analysis uncovered that men are more influenced by mobility and reputation, while women are more affected by social influence and perceived risk. The outcomes of present study will help m-payment service providers to better understand the factors that should receive the most attention to ensure that customers trust the m-payment service. The study also enables them to appreciate how gender differences affect trust in m-payment services.
Keywords:	Mobile payment, Trust, Gender, Structural Equation Modelling, India.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	A SYSTEMATIC STUDY ON SUGGESTION MINING FROM OPINION REVIEWS
Author:	NAVEEN KUMAR LASKARI, SURESH KUMAR SANAMPUDI
Abstract:	Online product reviews have become eminent in the purchase decision-making process. With progress in web 2.0 technologies, huge volumes of unstructured text data are generated as reviews on e-commerce platforms and third-party web portals. Opinion review mining has become a critical area of research in language processing and applied machine learning. Opinion reviews available across various portals are perceived primarily to understand the sentiment polarity expressed by the reviewer at multiple granularities. The opinion review may also contain suggestions or tips for manufacturers and peer customers. Suggestion Mining refers to the automatic extraction of suggestions from opinionated text. The applications include product quality improvement, peer customer suggestions, summarizing collected surveys and feedback, a recommender system, and enhancing sentiment polarity classification. Suggestion mining is considered a sentence classification task, such as classifying a given review as suggestive intent or not. Various linguistic, syntactic, and semantic features with core machine learning and neural network approaches are used for suggestion mining. This paper presents a comprehensive and systematic review of suggestion mining from opinion reviews and their facets in the literature
Keywords:	Suggestion Mining, Word Embedding, Deep Learning, Opinion Reviews.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	A MODEL FOR SUPPLIER SELECTION IN MANUFACTURING INDUSTRIES
Author:	SOUMIA TABIT, AZIZ SOULHI
Abstract:	The success of a company depends on its ability to manage its supply chain. Moreover, the consumer demands and the fierce competition existing in local and international markets have pushed companies to focus on their relationships with their suppliers. The choice of the latter (suppliers) is a major stake in the supply chain and represents a key step, which can strongly impact the global performance of the company. The goal of this research is to develop a decision support model that allows companies to identify the most appropriate suppliers for their business. This model considers the various decision criteria and then ranks the suppliers according to their output indicator. For the validation of this proposed model, an experimental study was conducted to rank (03) suppliers available on the market related to the delivery of raw material for the case of a company manufacturing plastic products. The proposed model meets the desired objective and is therefore retained for the selection of the best supplier in a certain/uncertain multi-attribute and multi-actor context.
Keywords:	Supply chain, Supplier, Fuzzy logic, Global performance , decision support.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	TRACKING PEOPLE IN CLOSED SPACES TO LINK WITH METAVERSE
Author:	RODOLFO ROMERO-HERRERA, JONATHAN AXEL CRUZ VÁZQUEZ, JESÚS YALJA MONTIEL PÉREZ
Abstract:	The need to know the location and track people has become an important aspect of our daily lives, and although the global position system (GPS) has dominated outdoor location, in terms of indoor signal it is blocked and distorted by buildings, which affects its performance. Much of the technology that has emerged makes use of location, such are the applications that you have to do with the internet of things (IoT). In this work, an indoor people tracking system is proposed using the inertial navigation method to access different areas. Through an IMU device, the values of its sensors are obtained, which are transmitted to a computer in a virtual world, and the location of the person inside a building is disclosed. Thus, communication is established between the real world and a metaverse. Where movements of a person are represented in a virtual world.
Keywords:	RFID, Location, Inertial Navigation, IMU, Metaverse.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	E-COMMERCE CUSTOMERS OPINION PREDICTION ON MULTIPOLARITY WORDS WITH RULE BASED CLASSIFICATION TECHNIQUE
Author:	A. AL FIRTHOUS, P.ARUL
Abstract:	The foremost goal of this research is to analyze the reviews of E-Commerce products using Social Media Big Data using proposed Rule Based Classification Technique. This proposed work is about evaluating customer’s Tweets about Amazon products. Customer’s Tweets may vary according to the person’s taste and style. And Amazon reviews presented in the website is very huge this is making it impossible for customers to discover about product reaction. This issue is addressed in the proposed approach, which involves undertaking opinion mining across numerous social networks. Its goal is to gather reviews from Twitter in order to scrutinize Amazon product sentiment. And it delivers useful information to online shopping customers about product worth, as well as valuable decision-making thoughts to businesses about the customer’s favorite for and buys products. This work take into account of various kinds of opinion words found in tweets, such as capitalized words, repeated letter sequences, negation words, modifier items, emoji, intensifiers, slang terms, conjunction words and exclamatory words. This proposed work integrated the five kinds of sentiment or lexicon dictionary. This kind of amalgamation can reduce the lacking of opinion words, and also can avoid the missing polarity value.
Keywords:	Opinion Mining, Analysis, Prediction, Classification, Amazon, Products
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	A REVIEW OF COMMUNICATION PROTOCOLS IN POWER SYSTEMS
Author:	ANDRÉS FELIPE RODRÍGUEZ AYALA, DANIELA JOHANNA ROJAS MARTÍNEZ, DIEGO ARMANDO GIRAL-RAMÍREZ
Abstract:	The objective of this article is to present a review of the communication protocols implemented for the power system. Communication protocols arise with the need to be able to perform immediate communication between one or several sectors of the system, in order to minimize possible failures that may occur along this, in addition to sending orders and signals that decrease manual operability, giving way to automatic control that aims to manipulate the largest amount of information remotely. The protocols shown here are intended to make known how new technologies have come to stay, but these will take time to implement, this is mainly due to the poor infrastructure conditions of the power system. Finally, it delves into new communication protocols opening up new and future ways of controlling the electrical power system
Keywords:	Automatic Control, Communication Protocols, Power System, Internet of Things
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	A COMPARATIVE STUDY ON MACHINE LEARNING AND DEEP LEARNING METHODS FOR MALWARE DETECTION
Author:	ESLAVATH RAVI, MUMMADI UPENDRA KUMAR
Abstract:	The advent of Artificial Intelligence (AI) and data science with Machine Learning (ML) and deep learning techniques has paved way for solving many real world problems. Malware detection is one such problem that is solved with AI based solutions. Malicious code that comes through genuine software components or through storage media and networks is termed as malware. This paper has made a reviews of literature for ascertaining the current academic thinking and the methods being used or methods possible to detect malware automatically. The study in this paper is divided into three categories known as ML methods for malware detection, deep learning methods for malware detection and optimization methods for improving malware prediction performance. Each category is summarized to have most useful insights. It covers malware research with various datasets available including Android apps based datasets. It has brief discussion on ML and deep learning methods along with their methodology. The insights of this paper provide good understanding on different methods existing, their approach, datasets collected and used besides evaluation metrics. These insights along with the proposed framework and experimental results can trigger further research with specific possibilities in future. Since the dataset utilized in this paper has more number of attributes the survey has identified that deep learning based approaches has more efficiency rather than the ML approaches. The integration of deep learning approaches with optimization techniques has enhanced the utilization of resources.
Keywords:	Malicious Code Detection, Malware Detection, Machine Learning, Deep Learning, Malware Detection Optimization
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	THE IMPACT OF FACTORS OF AFFECTING MOBILE COMMERCE USER SATISFACTION TO IMPROVE CUSTOMER ENGAGEMENT
Author:	ALBERT HALOHO, RIYANTO JAYADI
Abstract:	Competition for customer engagement is an important part of the company's long-term competitive advantage. User satisfaction in using mobile commerce is one of the determining factors in increasing customer engagement. Therefore, it is necessary to know other factors that influence user satisfaction by conducting an analysis of the survey of each factor that has a significant influence. The sample will consist of 400 respondents and will be analyzed with a model designed based on these factors. It is very important for companies to increase their customer engagement through user satisfaction in mobile commerce. This research found that trust, innovativeness, mobility, perceived enjoyment, involvement, service quality, perceived usefulness, experience has significantly affected mobile commerce user satisfaction. But for social influences and perceived ease of use not significantly affecting mobile commerce user satisfaction to improve customer engagement in Greater Jakarta area of Indonesia.
Keywords:	Mobile Commerce Applications, Customer Engagement, User Satisfaction, Perceived Usefulness, Perceived Ease of Use, Experience.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	A FRAMEWORK FOR PREDICTION BANKING RISK USING MACHINE LEARNING TECHNIQUES
Author:	ASMAA SAEED EMBARK, RIHAM Y. HAGGAG, SAMIR ABOUL FOTOUH SALEH
Abstract:	One of the main challenges facing the banks is to determine the proper bank liquidity. Risk differs widely from bank to bank, and a Careful understanding of various risk factors assists predict the likelihood of expected liquidity based on historical data, Real-world datasets often have missing values, which can cause bias in results. the most widely adopted method for dealing with missing data is to delete observations having missing values, these methods have the disadvantages represented in loss of precision and biased. The purpose of this study is to forecast banks' liquidity risk. We also present a method for dealing with missing data using powerful machine learning methods. we Used available datasets through Kaggle there are 350 cases and 19 characteristics in this dataset. SPSS and the WEKA tool were used to analyze the data. ROC and accuracy were used to assess and compare three classification models (Decision Tree, Support Vector Machine (SVM), and random forest ). Results showed that the model obtained acceptably, results The 66-fold( 97.47, 97.47, 97.47) respectively (DT, SVM, RF) the best accuracy among from 10-fold.
Keywords:	Liquidity Risk; Machine Learning; Decision Trees; Support Vectors; Random Forests; Missing Data
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	SQUIRREL SEARCH-BASED OPTIMAL FEATURE EXTRACTION WITH BI-LSTM FOR THE ARRHYTHMIA CLASSIFICATION USING ECG
Author:	SHAIK MUNAWAR, GEETHA A, SRINIVAS KONDA
Abstract:	Electrocardiogram (ECG) arrhythmia classification seeks more attention in the research areas for preventing and diagnosing cardiovascular diseases. The conventional approaches related to arrhythmia classification have achieved reasonable performance on the detection of diverse heart scenarios particularly when processing with the imbalanced datasets. Recently, deep learning shows an enhanced performance in the area of healthcare industry for extracting the high level of abstract features in an automatic way to reduce time consumption and avoid manual effort. Many researchers have developed deep learning-aided methods for detecting the arrhythmia with the help of ECG signals; however, it fails to ensure the accurate classification. Hence, this paper plans to develop the arrhythmia classification using ECG signals by the intelligent technology. Initially, the data is gathered from online sources. The gathered data undergo pre-processing using noise removal, artifacts removal, and peak detection techniques. From the pre processed signals, the features are extracted using the “Mel Frequency Cepstral Coefficients (MFCC), spectral features, and Short Time Fourier Transform (STFT)”. As the extracted feature length is lengthy, significant features are extracted in the optimal feature extraction step using the Squirrel Search Algorithm (SSA). These optimally extracted features are given to the final classification step, where “Bi-directional Long Short Term Memory (Bi LSTM)” classify the heartbeats in a more efficient and accurate manner into 5 prominent classes such as “Normal Sinus Rhythm (N), Left Bundle Branch Block (LBBB or L), Right Bundle Branch Block (RBBB or R), Premature Ventricular Contraction (V), and Atrial Premature Beat (A)” that determines the types of arrhythmia present. The comparison illustrates the success of the proposed ECG classification model.
Keywords:	Electrocardiogram; Arrhythmia Classification; Mel Frequency Cepstral Coefficients; Spectral Features; Short Time Fourier Transform; Optimal Feature Selection; Squirrel Search Algorithm; Bi-directional Long Short Term Memory
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	BONE ABNORMALITIES DETECTION AND CLASSIFICATION USING DEEP LEARNING-VGG16 ALGORITHM
Author:	ALAA M. A. BARHOOM, MOHAMMED RASHEED J. AL-HIEALY, SAMY S. ABU-NASER
Abstract:	Bones are both strong and flexible tissue made up of collagen and calcium phosphate. They mainly contribute to the movement of the human body and also serve as a protective shield for the body's soft organs such as the heart, lungs, and brain. Without them, the human body would not be built to function normally. But sometimes, due to various accidents, a person is exposed to some diseases such as infection or injury, which lead to defects in normal growth and shape of bone structure. This defect in the bone structure is called bone abnormalities, which increase the risk of fractures, cause chronic pain or disability, and in some cases, the risk of death if not diagnosed in a timely, accurate and quick manner so that the specialists make the right decision to treat the patient. Often, the initial diagnosis of bone abnormalities is made by doctors and specialists using X-rays of the patient's complaint and the injury site to show the X-ray of the shape and density of the bones, then they are classified into normal or abnormal. Detection and classification depend on experience and human effort, so the error in the results of this process can expose the patient to a great danger and catastrophe of his life. Therefore, deep learning algorithms from artificial intelligence and machine learning science were applied to help specialists avoid wrong or inaccurate diagnoses when detecting bone abnormalities in X-ray images by using a pre-trained convolutional neural network called VGG16. The model was customized to fit the bone abnormalities classification then applied to a dataset consisting of 42000 X-rays of the upper bones of some patients collected from Kaggle depository called Mura-v1.1. We trained, validated, and tested the modified VGG16 model. The proposed VGG16 mode obtained Precision (85.96%), Recall (85.82%) and F1-Score (85.77%).
Keywords:	Bone Abnormalities, Deep Learning, VGG16
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	GENERATION OF MATHEMATICAL MODELS OF LINEAR DYNAMIC SYSTEMS DESCRIBED BY BLOCK DIAGRAMS
Author:	MIKHAIL SIMONOV, KONSTANTIN ZAYTSEV, NATALYA POPOVA
Abstract:	The purpose of the study is to develop a method for calculating the mathematical models of block diagrams in the form of equations in a state-space representation. The model is calculated through an iterative process. The initial condition of the mathematical model is taken as a model consisting of unconnected elements of the block diagram. The hierarchy of elements, in general, is not set and is arbitrary, but remains unchanged throughout the computation. The iterative process is composed of steps, each of which processes one connection. The connection bridges the output and input ports of the element(s) in the block diagram. It is helpful (for example, to obtain the matrix frequency response of the system) to implement an algorithm for calculating the current connection without excluding and without zeroing the rows and columns of the equation-of-state matrices corresponding to this connection. This corresponds to a derivation of an equivalent model of a block diagram with input ports accessible for signal input and output ports of all elements composing the block diagram being open for observation. In this case, the definition of indexes at all steps of the algorithm remains the same as at step zero. The paper demonstrates that if a linear dynamic system contains a solvable system of algebraic loops, the mathematical model of a said dynamic system can be obtained as equations of state. In this case, the condition is derived, under which the system of algebraic loops can be solvable, and then the mathematical model of the block diagram can be obtained. If this condition is not met, the block diagram is to be rebuilt. The paper provides an example of step-by-step construction of a control system model defined by a block diagram and a class diagram of a system defined by a block diagram.
Keywords:	Mathematical Model, Block Diagram, Algebraic Loop, Object-Oriented Development.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	EEG SIGNAL ANALYSIS FOR MENTAL STRESS CLASSIFICATION: A REVIEW
Author:	ALI NIRABI, FARIDAH ABD RAHMAN, MOHAMED HADI HABAEBI, KHAIRUL AZAMI SIDEK, SITI HAJAR YUSOFF
Abstract:	Mental stress has been considered an important issue nowadays. Prolonged stress may lead to many severe diseases like heart attack, diabetes, possible sudden death and mental disorder. The traditional technique of clinical detection and monitoring the stress are mainly based on questionnaires and interviews. However, due to their limitations and data handling obstacles, it is highly needed for more advanced techniques. Recently, many studies have focused to classify mental stress using physiological signals such as heart activity, brain activity, muscle activity, speech, and facial expressions. One way to collect the data from brain activity is using a non-invasive device named Electroencephalograph (EEG). This paper gives a brief introduction of EEG, followed by a comprehensive analysis of artifacts and their removal techniques. Two types of artifacts in EEG and their removal methods are being discussed along with the challenges, advantages, and different obstacles being faced by the experts. The possible machine learning (ML) and deep learning (DL) models for mental stress classification are also discussed. Further, future direction on the possible methods to enhance the accuracy of stress detection is discussed.
Keywords:	EEG Signals, Classification, Mental Stress, Machine learning, Deep learning
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	AGROTECHNOLOGY SYSTEMS BASED ON INTERNET OF THINGS
Author:	AHMAD NURUL FAJAR, RIYANTO JAYADI, ASTARI RETNOWARDHANI, JAYADI HALIM, BILLY ROBERTSION , SANTONY DYAZ
Abstract:	The use of IoT can realize precision farming ,which means through the use of sensors that are applied to several planting media or agricultural land that allows users to get detailed information about light levels at any given time. In this study is we proposed an agrotechnology system using internet of things and mobile application development, which is called AGROTECHFARM Systems. Its can help the productivity of crop planting. The research methodology consists of several stages such as: requirement analysis, systems design, and development. First stage was conducted by collecting system requirements data through interviews. In this stage, we analyze user rand system requirement for AGROTECHFARM systems. Second stage we used UML to design AGROTECHFARM systems. Third stage is build and implementation AGROTECHFARM systems. .The results of this study is implementation AGROTECHFARM systems in hydroponics, Indoor, and Outdoor planting. It can be used for urban agricultural community. Besides that, the impact of AGROTECHFARM systems is can help users to controlling plant maintenance. We proposed IOT sensors for support and monitoring the status of the planting growth.
Keywords:	AGROTECHFARM Systems, IOT, Hydroponics, Indoor, Outdoor, Planting
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	UTILIZING DATA FRAMEWORK TO SUPPORT DECISION MAKING PROCESS WITH ENTERPRISE ARCHITECTURE APPROACH BY USING TOGAF FRAMEWORK
Author:	YULYANTY CHANDRA, NILO LEGOWO
Abstract:	A university needs to attach importance ingredients to the development of its institution in making many changes and intensively making innovations to find the right information technology that is educational and useful for education in the future, also expected to continue to develop through various periods of change at the forefront in the field of information technology, and always produce graduates who are ready to enter the competition in a society and be able to have a best quality of education. A university's commitment to improve the quality has pushed to implement a quality management system to maintain the overall education program that has been built. With strategic planning and university business management processes, designing an Enterprise Architecture (EA) as an architectural basic for providing data for the analysis of university management conditions by using big data technology and data analytics, so the information can support rapid decision-making process in business management. As we know, the world of technology in education always brings up its latest innovations and requires additional competent human resources to be able to help the management process to run in accordance with the vision and mission of the university. This study uses TOGAF (The Open Group Architecture Framework) which already developed by The Open Group Architecture framework in 1995, which helps to make an information system strategic plan with the aim to align between the vision and mission to improve service efficiency and support the organization's strategic plan. TOGAF is a complex framework that is capable of meeting all needs in the development of EAs, because it’s involved the design, implementation, scheduling, governance of enterprise information architecture, to detail the needs of enterprise architecture from the university, with the highest goal of this research is to produce Enterprise Architecture design and management blueprints. After the process of the Enterprise Architecture, the final decision is to help the top management to analyze and forecast the whole university data in a real time and helps to coordinate all division that involved the final decision-making process.
Keywords:	Enterprise Architecture, TOGAF Framework, Data, Support Decision Making Support, Strategic Planning.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	HARMLESS CYBERSTALKING, CASE OF ONLINE DATERS
Author:	LIANA WIJAYA, EKA UTARI TAIWANELLA, RAMANDA ANUGRAH AFRIANTO, ENGKOS ACHMAD KUNCORO, Z. HIDAYAT
Abstract:	With the growth in using social media and online dating sites from the effect of the pandemic in 2021, this research focuses on how cyberstalking occurs as a result of using online dating sites. While cyberstalking is perceived as a crime, this research intended to discuss a 'harmless' cyberstalking, which means seeking information about the other person from their social media sites or even using the google search engine without the acknowledgement of the other party. There were 347 (n= 264) participants that were requested to fill up a survey, which this study revealed that people cyberstalk as one of the strategies to reduce uncertainty about their matches. The reasons behind why people choose to use uncertainty reduction strategies are as the cause of concerns (warranty, personal security and misrepresentations) cause, looking for homophily and also goals from using online dating sites. The results has shown that people do cyberstalk harmlessly from the cause of the concerns behind warranty, personal security and misrepresentation of the other party, also as a cause of looking for homophily in matches, and there is no correlation behind the goals of using online-dating apps with uncertainty-reduction strategy.
Keywords:	Computer Mediated Communication (CMC), Cyberstalking, Social Media, Online-dating, Uncertainty Reduction
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	ARABIC QUESTIONS CLASSIFICATION MACHINE LEARNING ALGORITIMS
Author:	RAMI MALKAWI, SAJA ALSRAHAN, AHMAD A. SAIFAN
Abstract:	With the increasing volume of data on the web, the user needs a fast, accurate and directly access to information and quick responses to his/her questions. This led to motivating the authors of this paper to adopt the idea of Question Answering Systems; these systems depend widely on the language. There are many research studies have been conducted focusing on the English and Latin languages. However, number of studies related to the Arabic language is very limited and it still needs to more enhancements. Question Answering Systems consist of three main modules (Question Pre-processing, Document Processing and Answer Processing). Question preprocessing form is considered as an important phase on the overall Question Answering Systems because it plays a main role in identifying the question class which effects on the detection of a candidate answer. Within this research study, the focus was on identifying the Arabic question class based on an Arabic taxonomy and building a model for classifying the Arabic question using machine learning algorithms such as Support Vector Machine, Naive Bayes, and Logistic Regression., with an attempt to build a Named Entity Recognition model for Arabic language. Although, the results were not as good as expected, however there is a chance to improve the results in future. The outcomes of the experiment were as follows: logistic regression achieved the highest accuracy 82%, linear SVM 81% and Multinomial 79%.
Keywords:	Question Classification, Arabic QA Systems, Arabic Question Classification, Machine Learning.
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text

Title:	INFORMATION SYSTEM RISK MANAGAMENT WITH OCTAVE ALEGRO AT ED-TECH COMPANY (PT RAKAMIN KOLEKTIF MADANI CASE STUDY)
Author:	INTAN BEREANI WIGUNA, JAROT S. SUROSO, SANDY ANUGERAH
Abstract:	Today, various areas of business depend on information systems. The more sophisticated the technology, the more diverse the data collected to help business processes. However, as technology develops, there are also information system security risks that must be a concern. Therefore, various areas of the company need to mitigate to overcome possible security problems that arise. One of the fields of business that currently uses information systems to assist its business processes is education. Many education technology companies create educational platforms in their business processes. As the number of students increases, there needs to be a qualified risk assessment. One of the common methods is using OCTAVE Allegro is a method that helps organizations to detect risks and make decisions.
Keywords:	OCTAVE Allegro, Risk Assessment, Information Security, Risk
Source:	Journal of Theoretical and Applied Information Technology 31^st October 2022 -- Vol. 100. No. 20-- 2022
Full Text