		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
November 2021 | Vol. 99 No.22

Title:	CHALLENGES AND OBSTACLE TO IMPLEMENTING 5G IN INDONESIA
Author:	AZANI CEMPAKA SARI, JASON, 3ENDRICO LANSKY, MUHAMMAD ALIF FERDIANSYAH
Abstract:	Over the last few years, the development of wireless communication has become something that is often to be seen. This development has been started from 1G to the latest, which is called the 5G Network. The 5G Network will greatly improve the quality of the internet network (QoS) and industry in Indonesia. However, to successfully implement 5G in Indonesia, there are several challenges that we must overcome to implement 5G in Indonesia. The challenges start from implementing the 5G Infrastructure. First we must know the exact frequency to implement 5G in Indonesia, other than that we also have to know the positive and negative effects if we succeed in Implementing 5G. If successfully implemented, it is certain that 5G will increase data transfer speeds with more stable bandwidth and much lower latency compared to its predecessor generation. This positive development will later improve internet performance in Indonesia to be able to compete with Countries that have already implemented 5G.
Keywords:	Iot, Heterogen Networks, Massive MIMO, D2D Communication, Cloud Technology.NFV, SDN, EMB (Enchanced Mobile Broadband).
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	ADAPTIVE E-LEARNING RECOMMENDATION MODEL BASED ON THE KNOWLEDGE LEVEL AND LEARNING STYLE
Author:	ALBER S. AZIZ, REDA A. El-KHORIBI, SHEREEN A. TAIE
Abstract:	E-learning systems facilitate the process of education and interaction between teachers and learners during minimizing a lot of temporal or spatial restrictions. Recently, many learners prefer to use electronic devices to achieve everyday jobs. The process of using the learner style, learning goals, and learner characteristics, and electronic devices and systems are called Adaptive e-learning. The importance of Adaptive E-learning Systems (AES) is to help the teachers to choose and recommend some materials to the learner and to increase the knowledge level. This paper develops a new adaptive e-learning recommender model using learning style and Knowledge Level Modeling (AERM-KLLS). The proposed model adapted automatically to the requirements, interests, and levels of knowledge of the learners by analyzing learner style using a fast questionnaire, representing the knowledge level and all the course questions in the learner model as a knowledge overlay model, which helps the proposed model to recommend objects from the points that have the least scores at the pre-test. The analysis of AERM-KLLS performance measured by making two tests and comparing the two test performance; the performance of using the AERM-KLLS algorithm used in the second test for 321 participated learners increases the overall performance for the students with an accuracy of 90.97%. The proposed model provided to the learners for an English course in the Faculty of Computer Science, October 6University, to make the best use of the E-learning advantage and increasing the performance, in COVID 19 restrictions.
Keywords:	Learning Style, Knowledge level, Questionnaire, Adaptive E-Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	DESIGN AND EVALUATION OF QUALITY ASSURANCE-BASED INTERACTIVE MACHINE LEARNING MODEL
Author:	AYOBAMI STEVE SHOFADEKAN, AMBROSE A. AZETA, HANNAH AKINWUMI
Abstract:	Some complex task can be difficult to fully understand or represent or there may even be few data available about them thereby making it difficult to solve with classical machine learning approaches. Hence, Interactive Machine Learning (iML), an approach where humans are used to complement machines. However, existing interactive machine learning approaches have not sufficiently considered quality assurance of the human feedback in the interaction cycle to guaranty improved performance of the model. Interactive machine learning systems take on data for updates without checking the quality of the update data. This is capable of misleading a machine learning model if wrong, noisy or malicious data are used to update the model. Therefore, this paper proposes a quality assurance-based interactive machine learning model that is able to evaluate the quality of the feedback obtained from the human in the iterative feedback loop before passing such feedback to the learning model to update its knowledge about the problem. Existing literatures and concepts on interactive machine learning were reviewed. Also explored are areas where interactive machine learning approach has resulted in faster, less expensive model training process than the classical Machine Learning, especially when applied on rare and complex problems. Questionnaire method was used to conduct a survey that evaluates the usability and understandability of the proposed quality assurance-based interactive machine learning model using the Cognitive Walkthrough Strategy. The result gave a rating of 4.2 out of 5 for the usability of proposed model. This approach will increase the acceptability of the interactive machine learning model and the credibility of its predictions.
Keywords:	Evaluation, Human-in-the-loop, Interactive Machine Learning, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	DEVELOPMENT OF AN INTERACTIVE INFORMATION SYSTEM USING AUGMENTED REALITY MEANS
Author:	YERSAIN CHINIBAYEV, RAISSA USKENBAYEVA
Abstract:	This paper describes the technology of formation of the augmented reality, a comparative overview of the proposed development tools, as well as an analysis of existing types of software for handheld devices. The work is a continuation of a series of articles [1-5]. The study developed an information system that in conjunction with a web server provides interactive visualization effect. Currently, one of the important directions of development of Ad Hoc networks is VANET. However, in recent years, VANETs and their applications are increasingly being considered to work in complex application with other new telecommunication technologies. Thus, the use of unmanned aerial vehicles (UAV) (Unmanned Aerial Vehicle) can often significantly improve the functioning of the VANET and / or expand the functionality of this network. Using augmented reality applications also provides for VANET new opportunities, particularly in connection with the use of UAV. At the same time, in most VANET applications, including the use of UAVs and AR, the VANET architecture is based on software-defined networks (SDN). In the proposed structure, the UAV performs the functions of a SDN controller, which peripheral modules are located in the vehicles of the priority cluster. The image from the UAV is received on augmented reality glasses by the driver's assistant, which allows him to know the speed and other parameters of the movement of ambulances and other similar vehicles. A model of timely traffic light control is proposed. The VANET technology was chosen as the base for the implementation of control functions. To better manage the scalability and flexibility of the VANET, it is complemented by SDN technology, where the UAV acts as a controller. For visual assessment of the situation and control, the model uses augmented reality technology. The video stream received from the UAV can be supplemented with the necessary current information, for example, the speed and intensity of vehicle traffic on crossing streets, vehicle dimensions, etc.
Keywords:	Augmented reality, information support, UAVs, the SDN for VANET applications.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	THE TECHNOLOGY OF INTERACTIVE BOOK AUGMENTED REALITY (IBAR) FOR FACILITATING STUDENT 21-CENTURY SKILLS
Author:	FIRMANUL CATUR WIBOWO, HADI NASBEY, LARI ANDRES SANJAYA, DINA RAHMI DARMAN, NUR JAHAN AHMAD, HAIRUL NIZAM ISMAIL
Abstract:	This study aims to development of technology Interactive Book Augmented Reality (IBAR) for Facilitating 21st-Century Skills (21-CS). Technology influences high school students towards learning, and to determine 21st-Century Skills (Critical Thinking, Collaboration, Communication, and Creativity) for AR applications. The research method used was a quasi-experimental design, in which one whole class was used in four schools in different cities. The total sample of the study was 120 students in grade 10 middle school students, the sample was randomly assigned to the experimental or control group. The experimental group completed the Interactive Book of the Atomic Nuclear Structure concept in their physics lesson using AR technology. Meanwhile the control group completed the same interactive book using traditional methods and textbooks. Students in the experimental group were found to have a higher level of achievement in 21st-Century Skills consisting of Critical Thinking, Collaboration, Communication, and Creativity compared to the control group. In addition, the results show that most students are challenged and want to continue to use AR applications in the future for learning. In addition, they also showed no signs of being afraid to study physics while using the IBAR.
Keywords:	Interactive Book Augmented Reality (IBAR), Facilitating Student, 21st-Century Skills (21-CS), Media in Education.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	CHARACTERISTICS OF PHOTOVOLTAIC MODULES IN VARIOUS CONFIGURATIONS FOR PARTIAL SHADING CONDITIONS
Author:	ASNIL, KRISMADINATA, IRMA HUSNAINI, ERITA ASTRID
Abstract:	Partial shading conditions (PSCs) can cause a significant reduction in energy output in photovoltaic (PV) systems. This paper recounts the characteristics of PV in various condition of PCSs. The compared PV characteristics involve voltage, current, generated power, fill factor, mismatching loss, and efficiency. Six configurations of the PV system are used in this research namely Series-Parallel (SP), Honey Comb (HC), Total Cross Tied (TCT), Bridge Linked Honey Comb (BLHC), Bridge Linked Total Cross Tied (BLTCT), and Series-Parallel Total Cross Tied (SPTCT). The PSCs are considered uniform, short and narrow, long and narrow, long and wide, short and wide, and corner. The result indicates that TCT configuration is the best configuration among others then followed by the BLHC, BLTCT, SPTCT, HC, and SP configurations.
Keywords:	Partial Shading Conditions; Photovoltaic System Configuration
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	FRUIT CLASSIFICATION QUALITY USING CONVOLUTIONAL NEURAL NETWORK AND AUGMENTED REALITY
Author:	AZANI CEMPAKA SARI, HARI SETIAWAN, THORIQ WIMA ADIPUTRA, JOVIANDY WIDYANANDA
Abstract:	In Indonesia, the need for fruits is still relatively low. The contributing factor is that the quality of fruits in Indonesia is still quite low compared to imported quality fruits. Until now, Indonesia still relies on imported fruit rather than local fruit. For this reason, researchers have created a new innovation in this modern era, namely the application of fruit quality classification using Conventional neural networks and Augmented Reality. Convolutional Neural Network is one of the deep learning algorithms that can work well in image processing, such as classification and comparison. This research is to classify fruit using augmented Reality, which is combined with the conventional neural network. The CNN algorithm is good enough to classify fruit images into seven categories with an error of 10%. This shows that CNN, which is one of the deep learning algorithms, can be applied in agriculture. This application only needs to use a smartphone in the following way: scanned into real fruit, then this application will issue fruit quality information and three-dimensional images to compare fruit quality. So that farmers can easily separate which fruit is of low or high quality.
Keywords:	Convolutional Neural Network, Deep Learning, Augmented Reality, Fruit, Quality
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	THE EFFECT OF E-CRM AND TECHNOLOGICAL INNOVATION TOWARD CUSTOMER LOYALTY: A MEDIATION EFFECT OF CUSTOMER EXPERIENCE ON TOKOPEDIA CUSTOMERS
Author:	ENNY KHURNIASARI, IRMAWAN RAHYADI
Abstract:	This research aims to discover the effect of e-CRM and Technological Innovation toward Customer Loyalty mediated by consumer experience variables. The approach in this research uses a quantitative approach while the type of research is using survey research. The use of this survey research is to obtain an overview of e-CRM, technological innovation toward the product consumers mediated by the consumer experience variable. The sample in this research is 100 Tokopedia customers. The technique of sampling utilized in this research is purposive-sampling technique. In addition, the data analysis technique utilized in this research is SEM (Structural Equation Modeling) analysis in the PLS (Pertial Least Square) program. The result of this research manifests the significant and positive effect of e-CRM toward customers’ experience and customers’ loyalty. Technological innovation significantly and positively affects Customer Experience. Customer Experience significantly and positively affects Customer Loyalty. Technological Innovation significantly and positively affects Customer Loyalty. E-CRM Variable significantly and positively affects Customer Loyalty through Customer Experience. The Technological Innovation significantly and positively affects Customer Loyalty Variable through Customer Experience.
Keywords:	Customer Loyalty, E-CRM, Customer Experience, E-Commerce, Influence
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	SYSTEMATIC REVIEW BLOCKCHAIN MODIFICATION METHODS, CONSENSUS ALGORITHMS, AND BLOCKCHAIN APPLICATIONS (MAY 2021)
Author:	OWAIS ZAID, DERAR ELEYAN, AMNA ELEYAN
Abstract:	The Blockchain technology is a revolutionary technology for its stability in an environment that is predominantly unreliable, making it one of the most prominent technologies that everyone seeks to use and develop in a very wide range of applications, with all this when starting to expand using blockchain technology, defects appear quickly, especially when used in the applications in which they are made. Data modification and also when used in areas that contain simple processors such as the Internet of things, consensus algorithms and encryption are a heavy burden on these processors, and it is not possible to use the blockchain in applications that need to modify data such as the financial sector, so it was necessary to propose several Ways to make blockchain modifiable, so that the blockchain is applied to a wide range of applications. In this study, we will be able to know the most popular modification methods on the blockchain and provide a comparison between them and which one is better, and we will also learn about consensus methods and whether they have an impact on modification algorithms How much will we know if it is possible to know whether devices that contain small processors will be able to apply the blockchain to them and the extent of the influence of encryption algorithms the consensus and amendment to it.
Keywords:	Blockchain, Right To Be Forgotten, Right To Be Modified, Consensus Algorithms, Blockchain Applications
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	SIMPLEX AND INTERIOR POINT METHODS FOR SOLVING BUDGETARY ALLOCATION LINEAR PROGRAMMING PROBLEM AS IR4.0 STRATEGY
Author:	ALI KADHIM YAQOOB, AHMAD KADRI JUNOH, WAN ZUKI AZMAN WAN MUHAMAD, MOHAMMAD FADZLI RAMLI, NAJAH GHAZALI, MOATH ALLUWAICI
Abstract:	Increasing the complexity of solving budgetary allocation (NP-hardness problem) has led a wide range of methods to minimize the costs. Metastrategy (or often called metaheuristic) and Linear Programming (LP) are the most popular optimisation methods used in this fields. Therefore, this study provides some insights and deep understanding of the applicability LP models in industry and how to formulate Simplex Method (SM) and affine Interior Point Methods (IPM) for solving real world linear problems. Moreover, it will present a better way to deal with decision making problems through the development and comparison of the SM and affine IPM to solve LP optimization problem to maximize profit. Finally, to other researchers particularly of similar interests who are undertaking further investigation on this topic, this study can be vital as a secondary source of information and guidance towards IR4.0.
Keywords:	Simplex, Interior Point Method, Budgetary Allocation, Linear Programming, Ir 4.0
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	INTELLIGENT SYSTEM BASED ON K-MEANS AND ACO ALGORITHM WITH PARALLELISM FOR ROUTING IN LARGE AD HOC NETWORK
Author:	HALA KHANKHOUR, OTMAN ABDOUN, JÂAFAR ABOUCHABAKA
Abstract:	With the appearance of new technologies: ICT, IoT, 5G, the spread of wireless internet, increasingly growing services and the current explosion of information systems on Ad Hoc networks, it is therefore necessary to have a new efficient routing strategy especially for large Ad Hoc networks, which takes into consideration the quality of service to increase the lifetime of the network by reducing energy loss while being responsive to changes in the environment. Thus, new emerging methods to save time during the journey of the message from the source node to the destination. In this context, this article focuses on developing a hybrid model between three approaches: the best known K-mean algorithm for clustering and the most popular Ant Colony Algorithm (ACO) and using the newest parallel optimization approach today. We will first take a quick look at the solutions existing for the programming of parallel machines; it introduces a new method of calculation by the processor. However, parallelism makes it possible to create a new model capable of finding the shortest path in terms of cost and time. So, our motivation is to find the shortest path from the source node to the destination with a rapid speed of heuristics and parallelism. Details of our new approach, methods and analyzes are clearly described, well presented and relevant to the objectives of the project. To assess our model, we compared it with another recent article. The results show that our new approach can be beneficial in solving routing problems in AD Hoc networks that are large (until 1000 sensors) and which meet the user need of modern life.
Keywords:	Artificial Intelligence, NP-Complete, Parallel Computer, Ant Colony Optimization, And Ad Hoc Network.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	SECURITY-FOCUSED IS QUALITY INSTRUMENT A PROPOSED QUALITY INSTRUMENT ON ACADEMIC INFORMATION SYSTEM
Author:	INO SULISTIANI, SYAFRUDDIN SYARIF, YUSRAN, DEWIANI
Abstract:	Currently, academic-based information system software has not overall implemented quality model as an instrument of quality. Academic information system software requires quality instruments as a determinant of its quality. A conceptual model derived from a quality instrument that implements and focuses on standardizing security behavior in web application-based academic information systems is known as the Security Focused IS Quality Instrument. Quality Structure and Quality Factors of IS Quality Instruments Focused on Security and Quality Model Questionnaire Method, which is a research method in the form of questions in the form of choices consisting of Basic Quality Questionnaire Method for AISS, Basic Quality Model Questionnaire Method and Security Questionnaire Method is a quality model structure and method of determining parameters most appropriate as a description of a proposed quality instrument. The academic information system software has quality instruments and their security behavior is known as integrity, privacy, confidentiality, authentication, access control and availability. The proposed Security Focused IS Quality Instrument implements these five quality instruments and security behaviors as quality factors. Security Focused IS Quality Instrument will be provided security quality assurance for academic information system software including control over unauthorized access, personal data classification, access control to Academic Information System Software source code, data integrity compliance, access rights management, access restriction to information, service readiness of academic information system software, and classification from data and users of academic-based information system software.
Keywords:	Security-Focused IS Quality Instrument, Quality Instrument, Quality Model, Academic Information System Software
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	HYBRIDIZATION OF NEURAL NETWORKS AND GENETIC ALGORITHMS FOR BETTER CLASSIFICATION
Author:	MARYEM HOURRI, NOUR EDDINE ALAA
Abstract:	In this paper, neural networks and genetic algorithms are used in a hybrid approach in order to increase the quality of classiﬁcation problems. The proposed method allows us to design the optimal neural network architecture, while avoiding overﬁtting. In order to evaluate the eﬃciency of the proposed algorithm, experimental results in three ﬁelds are presented by comparing the indices of performance. The hybridization technique produces two desirable eﬀects, a better result and a high performance.
Keywords:	Artiﬁcial Intelligence, hybridization, classiﬁcation, Neural Networks, Genetic Algorithms, Deep Learning.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	THE CREATION OF CONTENT IN SOCIAL NETWORKS AS AN IDENTITY-FORMING ELEMENT IN YOUNG MILLENNIALS
Author:	ROBERTO GARCÍA-PINEDA, ELIZABETH ACOSTA-GONZAGA, ELENA FABIOLA RUIZ-LEDEZMA, ABRAHAM GORDILLO-MEJIA
Abstract:	This article is a case study based on the content generation strategy of a startup, e-commerce platform, dedicated to users looking for or offering shared hosting. The company's content creation strategy was analyzed. The data was obtained from the publications made through its Facebook fanpage in the period from January to December 2019. The results show that this company uses its content in order to promote an identity based on lifestyle of millennials from large cities prone to sharing an apartment, which facilitates generating engagement, and which has allowed it to position itself as the most important in its market. The virtualization of social relationships has a significant identity-forming power that allow the formation of a certain part of the identity of a subject. Information technologies have helped these companies to communicate more efficiently and mainly economically with their users. Content creation, as a marketing strategy, emerges as an easily accessible alternative based on TI, for startups to increase their reach on social networks and for their product to reach more users. However, content creation should not only be perceived as a short-term conversion marketing tool, but also as an identity-forming element through symbolic references that are meaningful to the user at a particular moment.
Keywords:	Ecommerce; Content Marketing; Millennials; Inbound Marketing; Social Networks.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	INSTAGRAM AS REGIONAL LEADERS PERSONAL BRANDING MEDIUM: A CASE STUDY OF HEAD OF SUMEDANG DISTRICT – INDONESIAS INSTAGRAM ACCOUNT
Author:	SUGIHARTI, EVVI , ARAS, MUHAMMD
Abstract:	Instagram is the most used a social media platform in Indonesia. Therefore, Instagram is a perfect place to form a favorable personal branding for prospective regional head candidates to win the regional head elections (Pilkada). Personal branding was one of the key success to winning the election, strategically performed by the elected heads of Sumedang District to maintain their positive image. Through the regent's personal Instagram account @dony_ahmad_munir and the deputy regent @erwan_setiawan54 they built a charming personal branding. This study aims to explore the process of personal branding formation of both Regent and Deputy Regent of Sumedang Regency through social media Instagram based on three aspects of Peter Montoya and Tim Vandehey theory. Those are the individual/personality aspect, promise and relationship and the eight laws of personal branding. The research used a qualitative approach, descriptive analysis in a single-case study. Descriptive qualitative approach was performed by analyzing, describing, and summarizing various conditions and situations from data collected from interviews or observations acquired through field study, in order to obtain more detailed data that is comprehensive, intense, detailed, and in-depth. The findings show that Instagram succeeded in mediating the couple's personal branding, which led Dony A. Munir and Erwan Setiawan to win the 2018 regional election as regional heads of Sumedang. Moreover, Instagram remained the main platform of personal branding when they served so that the positive image was upheld, fostering sympathy and trust from the public.
Keywords:	Branding, Instagram, Social Media, Personal Branding
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	GAIN IMPROVEMENT OF MIMO MICROSTRIP ANTENNA USING ARRAY 2X1 ELEMENT
Author:	SYAH ALAM, INDRA SURJATI, LYDIA SARI, FAHRUL SOLEHUDIN, ZIKRA AULIA
Abstract:	This paper proposes the design of a MIMO Array 2x1 element microstrip antenna for a fifth generation (5G) technology system at a frequency of 3.5 GHz. The antenna is designed using RT-Duroid R5880 substrate type with dielectric constant (εr) = 2.2 , thickness (h) = 1.57 mm and loss tan (tan ) = 0.0009. MIMO array is applied to increase the gain and directivity of the proposed antenna. The proposed MIMO antenna design has been successfully simulated with a reflection coefficient of -22 dB, an isolation coefficient of -78 dB and a gain of 12 dB at a frequency of 3.5 GHz. Furthermore, the bandwidth of the proposed antenna is 0.32 GHz (3.32 GHz – 3.68 GHz). The application of 2x1 MIMO arrays succeeded in increasing gain and bandwidth up to 47.05 % and 91.07% compared to single element antennas. The correlation and directivity of the proposed MIMO antenna has a good value with an Envelope Correlation Coefficient (ECC) of 0.0005 and a Diversity Gain (DG) of 10 dB at a frequency of 3.5 GHz. The proposed antenna design has worked according to the criteria and can be used as a recommendation as a receiving antenna in the fifth generation (5G) communication system.
Keywords:	Antenna, Microstrip, Array, MIMO, 5G Communication System
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	FACTORS AFFECTING USE BEHAVIOR IN E-LEARNING IMPLEMENTATION USING CHROMEBOOK DEVICES
Author:	TIMMY SETIADI, VIANY UTAMI TJHIN
Abstract:	With the developments in the world, especially in the world of education, technology has become a necessity. The rapid development of technology causes schools and educational institutions to compete by integrating technology in teaching and learning activities. Educators' readiness to integrate technology with conventional learning is a challenge for schools and educational institutions today. This study aimed to determine the factors that influence behavioral intention and use behavior towards e-learning using Chromebooks for educators. This study uses a modified UTAUT research model to suit the study. Through this research model, the writer tries to find a relationship between Performance Expectancy, Effort Expectancy, Social Influence, Facilitating Condition on Behavioral Intention, and the relationship between Facilitating Condition and Behavioral Intention to Use Behavior. This study used a census method for all Junior High and Senior High, with 34 respondents. Hypothesis testing is done with the SmartPLS 3 computer application. This study has five hypotheses, two hypotheses are rejected because they have an insignificant relationship. This research can be used as a reference and management consideration in implementing policies.
Keywords:	E-Learning, Chromebook, Google Classroom, UTAUT, and Educational Technology
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	HYPERPARAMETER OPTIMIZATION IN CUSTOMIZED CONVOLUTIONAL NEURAL NETWORK FOR BLOOD CELLS CLASSIFICATION
Author:	GHAZALA HCINI, IMEN JDEY, ASHRAF HENI, HELA LTIFI
Abstract:	Recently, various uses of supervised classification recognition algorithms for medical images are reported in literature. Specifically, in the current deep learning era, machine learning techniques are considered as the most important and used approach for automatic healthcare systems. In this context, many comparisons of supervised deep learning techniques, more precisely, the neural one, are proposed. The proposed approach provides a medical assistance based on relevant aspects of Machine -Learning methods applied for blood cells objects recognition while taking into consideration the property of uncertainty of this kind of image. The overview presented in this article examines the existing literature and the contributions already done in the field of intelligent healthcare systems for blood cell images classification. For this purpose, we summarize previous efforts made to define recognition process with supervised deep learning method, establishing a novel definition of personalized Machine- Learning with a major focus on the uncertainty input image. Departing from this definition, we propose and discuss the efficiency of Convolutional Neural Network for which the architecture is built and examined in detail. A Bayesian optimization of Convolutional Neural Network hyper parameters is also proposed. The main goal is to increase recognition rate while respecting time complexity. That is why an experimental comparison of Convolutional Neural Network with Support Vector Machine and K- nearest neighbor performance is discussed.
Keywords:	Blood Cell Images, Machine Learning, Deep Learning, Convolutional Neural Network, Bayesian optimization
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	IOT BASED RUZICKA INDEX TWO-STEP AUTHENTICATIVE MATYAS–MEYER MESSAGE DIGEST FOR SECURED CLOUD DATA STORAGE WITH INDUSTRIAL INTERNET OF THINGS
Author:	FLINDON W.G , DR. DIVYA S.V
Abstract:	Cloud computing is a kind of computing technology based on shared resources than the local servers to handle the different applications. Cloud computing is the process of storing data on remote servers and accessing them through the internet. Cloud provides a large amount of virtual storage to users. Security is one of the essential barriers for protecting the stored data from unauthorized user access. However, existing methods failed to improve authentication accuracy and data confidentiality. In order to improve the security level during the data storage in cloud computing, a novel technique called IoT based Ruzicka Index Two-Step Authenticative Matyas–Meyer Message-Digest Cryptography (IoT-RITSAMMMDC) is introduced in industrial applications. The main aim of IoT-RITSAMMMDC is to store the industrial data with a higher confidentiality rate, integrity, and lesser space complexity. The IoT-RITSAMMMDC consists of three major processes namely registration, authentication, and secure data storage. In the registration phase, the user's details like name, age, date of birth, etc are to be registered to the cloud server. After registering the user details, the cloud server generates an identity (ID) and password for every registered cloud user. Cloud server stores user ID and password for performing the two-step authentication using Ruzicka similarity index. Whenever the cloud user needs to store the data, the cloud user sends the ID to the server for performing the authentication process. The cloud server verifies whether the user is authorized or not by matching the cloud user ID and password. After authentication, the cloud user is allowed to store the data in a cloud server. In the IoT-RITSAMMMDC technique, the cloud server uses Merkle–Damgård Matyas–Meyer Message-Digest Cryptographic hash for storing the cloud user data in a secured manner. This in turn helps to improve the data confidentiality and reduce the space complexity. Experimental evaluation is carried out on the factors such as authentication accuracy, data confidentiality, data integrity rate, and space complexity with respect to a number of cloud user requests and data. The observed results reveal that our proposal IoT-RITSAMMMDC technique offers an efficient solution in terms of achieving higher authentication accuracy, data confidentiality, data integrity rate, and lesser space complexity.
Keywords:	Cloud Computing, Industrial Iot, Secured Data Storage, Registration, Two-Step User Authentication, Ruzicka Similarity Index, Merkle–Damgård Matyas–Meyer Message Digest
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	INNOVATIVE INTELLIGENT DATA MODEL FOR AN INTERNATIONAL LANGUAGE MORPHOLOGY SYSTEM
Author:	A. LECHHAB, Y. FAKHRI, S. ELHAKMI, N. RAFALIA, S. BENCHEHLA, M. ES-SOULI
Abstract:	We offer a unique framework foclassr representing Persian-Arabic morphology in this paper. Because this was too complicated to model exhaustively using traditional methods, it was required to develop a suitable representation formalism. As a result, we created MorphoScript, a declarative object-oriented language that allowed us to best describe the entire morphological knowledge that we could identify. The goal of the research presented here is to develop a data model for natural language morphological components and composition rules. As a result, we shall provide the fundamental elements as well as the theoretical and technical underpinnings of a language capable of replicating and helping morphologies.
Keywords:	Innovation, Natural Language processing, Morphological Knowledge Base, Intelligent Data, Learning, Education System
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	BIG DATA ANALYSIS ON YOUTUBE WITH TABLEAU
Author:	JOHANES FERNANDES ANDRY, HENDY TANNADY, ISABELLE IVANA LIMAWAL, GLISINA DWINOOR REMBULAN, RUSTONO FARADY MARTA
Abstract:	YouTube is the second biggest search engine on the web and a platform with features where users can post, view, comment, and link to videos. YouTube has more than a billion active users where users can see Recommended Channels, which are based on videos that users watch frequently. Furthermore, Trending is based on video trending on the number of clicks the video gets every day. This study aims to provide insight into how understanding and implementation of Big Data on YouTube. In the current era, Big Data is gaining much interest because of the opportunities and benefits felt to be unprecedented. Big data analytics can leverage business change, enhance decision-making by applying advanced analytic techniques on big data, and reveal hidden insights and valuable knowledge. To better understand the changes brought about by big data, this paper focuses on data analysis using data visualization. In analyzing YouTube trending videos, we use tableau software to help visualize the data that has been obtained. The following are some of the charts used in this analysis, such as pie charts, area charts, horizontal bars, highlight tables, treemaps, and mapping. Data Visualization can help YouTube, and its users identify which areas need to be improved, which factors affect users' satisfaction and dissatisfaction, and what to do and know to develop parts lacking and pay attention to today's users' needs. Visualized data can give a better prediction of current trending topics or videos and future growth. It can be used to influence our decision-making.
Keywords:	Big Data, YouTube, Data Analytics, Data Visualization
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	REMOVING ARTIFACTS IN EEG DATA BASED ON WAVELETS AND NEURAL NETWORKS
Author:	PADMINI CHATTU , Dr. C.V.P.R. PRASAD
Abstract:	Electroencephalogram (EEG) is a set of cardiovascular activity that the electrical capacity of cerebral exercise consists of reduced amplitude, and not as much frequency ranges between 4 to 60 Hz, which may readily mix up distinct non-cerebral signs and other ecological noise signs. The extraction of genuine cerebral signs from your infected EEG indicate could be the primary barrier in clinical investigation. Noise removing from recorded EEG indicate is the most required for far better diagnosis of mind ailments. Throughout recoding period, EEG signs are often polluted by numerous racket and distortions thanks several artifacts. These noisy EEG signs may possibly cause erroneous prognosis of brain ailments. There are plenty of methods accessible to take out the noises out of EEG signs. However, these methods are not able to take out the noises absolutely. But they could diminish the noise from EEG signs therefore your medical professionals can forecast mind ailments. The operation of all the existent systems in electromyograph artifact removing has been constrained and endured against over-fitting issue. Right here we present a Nevertheless they could diminish the noise from EEG signs therefore the medical professionals can forecast mind ailments. This work allows to reduce the noises by pre-processing brand new wavelets that are numerically steady and orthogonal foundations will probably be suggested making use of Morelette wavelets and categorized with convolutional neural networks (CNN). The performance of the proposed method is compared without preprocessing of the existing methods. From the results the proposed method with pre-processing (morlet wavelet de-noise) (%) achieves accuracy with maximum percentage of 88.175, Precision with maximum of 94.4%,recall with minimum of 83.94 %, FPR with minimum of 6.39 % and F-Measure with maximum of 88.86% achieved .
Keywords:	EEG, Noise removal, Morelette wavelets, CNN, SNR, MSE
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	DELAY REDUCTION THROUGH SECONDARY USER COOPERATION IN SPECTRAL HANDOFF
Author:	CESAR A. HERNÁNDEZ S., FREDY H. MARTÍNEZ S., DIEGO A. GIRAL R.
Abstract:	An inadequate selection of spectral opportunities within a cognitive radio network can lead to an increase in the spectral handoff rate and thus increase delay in the communication of the secondary user. The purpose of the present article is to assess the performance of the delay level in a cognitive radio where secondary users cooperate by exchanging information over the spectral occupation frequency band. Using the SAW and Naïve Bayes algorithms for decision-making tasks, the obtained results reveal a significant reduction in the delay of the communication from secondary users when they cooperate between them.
Keywords:	Cooperation, Delay, Spectral decision, Handoff, Cognitive radio.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	A LATENCY-IMPROVED BLOCKCHAIN IMPLEMENTATION MODEL FOR NATION-WIDE ELECTRONIC VOTING SYSTEM
Author:	APEH JONATHAN APEH, CHARLES K. AYO, AYODELE ADEBIYI
Abstract:	The application of blockchain technology has been considered a breakthrough for the electronic voting system research domain, given that the technology has the potentials to fix the issues of ballot confidentiality, single point of failure, and compromise of election results integrity that have been regarded as the bane of electronic voting systems. However, blockchain technology itself is not without some concerns. Chiefly amongst these concerns are latency and scalability. This paper aims to showcase existing efforts to improve the latency of a blockchain network and to present a Blockchain Implementation Model that improves the latency concern in electronic voting systems, using the Nigeria’s Independent National Electoral Commission as a case study. The study evolved a latency-improved blockchain model that showcases the latency performance of the proposed blockchain-based e-voting system. The result showed a 99.36 percent improvement on the existing blockchain-based e-voting system.
Keywords:	Blockchain, Election, Electronic Voting System, Latency, Suffrage
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	COGNITIVE PROPERTIES OF CYBERSECURITY: POSTQUANTUM CRYPTOGRAPHY
Author:	AKTAYEVA AL., MAKATOV E., 3YESMAGAMBETOVA G., KUBIGENOVA A., NIYAZOVA R., ZAKIROVA A.
Abstract:	This paper provides background information on post-quantum security. It explores the security threats against communication security and particularly against key exchange that is enabled by the development of quantum computers. The applied and theoretical aspects of quantum-cryptographic technologies are considered. The systematic analysis of quantum algorithms, quantum cryptography, and quantum hashing are presented. The interrelated elements that make up to the concept and content determined by the application of quantum cryptography are analyzed. The development of specialized quantum computers focused on solving cryptographic problems is justified. Terms which must be taken into account in the selection of elliptic curves for cryptographic applications are determined. The proper concept vehicle over is brought, in particular, the concepts of singularity and super singularity are determined for elliptic curves and theoretical positions, lying in their basis, are examined.
Keywords:	Elliptic Curve, Singularity, Super-singularity, Quantum Cryptography, Qubit, Cognitive Technology.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	ANALYSIS AND EVALUATION OF SPECTRAL DECISION WITH MULTI-USER ACCESS USING MARKOV CHAINS IN COGNITIVE WIRELESS NETWORKS
Author:	DIEGO ARMANDO GIRAL-RAMÍREZ, CESAR AUGUSTO HERNÁNDEZ-SUAREZ, FREDY HERNAN MARTÍNEZ-SARMIENTO
Abstract:	The increase in wireless applications, limited spectrum resources and the fixed allocation policy have caused the radioelectric spectrum to present shortage problems. Cognitive radio (CR) emerged as a solution to solve the problems of allocation and spectrum scarcity, it is a dynamic allocation technique, which identifies spectral opportunities and then automatically configures the system according to the electromagnetic environment. One of the most important aspects in cognitive radio networks (CRN) is the spectral decision function, which involves challenges and a high level of complexity, due to the need to work with real characteristics, such as multi-user spectral allocation and network externality. This work analyzes the decision-making process in CRN with multi-user access using Markov chains. The analysis is performed for the access of 3 users based on the number of total accumulated handoffs, number of total accumulated failed handoffs, average bandwidth, average delay, and average Throughput. The results show that the best performance is for the scenario with 1 user, the lowest performance is for the scenario with 3 users. The results obtained indicate that the users opportunistically used a greater bandwidth, maximizing the effective transfer capacity without affecting the transmission of the licensed users.
Keywords:	Cognitive Radio Networks, Decision-making Model, Markov Chains, Multi-user Access, Spectral Mobility
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	DEEP ARTIFICIAL NEURAL NETWORKS OPTIMIZATIONS USING SECOND-ORDER NEWTONS METHOD
Author:	RAWAN GHNEMAT, AHMAD GHANNAM, ABRAR M. AL-SOWI
Abstract:	Optimization is the process of finding parameters that return the maximum or minimum value of a function, where the function symbolizes the effort needed or the desired benefit. First-order stochastic gradient (SG) methods are often used to solve deep learning models that involve a hard non-convex optimization problem. Although second-order methods can ensure faster convergence, they have been less explored because processing time and costs are high. Optimizing deep learning models is a challenging problem; many deep learning companies spend a lot of their resources on training deep models. This paper proposes an implementation and evaluation of Newton's second-order optimization method, Hessian Free Optimization (HFO), on fully connected feed-forward networks, and enhances the method by the integration with some acceleration techniques such as Momentum and Root Mean Square Propagation (RMSProp). The paper also proposed a hybrid algorithm capable of combining two-degree orders, first-order, and second-order optimization methods. The hybrid algorithm can achieve better convergence (5% better in testing loss) compared to first-order methods with approximately the same time consumption.
Keywords:	Machine Learning, Optimization Method, Deep Neural Network, Newton’s Method, Deep Learning Models, Hessian Free Optimization (HFO).
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	VOLTAGE SOURCE BASED HVDC WITH FACTS AS ANCILLARY CONTROLLER USING FUZZY LOGIC CONTROLLER
Author:	PRABHAKARA SHARMA. P, P. KANTA RAO, and K. VAISAKH
Abstract:	Increasing demand of energy becomes major issue in emerging technology to deliver cost effective electrical power. By using HVDC systems we can achieve transmission of power over long distance with minimal losses with utilization of proper controller like flexible alternating current transmission (FACTS) devices. The main application of HVDC system is large amount of power transfer over long distance with view of reliability, cost and technical performance. FACTS devices are composed of static equipment utilized for increase power transfer capability and enhancing controllability of line. It consists of advance power electronic devices with combination of series and shunt converter called UPFC for facilities fast acting reactive power compensation in tie lines of HVDC network. The proposed system identifies improved power transmission capability through conventional and advance control schemes, simulation study is made with application of PI and Fuzzy logic based UPFC on HVDC network. The conventional controller cannot compensate power fluctuations and time constant of active and reactive power which is integrated in controller of UPFC [2]. The system model is analyzed for various fault conditions by maintain UPFC fixed which reduces the magnitude of the fault current and oscillations in excitation voltage.
Keywords:	High-voltage dc transmission (HVDC), Faults in HVDC system, Flexible ac transmission system (FACTS), PWM Power transfer controllability, Fuzzy Logic Controller
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	CORRECTION OF KAZAKH SYNTHETIC TEXT USING FINITE STATE AUTOMATA
Author:	KARTBAYEV A., MAMYRBAYEV O., KHAIROVA N., YBYTAYEVA G., ABILKAIYR N., MUSSAYEVA D.
Abstract:	In this paper we investigate the correction of generated synthetic text for resource-poor languages. In most cases, this synthetic text contains many errors that need to be carefully checked and corrected by additional tools. These errors must be corrected automatically to avoid degrading the performance of the system. Our approach to automatic error correction is based on the use of finite automata to suggest candidates for correction of the misspelled word. After selecting correction candidates, a language model is used to assign points to the correction candidates and choose the best correction in a given context. The proposed approach is language-independent and requires only dictionary and text data to construct the language model. The approach was evaluated in Kazakh and achieved an accuracy of 91%.
Keywords:	Synthetic Data, Language Model, Finite State Automata, Hidden Markov Model, Text Generation.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	SENTIMENT ANALYSIS OF AMAZONS REVIEWS USING MACHINE LEARNING ALGORITHMS
Author:	SANA NABIL, JABER ELBOUHDIDI, MOHAMED YASSIN CHKOURI
Abstract:	Sentiment analysis also called opinion mining, is the field of study that analyses people’s opinion, sentiment, evaluations, appraisals, attitudes and emotions towards entities such us services, organizations, individuals, issues, events, topics and products. The fast evolution of Internet-based applications like websites, social networks, and blogs, leads people to generate enormous heaps of opinions and reviews about products, services, and day-to-day activities. Sentiment analysis poses as a powerful tool for businesses, governments, and researchers to extract and analyze public mood and views, gain business insight, and make better decisions. There are many approaches to classify the sentiment, approaches based on machine learning or lexicon-based approach. In this article we will discuss the different approaches of sentiment analysis, and we will compare the performance of the different machine learning algorithms. In this comparative study we will use the naïve Bayes, Support vector Machine, the Decision Tree and the Logistic regression algorithms to analyze the sentiments in amazon’s reviews data. The main objective is to analyze the large number of reviews expressed in amazons in order to deduce the different feelings expressed in it, positive, negative or neutral. The main goal of this work is to achieve the best result of sentiment analysis. So, to analyze and classify the data we will start by preprocessing the data then the features extraction after that the sentiment classification using the machine learning algorithms and finally the evaluation of the algorithms, using Spark and Scala language for implementing the algorithms. The final results show that the SVM classifier achieved 100% accuracy, Naive Bayes classifier achieved 95% accuracy, the Logistic regression 97% and the Decision Tree classifier achieved 75% accuracy.
Keywords:	Sentiment analysis, Opinion mining, Machine learning, Big data, Lexicon-based approach, Spark, Amazon, Naïve Bayes, SVM, Decision Tree, Logistic regression.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text

Title:	METHODS FOR SUBSTANTIATING DECISIONS ON THE CHOICE OF THE COMPOSITION OF TELECOMMUNICATIONS EQUIPMENT
Author:	AIDANA ZHANASBAYEVA , AKYLBEK TOKHMETOV, AKZHIBEK AMIROVA
Abstract:	Telecommunications is an important component of modern infocommunication. When designing them, there are requirements for strict consideration of a set of requirements that contradict their quality. This determines the need to use multidimensional optimization methods when choosing design solutions from a variety of suitable options. Previously, when designing telecommunications equipment, only strictly permitted design options were selected that meet specified quality constraints. With the increasing complexity and cost of the designed telecommunications equipment, it is necessary to find optimal design solutions. This presents the main aspects of the choice of technical means of building a network, a set of indicators for their selection is presented. Using the example of the choice of switches, the problem of comparative assessment and their selection is solved using the method of analysis of hierarchies and network analysis method. The use of such a DSS will significantly reduce the complexity of calculations, increase the efficiency of decision-making and their quality and, ultimately, increase the success of the implementation of planned projects at the early stages of their justification.
Keywords:	Analysis Of Hierarchies, Criteria, Network Analysis Method, Switch, Telecommunication Networks, Telecommunication Equipment.
Source:	Journal of Theoretical and Applied Information Technology 30^th November 2021 -- Vol. 99. No. 22 -- 2021
Full Text