		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 Informtion Technology
December 2021 | Vol. 99 No.23

Title:	THE BEST METHOD OF MUSIC RECOMMENDATION SYSTEM
Author:	ZANI CEMPAKA SARI, MARCELLA MARELLA CIPUTRI, STEFANNY SUSILO
Abstract:	The discussion in this paper is about music applications. The development of music applications that have many features, especially the music recommendation system. In this paper, we will compare several methods that can be used in forming a music recommendation feature and the best method will be determined. The methods we have picked have their own advantages and disadvantages. With this comparison, the best method we get is to use the Collaborative Filtering method.
Keywords:	Music Recommendation System, Recommender System, Collaborative Learning, Item-Based Method, User-Based Method
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	DEVELOPMENT OF PATH ANALYSIS BASED ON NONPARAMETRIC REGRESSION
Author:	FATHIYATUL LAILI NUR RASYIDAH , ADJI ACHMAD RINALDO FERNANDES , ATIEK IRIANY , SOLIMUN, NI WAYAN SURYA WARDHANI
Abstract:	This study aims to develop a robust nonparametric regression-based path analysis with the assumption of linearity. This study used a multivariate approach, namely nonparametric path analysis. The conclusion that can be obtained is that the properties of the spline estimator in Nonparametric Regression-Based Path Analysis using the PWLS approach, hypothesis testing on each relationship between variables in Nonparametric Regression-Based Path Analysis using the PWLS approach, as well as several findings regarding confidence intervals. The novelty of this research is to describe the estimation of nonparametric path analysis parameters through lemmas and theorems.
Keywords:	Path Analysis, Spline, Nonparametric, Regression, Penalized Weighted Least Square
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	RECOMMENDATION OF A LIST OF ITEMS OF SEARCH RETRIEVAL FOR USER’S INTENT
Author:	SALMA GAOU, MOURAD ELOUALI, KHALID AKHLIL, HICHAM TRIBAK
Abstract:	Information retrieval systems aim to generate Search Engine Results Pages (SERP), which are web pages automatically generated by a search engine according to the keywords entered by the net surfers. The results are presented in a list where the most relevant data from the search engine are at the top. The main challenge about Information retrieval Systems is the gap between the intent of the Internet user and the appropriate keywords in their disposal. The emergence of such systems is motivated by the need of precise information and they may be different from Internet search engines like Google or Yahoo! WikiAnswers, Answers and domain-specific forums like Stack Overflow, on certain specific points. Although the idea of receiving a direct and targeted response to an issue seems very attractive and the quality of the question itself can have a significant effect on the likelihood of obtaining useful responses. Such an information retrieval paradigm is particularly appealing when the problem cannot be answered directly by the search engines due to the unavailability of relevant online content. A good understanding of the underlying purpose of an issue is important to better meet the information needed by the user. In this paper, we propose a new approach to detect the user's intent. This approach is based on the method of the recommendation of a list of items but without calculation of prediction. The method lies on the co-dissimilarity and the tree covering minimum weight based on the theory of graphs. Our approach improves the ranking of a website in organic search results to increase visibility and quality.
Keywords:	Search engine optimisation (SEO), intent User, Information search, Ranking of search results, search retrieval
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	DESIGN AND IMPLEMENTATION OF A SECURE AND AUTONOMOUS WEB SERVER USING FPGA FOR REMOTE CONTROL OF INTELLIGENT SENSORS
Author:	KHAMLICH FATHALLAH, EL GHOLAMI KHALID, KHAMLICH SALAHEDDINE, EL JOURMI MOHAMMED, BENRABH MOHAMED
Abstract:	This paper introduces the design and implementation of an FPGA-based webserver to communicate with sensors in smart cars. It’s a better solution to replace traditional web servers in terms of processing speed, cost and power consumption. Our solution created using FPGA technology (i.e., Cyclone2, device EP2C70F896C6) is connected to the network and can play the role of a central WEB server achieving real time remote processes control or remote data transmission via the Internet. The main contribution of this work is creating an embedded WEB server using RISC processors called Nios II configurable for general use. This Nios II, which is a soft-core processor developed by ALTERA, can models specific processors using HDL and then can be customized (and synthesized) for any application. Network connectivity is tested between an embedded Web server on Nios II and a standard web client. Messages sent from the client-side can be displayed over LCD on Webserver. The client can send commands to the board for controlling IO’s, for reading from RAM, and for writing on RAM. The web server consists of an HTML interface, a MySQL database that contains user queries and results, a set of databases, a library of FPGA configurations, encryption algorithms, a responding host application user requests, and an FPGA coprocessor to speed up the alignment operation sequence.
Keywords:	HTTP / TCP, Nios II, FPGA, Soft Core Processor, Embedded Web Server, AES, RSA, Real Time.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	BACTERIAL AND VIRUS PNEUMONIA INFECTION DETECTION ON CHEST X-RAY IMAGES USING MACHINE LEARNING
Author:	AURELIA MICHELE, GEDE PUTRA KUSUMA
Abstract:	Pneumonia is a lung inflammation caused by viruses or bacteria, resulting in millions of deaths each year. Pneumonia can be diagnosed by analyzing chest x-ray images by radiologists. This research aims to help, accelerate, and simplify pneumonia detection processes. In this research, we proposed a deep learning framework for pneumonia detection using machine learning. Features from chest x-ray images are extracted using convolutional neural network models pre-trained on ImageNet. The extracted features were then fed into a classifier to predict virus pneumonia, bacterial pneumonia, and normal images. This research used four neural network architectures as features extractors, specifically MobileNetV2, MobileNetV3, ResNet50, DenseNet169. For prediction, we used CNN default classifier Artificial Neural Network (ANN), Support Vector Machines (SVM), Random Forest (RF), and Linear Discriminant Analysis (LDA). This research is using dataset from Guangzhou Women and Children’s Medical Center, Guangzhou. The final classification result achieves 96.5% accuracy on normal, bacterial, dan virus pneumonia classification using ResNet50 combined with SVM, continued by achieving 97.6% accuracy using ResNet50 combined with Random Forest on bacterial and virus classification. This result outperformed previous research using only DenseNet169. Hence, this approach can be used by radiologists or novices in pneumonia detection processes.
Keywords:	Pneumonia Detection, Machine Learning, Convolutional Neural Network, Support Vector Machine, Random Forest
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	A MODEL FOR CLASS NOISE DETECTION USING TREE-BASED CLUSTERING ALGORITHM
Author:	HELAL A. Suleiman, MANAL A. ABDELFATTAH, OSAMA E. EMAM
Abstract:	Clustering is the most descriptive task in a mining data stream, because it is a method of grouping or merging data objects into disjoint clusters based on some criteria you choose. So, such data objects in the same cluster are similar hence data objects in other clusters are different. This paper presents a model that includes methods for ensuring not only detecting outliers but also handling noisy data in real-time and offline as well. Furthermore, by using the improved tree-based clustering algorithm there is no need to initialize number of clusters in advance. Experimental results, applied to hotels and flights, find that this proposed model achieves high-quality results without outliers in less time on real datasets.
Keywords:	Clustering, Data Stream, Tree-Based Clustering, Noisy Data, Outliers
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	A BIBLIOMETRIC ANALYSIS OF PUBLICATIONS ON SOCIAL MEDIA INFLUENCERS USING VOSVIEWER
Author:	ALHAMZAH F. ABBAS , AHMAD JUSOH, ADAVIAH MASOD, JAVED ALI , AHMED H. ALSHARIF, ALHARTHI RAMI HASHEM E
Abstract:	The current study identified research trends regarding social media influencers. By searching journals related to social media influencers in the web of science collection database between 2007 and 2020 period. we collected 670 research articles about social media influencers. The study presents a knowledge-domain map that detects author collaboration networks as well as journal relationships. This was accomplished by a bibliometric study that can be examined using the VOS viewer software. The study on social media influencers reported resemblances which included the rise in the study period and the increasing recognition of “social media influencer” as a term. The results provide fundamental insights into research on social media influencers.
Keywords:	Social Media Influencer; Trends; Bibliometric Analysis; VOS Viewer
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	LEARNING TO LOCATE OBJECTS IN CROWDED SCENES BASED ON FULLY CONVOLUTIONAL NETWORK
Author:	HOANH NGUYEN
Abstract:	Locating objects in crowded scenes is a challenging problem since objects such as pedestrians or vehicles often gather and occlude each other. This paper proposes a new approach for locating pedestrians in crowded scenes based on fully convolutional network. First, ResNest, which combines the channel-wise attention strategy with multipath network layout to extract feature from images, is used as the backbone network to extract features from input image. ResNest is a simple architecture that achieves better speed-accuracy trade-offs than state-of-the-art CNN architectures without incurring excessive computational costs. Since the features produced by the backbone network often have small receptive fields and weak representation capabilities, the feature enhancement model is then designed to refine the features efficiently. The feature enhancement model is attached behind the backbone network and makes features deeper and more expressive than before. Based on the enhanced feature pyramid, the detection head including three branches is adopted to predict the classification score for each point on the feature pyramid, regress the distances from the point to the four sides of a bounding box, and predict the center-ness score which is multiplied by the classification score to rank the bounding box in NMS. Experimental results on the CityPersons dataset show the effectiveness of the proposed method on locating objects in crowded scenes.
Keywords:	Fully Convolutional Neural Network, ResNest, Object Detection, Pyramid Network, Crowded Scenes
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	A STUDY TO INVESTIGATE THE EFFECT OF DIFFERENT TIME-SERIES SCALES TOWARDS FLOOD FORECASTING USING MACHINE LEARNING
Author:	NAZLI MOHD KHAIRUDIN, NORWATI MUSTAPHA, TEH NORANIS MOHD ARIS, MASLINA ZOLKEPLI
Abstract:	Machine learning has been deemed to be a powerful approach in forecasting hydrological events such as flood using time-series historical data. A flood can be forecast in a manner of lead time whereby short-term forecast is up to 2 days, the medium forecast is between 2 to 10 days, and the long-term forecast is more than 10 days and several months of forecasts will have a seasonal lead time. Even though the determination of forecast lead time is normally bound with the purpose of operation i.e., daily operations or strategical, but the determination of time-series scale pattern to be input into the forecast model still impose a challenging task as it involves availability and variability of the data. Commonly, the hydrological data has a dynamic nature with non-stationary and non-linear characteristics. Therefore, it is important to choose dominant input to provide an accurate forecast. The objective of this study is to investigate the effects of different time-series scales of rainfall data from eight rainfall stations in Kelantan River towards the accuracy of forecasting water level at Kuala Krai station. Pre-processing techniques based on Mutual Information (MI) are also introduced to cater the variability of the data in finding the most dominant features as input to the forecast model. There are four scale patterns that have been investigated which consist of 7 days, 10 days, 14 days, and monthly. The forecasting analysis of all scale patterns were run against three machine learning models which are Artificial Neural Networks (ANN), Long-Short Term Memory (LSTM), and Adaptive Neuro-Fuzzy Inferences System (ANFIS) model. The results show that monthly scale pattern achieve the best performance compared to other scale patterns and LSTM is the best model for forecasting monthly water level. It indicates that longer time-series of scaled pattern may provide better forecasting accuracy and able to capture more information of the seasonal characteristics of the rainfall. Thus, it will largely benefit the flood management in reducing the flood risk and controlling its resources.
Keywords:	Flood Forecasting. Machine Learning, Rainfall, Time-Series Scale, Water Level
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	CURVE RECONSTRUCTION BY CUBIC BALL ON ARABIC FONTS USING BUTTERFLY OPTIMIZATION ALGORITHM
Author:	MOHD LUTFI ZAINUDIN, ZAINOR RIDZUAN YAHYA, WAN ZUKI AZMAN WAN MUHAMAD, ZABIDI ABU HASAN
Abstract:	The Butterfly Optimization algorithm (BOA) is taken into account as a new metaheuristic algorithm family. Researchers were drawn to this metaheuristic algorithm due to the potential offered to solve the problems broadly. The BOA algorithm was employed to obtain the best solution to the curve fitting problem by using the cubic Ball curve. Sum Square Error (SSE) is used to evaluate the error generated between two curves because the goal of this research is to shrink the distance between the extracted shape images and the generated curve by parametric equation. The pre-processing steps need to be followed before enter to the curve reconstruction process. According to the findings of this analysis, the proposed method did not successfully generate a fit cubic Ball curve because the shape formed on the boundary extraction is not closely fitted. The error generated has tarnished the expected results, and the method proposed need to be improved eventually.
Keywords:	Butterfly Optimization Algorithm, Cubic Ball Curve, Metaheuristic Algorithm
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	A SYSTEMATIC REVIEW OF SECURITY IN SMART GRID INFRASTRUCTURE
Author:	RASHI SINGH, NASIB SINGH GILL, PREETI GULIA
Abstract:	Today, a huge enhancement has taken place in our electricity grid system at every level either it is generation, transmission, distribution, or at the consumer side. More and more focuses are on making the grid reliable, efficient, and available all the time. Establishing a framework is a one-time process but maintaining and provides security is life long process and the same is with the smart grid. A smart grid consists of various components, and these components make it more prominent for threats. This paper describes the reasons for the adoption of the smart grid, various security threats in smart meter, Advance metering infrastructure, cloud, communication, and SCADA along with the research work going on these threats. This paper gives a comprehensive research review aiming to help the researchers to explore further possible solutions in making the power grid secure and smarter.
Keywords:	Smart Grid, AMI, SCADA, Communication, Cloud, Security of Smart Grid
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	MODEL OF AN AUTOMATED EDUCATIONAL AND METHODOLOGICAL COMPLEX BASED ON A SEMANTIC NETWORK
Author:	GULNUR ALKHANOVA, SERIK ZHUZBAYEV, ILIYA SYRKIN, NURGUL KURMANGALIYEVA
Abstract:	A method for developing an automated educational and methodical complex based on a semantic network is described. Requirements for such educational and methodological complex have been formulated. Structural and formal models of tools based on a semantic network have been presented. The purpose of developing the model is to make it easier for students to perceive the various educational and methodological complexes through its compilation on the basis of a holistic view of the subject area, as well as to optimise the work of the teacher.
Keywords:	Semantic Network, Educational Process, Educational And Methodical Complex, Intelligent Model, Automated
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	AN OPTIMAL APPROACH OF CONFORMITY ASSESSMENT AND ROBUSTNESS TESTING FOR OBJECT ORIENTED CONSTRAINTS
Author:	KHADIJA LOUZAOUI, KHALID BENLHACHMI
Abstract:	In this work we propose a formal modeling of optimal constraints for testing the conformity contract and robustness behaviors of object oriented (OO) programs. Our approach is an important way to generate test data of overriding methods of the inheritance process in the general case where behaviors of OO classes are not necessarily similar. The key idea of this work is to use mathematical entities for developing some algorithms of test data generation to simplify conformity and robustness verification process. Our model of constraints is based on set theory and logical axioms, and can represent in an unambiguous form all properties and behaviors of OO robustness contracts. The second model of this paper is an equivalence partitioning of input data of the program under test, this partitioning technique can be used to reduce the number of test cases that must be developed for classes and subclasses.
Keywords:	Software Verification, Formal Specification, Conformity Testing, Robustness Testing, Valid Data, Invalid Data, Test Data Generation, Equivalence Partitioning, Inheritance, Constraint Resolution.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	A COMPARATIVE STUDY ON THE ATTRIBUTES OF NHPP SOFTWARE RELIABILITY MODEL BASED ON EXPONENTIAL FAMILY AND NON-EXPONENTIAL FAMILY DISTRIBUTION
Author:	SEUNG KYU PARK
Abstract:	In this study, after applying the exponential family (Goel-Okumoto, Erlang) and non-exponential family distributions (Pareto, Log-Logistic) which are used in the field of reliability to the finite failure NHPP software reliability model, we compared and analyzed the reliability attributes reflecting the shape parameters of the proposed distribution. For this, software failure time data was used, parametric estimation was applied to the maximum likelihood estimation method, and nonlinear equations were calculated using the bisection method. As a result, in the analysis of the intensity function, the Log-Logistic model of the non-exponential family was efficient because the failure occurring rate decreases with the failure time and the mean square error is small. In the analysis of the mean value function, all the proposed models showed a slightly underestimated value compared to the true value, but the Goel-Okumoto model of the exponential family had a smaller margin of error than other models. As a result of evaluating the software reliability after putting the mission time in the future, the Erlang model was high and stable, but the Log-Logistic and Pareto model showed a small decreasing tendency. In conclusion, the exponential family models showed more efficiency than the general non-exponential family model but were ineffective than the log type (log-logistic) model. In this study, we have newly analyzed the software reliability attributes of the exponential family and non-exponential family distributions, which have no previous research cases, and expect it to be used as a basic guideline for software developers to search for the optimal software reliability model.
Keywords:	Erlang Distribution, Exponential Family, Log-Logistic Distribution, NHPP Model, Non-exponential Family, Pareto Distribution
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	A STUDY ON THE INFLUENCING FACTORS OF CONSUMERS' WILLINGNESS TO BUY LARGE MUSICAL INSTRUMENTS ONLINE
Author:	HOU SHAOPENG, OOK LEE, JONGCHANG AHN
Abstract:	Along with the fast development of the Internet and the continuous improvement of e-commerce platforms, Chinese consumption has dramatically changed. Online shopping is gaining wider popularity among consumers. In recent years, as the upstream and downstream industries relevant to e-commerce continue to develop, the types of online shopping have once again been widened. Large musical instruments such as pianos and guitars are also sold on e-commerce platforms. Their market share is gradually expanded by under more reasonable and transparent prices and lower logistics costs. Compared with the fast-growing market scale, we have few theoretical literatures concerning online shopping. At present, most of the study mainly focuses on the development of information technology and customer behaviors on the whole platform, and slightly ignores specific theoretical research on the art industry. Based on previous information systems theory, seven hypotheses about the behavior willingness for musical instruments online were put forward. A reasonable structural equation model is constructed; an empirical analysis on the collected valid 364 data is carried out; and six hypotheses are tested by analyzing the relation between path coefficient and variables. Moreover, perceived trust and perceived risk are two independent variables in the same dimension. The hypothesis that the result was not accepted is elaborated, and management and marketing suggestions are provided for managers of the online shopping platform.
Keywords:	Online Shopping, Behavior Willingness, Structural Equation Model, Influencing Factors, Musical Instrument Sales, Information Systems
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	DETECTING MALICIOUS ACTIVITIES ON TWITTER DATA FOR SENTIMENT ANALYSIS USING A NOVEL OPTIMIZED MACHINE LEARNING APPROACH
Author:	V. LAXMI NARASAMMA, DR. M. SREEDEVI
Abstract:	In Natural Language Processing (NLP), Twitter data is used for sentiment analysis and it is most prevalent theme in recent era. However, the security attacks on the Twitter data have been increased by hackers which reduced the performance of the sentiment analysis. Thus to detect the malicious activities in the Twitter data, a novel Spider Monkey based Generalized Intelligent (SMbGI) framework is developed in this paper. This model utilizes Twitter-based data about the coronavirus disease 2019 (COVID-19) to detect the malware activities for improving the classification of sentiments. Moreover, this model imposed a malicious attack on the data for recognizing the developed SMbGI model efficiencies. Thus, the proposed SMbGI approach has been effectually detecting malicious functions and enhances sentiment classification. Moreover, Python tool is used for sentiment analysis, and it computed the parameters like accuracy, recall, precision, F-measure, and error rate. Lastly, the attained outcomes are compared with recent existing works to identify the performance of the SMbGI approach.
Keywords:	Sentiment Analysis, Natural Language Processing, Spider Monkey Optimization, Twitter Data, Malicious Activities
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	SIMPLIFIED AND SECURE AUTHENTICATION SCHEME FOR THE INTERNET OF THINGS
Author:	ZHANAT KENZHEBAYEVA, ZHANAR AKHMETOVA, RYSGUL BAINAZAROVA, ZHANAR KAZHENOVA, AIGUL SARIYEVA
Abstract:	The study discusses the MQTT (Message Queuing Telemetry Transport) protocol for the Internet of Things and sensor wireless networks, its features, application options, and specific procedures. The information elements and principles of the message owner are analysed. The identification of users proposed in this study is carried out by identifying them from the Cloudant database. Such application runs on the Node.js server (JavaScript) in the IBM (International Business Machines) Bluemix environment and provides a RESTful API (Representational State Transfer Application Programming Interface) or which requires mobile client access to authenticate users. The mobile client access service is designed to activate these two APIs in any authentication application. The scientific novelty is determined by the fact that it is proposed to use separate approaches to authentication for a web application – on Cloud Directory, and for a mobile application – MobileFirst Client Access. However, both web and mobile applications use the same level of application security to allow the user to access device data. The practical significance of the study is determined by the fact that the transport layer security protocol increases the performance of the protocol and reduces computational costs, but it is not used when the initial connection to the server or in cases where the previous session has already expired. The study presents an algorithm for detecting weak symmetry breaking for analysing the randomness of a reconstructed electronic message. The study proposes a method of homomorphic encryption and authentication of users and their electronic messages in wireless sensor networks of the Internet of Things.
Keywords:	Information security, Protocol, Encryption, Interface, Programming.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	WHY DO STUDENTS ENGAGE IN GAMIFICATION? AN EXPLORATORY STUDY USING MEANS-END CHAINS
Author:	ANH Q.T.NGUYEN
Abstract:	Gamification is one of the educational techniques that increase the motivation and engagement of learners. With the expansion of gamification in higher education, especially in the context of COVID 19 emergence, it is an increased need to know about student engagement in such behavior. While many topics of gamification are growing at a rapid pace, the students’ personal values were not uncovered in related literature. The current study sought to address this gap by investigating a set of students’ personal values when they participate in gamification. Based on interview 69 students by the laddering technique, six personal values that drive students to participate in gamification are explored in the current study, such as Social Recognition, Exciting life, Sense of accomplishment, Sense of belongingness, Self Enhancement, and Self-expression. The findings suggest that educators and teachers focus on investigating how personal values can be used to motivate learners, improve their skills, and maximize learning by gamification.
Keywords:	Gamification; personal value; student; means-end chain; higher education.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	DIAGNOSIS OF COVID-19 USING 3D CONVOLUTIONAL NEURAL NETWORKS
Author:	JYOTHI VISHNU VARDHAN, POORNA CHANDRA VEMULA, SRINIVAS G, GUNASEKHAR CHOWDARY, SUNIL KUMAR B
Abstract:	To stop the fast-spreading of covid19, there needs to be a significant improvement in the speed with which the diagnosis is performed. Many studies have been done on using deep learning algorithms like convolutional neural networks and many of its variants available in the industry to make the diagnosis faster. However, most of these approaches involve using datasets that are not that compatible with the real world. In this paper, we will be using efficient techniques to address this problem by using CT scans and leveraging most of the features available in CT-scan images to build a model that can classify whether covid19 infects a person or not, given his CT scan as input to the model. As CT scan images are more reliable and can represent the condition of a person in a more detailed way than any other images like X-rays, these can be used for obtaining faster and precise results.
Keywords:	Data Augmentation, Image Processing, Voxnet, 3D CNN, Volumetric
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	CHALLENGES AND OPPORTUNITIES OF E-GOVERNMENT IMPLEMENTATION IN THE IRAQI MINISTRY OF OIL
Author:	AHMED RASOL HASSON, MOAMIN A MAHMOUD
Abstract:	Although the execution of e-Government has reached superior levels in developed nations, it is still in its beginnings in many developing countries. Indeed, there is an increasing need to exploit the opportunities created by the new emerging Information Communication Technologies (ICTs) to implement e-Government systems in developing countries, specifically, the countries who have not yet initiated an e-Government initiative or these who are in early phase of the e-Government initiatives development. Generally, information system has ability assistance for corporate sustainability in developing countries and regions at various development levels. The organizations of greater level sustainability are most likely to see voluntary Information System-enabled cooperation among employees, while those still at the infancy stage need to supply more incentive and assistance from top management. Lately, In Iraq government has the tendency to adopt e-Government initiatives to entrench Good Governance and improve public sector efficiency. Despite the passage of more than sixteen years for the application of Iraqi e-Government strategy, Iraq is still at rank 143 out 192 countries; in the e-Government development index of 2020. However, various obstructions are preventing successful implementation of this technology. The current investigation aimed to highlight issues that hinder successful implementation of e-Government systems in Iraq generally, and in the ministry of oil especially with recommend feasible solutions to tackle them. A sample of five managers was selected based on both convenience and representation: Two of them work in the Ministry of Oil as Inspection Director and Information Technology manager, while the remaining three work as Chief Executive Officers (CEOs) of ministry establishments. The semi-structured interviews were the method used in the study to obtain various perspectives on the challenges that faced the Ministry of Oil to implement the e-Government system. The method of analysis chosen for this study is a qualitative approach of thematic analysis. This supplied in-depth comprehending to the present status of e-Government in the Ministry of Oil in Iraq and highlighted key hindrances of its effective application. According to this investigation, the research proffered many recommendations that needs to be considered in order to completely benefit from e-Government technologies.
Keywords:	ICTs, developing countries, e-Government, challenges of e-Government Implementation, e-Government in Ministry of Oil.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	IMPROVE SALES USING DATA MINING APRIORI ALGORITHM TO EXTRACT HIDDEN PATTERN
Author:	ABDALLA YASIN MABROUK, MOHAMED HELMY KHAFAGY, MOHAMAD ELMASRY, MOHAMED HASAN IBRAHIM
Abstract:	With the increasing growth of data in the world of business and companies, the amount of data resulting from sales operations in these companies increases, and there is no doubt that the presence of this data is a treasure. Through analyzing this data, unusual results can be reached that help decision-makers improve the profit process for these companies. We use in this research paper real data taken for the sales operations of Emisal company, which is located in Egypt and works on the sale of salts products during 2020 and four years back. Data mining technology is used in this paper, especially the apriori algorithm to explore the relationships between returns and the item, and the customer, and the month, and the day of the week, and the province. The results recommend eliminating the scenarios that may occur between the causes of return and the relationship with the item, customer, month, day of the week, and maintaining future sales.
Keywords:	Association Rules, Data Mining, Sales Analysis, Sales Returns, SPSS Modeler.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	IMPROVE INDONESIA NATIONAL E-PROCUREMENT FAIRNESS WITH VENDOR DATA-DRIVEN CAPABILITY ASSESSMENT AND TOGAF ADM
Author:	R. ADHARI CAHYA MAHENDRA, NILO LEGOWO
Abstract:	The implementation of a distributed national e-procurement system creates problems with the low quality of vendors data. This paper aims to improve vendor data quality by making it single source of truth that various applications can share in LKPP. Data acquisition using ethnographic immersion techniques.in order to get deeper and meaningful research data. The analysis process uses the TOGAF ADM framework. The result is a blueprint and a roadmap for the work package implementation process to centralized vendor data. Therefore, it can be concluded that by using a good roadmap, the goal of improving the quality of data providers and the fair principle in national procurement with minimum downtime can be achieved.
Keywords:	Enterprise Architecture, Improvement Data-Driven, Capability Assessment, e-Procurement Government Agency, TOGAF ADM
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	HANDWRITING PREDICTION WITH LEARNING VECTOR QUANTIZATION METHOD IN MOBILE APPLICATION
Author:	DIAN PRATIWI, SYAIFUDIN, TRUBUS RAHARDIANSYAH, MUHAMAD ICHSAN GUNAWAN, STEVEN SEN, DIMAS ADI PRATAMA
Abstract:	Advances in technology are now increasing bringing people towards digital and mobile applications. To determine the owner of a handwriting, one of the manual techniques commonly used by humans that can be facilitated by mobile application technology is handwriting recognition. Learning Vector Quantization is one of the machine learning methods used to perform handwriting recognition and is one of the Artificial Neural Network (ANN) methods. This study aims to build a handwriting recognition system using the Learning Vector Quantization method on a mobile application, with feature extraction as the basic step in interpreting and classifying images. The results obtained from testing the prediction of learning vector quantization from 16 new data with a total of 80 tests. The results showed that 54 data were correct and 26 were incorrect, so the accuracy was 67.5%. Then obtained precision = 75.17%, recall = 67.5%, learning rate = 0.005, alpha value = 0.05 and iteration = 100
Keywords:	Android, Feature Extraction, Handwriting, Learning Vector Quantization, Mobile Application
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	HYBRID CRYPTOSYSTEM USING RC4+ AND MULTI-FACTOR RSA ALGORITHM FOR SECURING INSTANT MESSAGING
Author:	DIAN RACHMAWATI, SYAHRIL EFENDI, ZIKRI AKMAL SANTOSO
Abstract:	Communication and information exchange is the activity that apart from daily life. Instant messaging is one of the communication media by using internet protocol. In Many cases of tapping data and hacking information is a problem. Using a cryptography algorithm could secure the data information or message. Using a single algorithm of cryptography is still weak to send the data or information through the internet. Using a Hybrid cryptosystem scheme can solve this problem with the excellent implementation in instant messaging, that message will secure by RC4+ algorithm; this type is a symmetric algorithm that using one key, fast in the process but not secure enough, and the key of RC4+ algorithm will secure by Multi-factor RSA algorithm this type is Asymmetric algorithm has two key, but the process is slower than RC4+ but strong. The results showed that the hybrid combination of 2 algorithms cryptography successfully secures the message and is the key to ensuring that message, proving this scheme could secure faster than another combination of RC4+ and Multi-factor RSA.
Keywords:	RC4+, Multi-factor RSA, Cryptography, Hybrid, Instant Messaging
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	GDPR-BLOCKCHAIN COMPLIANCE FOR PERSONAL DATA: REVIEW PAPER
Author:	YAMAN SALEM, EMAN-YASSER DARAGHMI
Abstract:	Processing and collecting personal data by third parties poses a big concern to user’s privacy. GDPR is a regulation proposed to maintain users’ privacy, while blockchain is an innovation technology used in many applications. This research is motivated by the facts mentioned above, and it aims to investigate how to make blockchain complies with the GDPR regulation, a systematic review is conducted to explore the relation between GDPR and blockchain, in addition, this study explores the main compliance issues with the GDPR and blockchain. As a result, it states several suggestions that make a blockchain technology more compliant with GDPR. The suggested solutions may open a new idea to design a novel model for GDPR-Blockchain Compliance for Personal Data.
Keywords:	Blockchain (BC), Privacy, GDPR, Personal Data, Compliance.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	COMPARISON OF CLUSTER VALIDITY INDEX AND DISTANCE MEASURES USING INTEGRATED CLUSTER ANALYSIS AND PATH ANALYSIS
Author:	AISYAH ALIFA, SOLIMUN, MARIA BERNADETHA THERESIA MITAKDA, ADJI ACHMAD RINALDO FERNANDES, WAEGO ADI NUGROHO
Abstract:	This study wants to compare the Integrated Cluster Analysis and Path model with various cluster validity indices and distance measures on Character, Capacity, Capital, Collateral, Condition, Intention to Pay Obedience, Punctuality of Payment of Bank X Creditors. The data used in this study are primary data. The variables used in this study are character, capacity, capital, collateral, condition, intention to pay obedience, punctuality of payment bank X creditors. The data were obtained through a questionnaire with a likert scale. Measurement of variables in primary data using the average score of each item. The sampling technique used was purposive sampling. The object of observation is the creditor as many as 100 respondents. Data analysis was carried out quantitatively, to explain each of the variables studied, a descriptive analysis was carried out first, then an Integrated Cluster Analysis and path analysis was carried out with the average linkage method on various cluster validity indices, namely Gap, Index C, Global Sillhouette. , and Goodman-Kruskal, as well as three distance measures, namely the Euclidean, Manhattan, and Minkowski distances. This research uses R software. The integrated cluster and path analysis with the Gap Index, Index C, Global Sillhouette, and Goodman-Kruskal with the Manhattan Distance is better than the Gap, Index C, Global Sillhouette, and Goodman-Kruskal with the Euclidean and Minkowski Distance. The novelty in this research is the application of Integrated Cluster Analysis and path model approach to compare 4 cluster validity indices, namely Gap Index, C Index, Global Sillhouette, and Goodman-Kruskal, and three distance measures, namely Euclidean, Manhattan, and Minkowski distances. simultaneously.
Keywords:	Cluster Analysis; Path analysis; Integration Model; Dummy Variable; Cluster Validity Index; Distance Measures
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	TWO FACIAL EMOTION DETECTION BASED ON NAIVE BAYESIAN CLASSIFIER
Author:	URIEL ALAN FLORES-JUAREZ, JESÚS ANTONIO ÁLVAREZ-CEDILLO, TEODORO ÁLVAREZ-SÁNCHEZ
Abstract:	Emotion is an affective state of a subjective reaction in an environment accompanied by physiological and endronic changes in human beings; this happens suddenly and abruptly in the form of a crisis. In the article, Bayes' theorem's implementation was developed that allows classifying two facial emotions of the human being. Our central premise is based on realizing a Bayesian model to generate a supervised learning model, which uses the analysis of data collected to create an emotions classifier. The Naive Bayes classifier training model results provide a functional form of probability to capture joint statistics of local appearance and position on the object whose one-to-one match result is slightly higher than 56%. This value is less than the method used by Schneiderman and Kanade. Concluding that the proposed algorithm is better than those analyzed because several external variables such as lighting, pose, and detection of characteristics can change the performance in terms of precision.
Keywords:	Emotional computing, Naive Bayesian Classifier, Emotions, a system for predicting joy and sadness
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	TRUST SCORE MEASUREMENT METHOD FOR WEB DONOR SELECTION AND IMPUTATION OF MISSING VALUES
Author:	M. IZHAM JAYA, FATIMAH SIDI, UMAR ALI BUKAR, ISKANDAR ISHAK1, HAMIDAH IBRAHIM, LILLY SURIANI AFFENDEY, MARZANAH A. JABAR, NAVIN KUMAR DEVARAJ, AND MUSTAFA ALABADLA
Abstract:	The effects of trust score measurement is web donor selection is evaluated in this study. The performance of the proposed method is conducted by running a prediction model on the imputed dataset. Thus, several experiments were carried out to quantify the impact of the prediction model via Root Mean Squared Error (RMSE) and F-Measure. The results demonstrate that the proposed method improves the performance of existing web donor selection. The results showed that the RMSE, prediction accuracy, and F-Measure are improved when the prediction model is trained with datasets imputed using the proposed method. This research contributed to improved data quality, especially to the information system (IS) and database field, where good data quality benefited the data analysis performance.
Keywords:	Cold deck, Missing value, Imputation method, Web donors, Data quality.
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	OPTIMIZATION OF PARAMETERS ON SUPPORT VECTOR MACHINES AT VARIOUS FACTOR LEVEL VALUES
Author:	ALIFYA AL ROHIMI, ADJI ACHMAD RINALDO FERNANDES, ENI SUMARMININGSIH
Abstract:	The purpose of this study is to optimize the parameters on Support Vector Machines (SVM) at various factor level values and compare the classification results. The data used in this study are secondary data from the 5C (Collateral, Character, Capacity, Condition of economy, and Capital) assessment at Bank X. Optimization of the parameters is carried out by determining each of the 5-factor level values for parameters C and γ. The determination of the 5 factor level values was carried out based on previous research, namely for the value of C = {0.5,0.75,1,10,100} and γ = {0.005,0.05,0.1,0.5,0.75}. The data is divided into two parts, namely training data and testing data with a ratio of 80:20. This comparison is based on the Pareto principle. This division is also done using 5-fold cross-validation. The kernel used in this study is the Kernel Radial Basis Function (RBF) because RBF can transform data into very high dimensions so that it can perform classification well. The conclusion that can be drawn based on this research is by using a kernel trick, especially using the RBF kernel, the results of parameter optimization are better. This is proven by the average level of accuracy using the RBF kernel with cross-validation using 5-fold reaching 90.38% while without the kernel trick it only reaches an average accuracy of 65%. Novelty in this study is the use of the 5C variable in the credit assessment at Bank X and the use of the 5 level factor value for parameter optimization of the SVM.
Keywords:	SVM, Radial Basis Function, Optimization, Factor Level Value
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text

Title:	PERFORMANCE EVALUATION OF TWO BRAILLE-TO-SPANISH TRANSCRIPTION APPLICATIONS: MOBILE DEVICE VS. PC
Author:	EDWAR JACINTO GOMEZ, FREDY H MARTINEZ S, FERNANDO MARTINEZ SANTA
Abstract:	In Colombia, the participation of people with some disability in the different educational levels is still deficient. Although it has been growing since 2010, the CNPV estimates that the illiteracy rate for the population with some disability is still three times higher than the national figure. However, the country has been adopting a policy of Inclusive Education focused on reducing barriers to learning and participation for all, which implies a high level of commitment and understanding by the entire educational community to achieve good practices. When analyzing the specific case of people with visual impairment, it is evident that one of the main mediating agents of inclusive education is teachers. They, in some cases, have led their students' reading-writing process to be ineffective due to their lack of knowledge in the Braille language. An example of this is the significant amount of time they take to transcribe texts in Braille, decreasing the ability to evaluate or rectify whether or not the student understands a text, preventing timely feedback. This situation hinders how students learn, understand, and produce texts. Therefore, the use of technological tools that facilitate the teaching work is proposed by developing applications for transcription of Braille text to literary Spanish both on mobile devices and personal computers to minimize this problem and support the teaching-learning process in the classroom. Initially, the article describes the application developed for mobile devices with an Android operating system and the software application developed for PCs using Matlab. Subsequently, the performance analysis of applications is presented in terms of processing time, transcription error percentages, and response to different test conditions. Finally, the results and improvements concerning previous works are presented in terms of versatility and robustness achieved in detecting Braille dots, cells, and characters with different lighting characteristics and types of sheets.
Keywords:	Braille, Visual Impairment, Inclusive Education, Software, OBR
Source:	Journal of Theoretical and Applied Information Technology 15^th December 2021 -- Vol. 99. No. 23 -- 2021
Full Text