		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
Feburary 2022 | Vol. 100 No.04

Title:	COMPARATIVE STUDY OF INFORMATION SECURITY EVALUATION MODELS FOR INDONESIA GOVERNMENT
Author:	MUHAMMAD RADITYA PUTRA DEWANTO , TANTY OKTAVIA, DAVID SUNDARAM
Abstract:	The stream in which every bit of information shared and viewed has been rapidly increasing at the current era, with speed like never unlike in previous generations. Because of that, there is dire need to effectively secure this information stream in order to prevent compromise from any risk and threats. This is particularly true for government sector that holds highly classified information crucial for the country operations. Indonesia government strive to protect and to better maintain information through an adoption of a robust security implementation within the many bodies of government throughout the country, however for an implementation to be robust the first time is near impossible. Robustness is achieved through rigor evaluation that actively assess the performance and effectiveness of that implementation to know its resiliency in withstanding attacks and efficient in its application. For this reason, KAMI Index is developed in order to evaluate and assess the maturity and the readiness of information security in each government agency, but does it reliable and accurate? To answer, this research will make a comparison to an existing evaluation frameworks or models proposed by other researchers that study the topic of information security with regards to different aspects that exists within it. By making a comparison, an analysis for an existing model what aspects that they do better or best compared to KAMI Index can be perform so that a suitable recommendation and suggestion can be made. This research will be conducted through Systematic Literature Review (SLR) methodology, this paper will also provide an explanation of alternatives information security evaluation models or frameworks, and the reason why these models can be used to improve or even replace the KAMI Index model. Results from this research includes an alternatives models to KAMI Index and identified IS aspects crucial for evaluation.
Keywords:	KAMI Index, Information Security, Information Security Evaluation, Government, Comparative Study
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	DETECTION OF PLAQUES IN ARTERY WALL USING INTRAVASCULAR ULTRASOUND IMAGES FOR DIAGNOSIS OF CORONARY ARTERY DISEASES
Author:	K V ARCHANA, DR R VANITHAMANI
Abstract:	In past two decades, the Intra Vascular Ultrasound (IVUS) imaging technique is utilized for detecting the calcified plaque in the coronary artery aided with deep learning techniques. However, the existing approaches fall on computational complexity, time consumption and poor accuracy of plaque localization. In this paper, a deep CNN based plaque detection framework is proposed to tackle the issues in the existing approaches. Initially, the region between lumen and media contour is segmented with the terminus sector segmenting approach based on pixel concentration divergence and the texture features. Then the discriminative features are extracted through the meticulous feature extraction approach via construction of contraction path in multi-scale CNN. Finally, the location of the plaque has been identified with unambiguous detection and localization approach, whereas the expansion path is constructed for plaque detection. The experimental result shows the effectiveness of the proposed framework and the results are compared with other existing approaches.
Keywords:	Intravascular Ultrasound (IVUS) Images, Plaque, Deep Learning, Coronary Artery, Segmentation, Multi-Scale Deep CNN.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	TWO-WHEELED BALANCING ROBOT WITH ANDROID NAVIGATION SYSTEM
Author:	BAKTI DWI WALUYO, DADANG MULYANA, BAHARUDDIN, ARIF RAHMAN, MUHAMMAD AULIA RAHMAN SEMBIRING
Abstract:	The two-wheeled balancing robot is a robot that can move with two wheels on the left and the right. However, in order to maintain balance, the robot needs to use both wheels to move. We, therefore, need control to move the two-wheel robot so that it can stand in balance. This system has two inputs, namely accelerometers, used to measure angular acceleration (m/s2) and gyroscopes for measuring angular velocity (rad/s). The accelerometers and gyroscope values were calculated using the complementary filter method to obtain the angle values. The angle obtained is then compared with the setpoint, which is 0°. The difference between the setpoint and the complementary filter angle is processed using the Proportional Integral Derivative (PID) control method. The PID control process results are used to regulate the rotation of the wheel drive motor in the robot. The direction of the wheel drive motor rotation will go forward if the complementary filter angle is less than zero and reverse if it is more than zero. Based on the tests that have been done, the balancing robot can withstand an angle range of -1.5° to 1.5°. While the PID constant value is Kp = 1.5, Ki = 0.2, and Kd = 0.05 and the coefficient value on the complementary filter algorithm is α = 0.96. The two-wheeled balance robot can be operated with an Android smartphone via Bluetooth properly and can move in balance by lifting a maximum load of 40 Kilograms.
Keywords:	Balancing Robot, Complementary Filter, Android Smartphone, PID
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	THE EFFECTIVENESS OF TRAINING FUTURE COMPUTER SCIENCE TEACHERS IN COMPUTER NETWORKS BASED ON NETWORK MODELLING
Author:	YERMAKHAN ZHABAYEV, YESSEN BIDAIBEKOV, EVGENIY KHENNER, SHIRINKYZ SHEKERBEKOVA, ADILBEK ZHANBYRBAYEV
Abstract:	The study covers and substantiates the effectiveness of training future computer science teachers in computer networks based on network modelling. The analysis of academic and methodological literature has shown that in the training of computer science teachers, computer networks are studied in the aspect of information modelling of their structures, while modelling the processes of their functioning is not given due attention, despite the possibility of its use in the organisation of training. The purpose of the study was to provide practical confirmation of the effectiveness of training future computer science teachers in computer networks based on network modelling. Training in computer networks based on network modelling can play a significant role in improving the effectiveness of training students in the specialisation “Computer Science”. A pedagogical study was conducted based on the formation of control (40 people) and experimental (39 people) groups from among third-year students. In the experimental group, training in the discipline “Computer Networks and Web technologies” was carried out using the same means of informatisation, selected taking into account the specifics of methodological training systems. Comparative diagnostics of the students' knowledge level was carried out using methods of mathematical statistics and specially developed test tasks. The study established that the development and implementation of the proposed teaching methodology provides an opportunity for full and high-quality training of future computer science teachers in the field of computer networks, allowing them to solve professional problems in the design, maintenance, configuration, and administration of computer networks, and contributes to the development of specialised competences in this field. The effectiveness of training future computer science teachers in computer networks based on network modelling has been experimentally confirmed.
Keywords:	Software environment, Computer science teacher, Network technologies, Teaching methods, Informatisation.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	TEXT CLASSIFICATION USING RECURRENT NEURAL NETWORK AND SUPPORT VECTOR MACHINE ON A CUSTOMER REVIEW DATASET
Author:	BAMGBOYE PELUMI OYELAKIN, AYODELE ADEBIYI, BABATUNDE GBADAMOSI, AROWOLO MICHEAL OLAOLU, AFOLAYAN JESUTOFUNMI, ADENIYI ABIDEMI EMMANUEL
Abstract:	Text is constantly generated from our day to day use of the internet, and these large amounts of data generated are mostly unfiltered. In most cases, unstructured data needs to be classified to improve the rate at which a given text is understood. Text classification is a branch of Natural Language Processing that is used to create a distinction in unstructured text data. Machine learning is widely used in the classification of textual data as a result of its ability to create complex prediction functions dynamically. Similarly, statistical models are commonly used to classify textual data because they can describe the relationship between two or more random variables. In an e-commerce environment, sentiment analysis is usually a challenging task. Machine learning techniques of Naïve Bayes and Decision Tree have limitations in sentiment analysis performance. In this study, a comparative study of Recurrent Neural Network (RNN) and Support Vector Machine (SVM) is done for classification of customer product review dataset on whether they have positive or negative comments. This study tends to enhance the traditional RNN with the use of Long Short Term Memory (LSTM) in order to achieve optimal result. The result of this work shows that RNN with an accuracy of 94.86% is better than the state of art SVM with an accuracy of 86.67%. The result of this work is not only better in terms of accuracy, also in other performance metrics measured.
Keywords:	Recurrent Neural Network; Support Vector Machine; Text Classification; Review
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	UNDERSTANDING FACTORS DETERMINING THE USE OF MOBILE APPS BY CUSTOMER: CUSTOMER MOBILITY AS AN EXTENSION CONSTRUCT OF UTAUT2
Author:	ALDI WILMAN, WAHYU SARDJONO
Abstract:	MyIndiHome is a mobile apps developed by Telkom with the hope that it will further improve the quality of service to IndiHome customers. This application can be used by customers for requests for new installations, complaints of service interruptions, requests for additional services, service checks, and others where previously this could be done by customers by calling 147 or coming physically to Plasa Telkom which certainly makes customers hassle and not simple. The purpose of this study is to evolve a research model based on the UTAUT2 and then to test it empirically to determine factors that influence customer' intention to use MyIndiHome apps. This study used an online questionnaire survey namely Google form to collect data from IndiHome customers who have installed MyIndiHome in Medan city and obtained 400 respondents who filled out the survey and were declared valid. The data were analyzed utilizing the PLS method with SmartPLS software. This study prescribed that habit, performance expectancy, customer mobility, and hedonic motivation were factors that determine on the behavioral intention of customers to use MyIndiHome and confirmed the relationship between behavior intention to use and use behavior was significant (p<0.05). However, customer’s behavioral intention to use MyIndiHome was not determined by social influence, effort expectancy, and facilitating condition. Additionally, this study revealed that facilitating condition did not determine the use of MyIndiHome (p>0.05).
Keywords:	MyIndiHome, UTAUT2, Intention to Use, Customer Mobility, Use behavior
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	DESIGN AND IMPLEMENTATION OF A 3-TASK CONSTRUCT FOR MANAGING REDUNDANT FILES
Author:	EMMANUEL CHUKWUDI UKEKWE, HYACINTH AGOZIE ENEH
Abstract:	The operating system ensures efficient memory and disk space management which contributes a lot to computing speed. However, not all users have the technical expertise to make use of operating system tools for disk space management. This paper therefore proposes and implements a 3-task user friendly construct for managing redundant files which inadvertently occupy so much space in the computer disk and slow down the system. Redundant files such as duplicate files, temporary files and dormant files which are often taken for granted are detected. The construct employs the concept of hashing by making use of python hashlib.SHA-1 to detect duplicate files while dormant files are identified using file attributes such as date of creation and access date. The deduplication construct earmarks redundant files for deletion or compression in order to free disk space. Algorithms for implementation of the constructs are presented. The construct was implemented using python programming language. In order to test the efficacy of the construct in detecting file duplicates, the New York Times Comments for March, 2018 dataset was extracted from www.kaggle.com and used for that purpose. The simulation recorded an efficiency of 99%. The Construct is designed to provide alternative user friendly disk management support tools for computer users other than that provided by Operating systems.
Keywords:	Deduplication, Duplicate, Redundant, Disk-Space, Compress, Hashing
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	PERFORMANCEOF HETEROGENEOUS ENSEMBLE APPROACH WITH TRADITIONAL METHODS BASED ON SOFTWARE DEFECT DETECTION MODEL
Author:	Dr. E.SREEDEVI, Mrs. D. SREE LAKSHMI, Mrs. A. Divya, Dr. P.V.S.S. GANGADHAR, Ms. V. PREMALATHA
Abstract:	Identifying defective modules from the developed software is very much indispensable for constructive management and control of software testing. Software defect detection models helps a lot in effective allocation of limited testing resources. In this context several software defect detection modelling has been proposed by using machine learning algorithm. The main intention of heterogeneous ensemble model is to regulate each of its specific model strengths and weakness undoubtedly leading to the finest passable decision being taken overall. In this paper, we proposed heterogeneous ensemble learning, a defect detection model in which different learners are combined to form heterogeneous ensemble learning. Performance of individual learning models is compared with our proposed heterogeneous ensemble models, and it shows that our model is giving a better accuracy then the models developed by individual learning models. The evaluation results show that our proposed model achieved up to 98% accuracy which is more than the evaluation accuracy achieved by individual learning models.
Keywords:	Software Defect Detection Models, Feature Selection, Ensemble Learning, Accuracy, Defect Detection.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	DEEP REINFORCEMENT LEARNING TO MULTI-AGENT DEEP REINFORCEMENT LEARNING
Author:	MEHDI SAMIEIYEGANEH, PROFESSOR RAHMITA WIRZA BT O. K. RAHMAT, DR FATIMAH BINTI KHALID, DR KHAIRUL AZHAR BIN KASMIRAN
Abstract:	Machine Learning (ML) has been a remarkable success in the last few years, which Reinforcement Learning (RL) has seen rapid growth with new techniques that have revolutionized the area. Sequential -Decision Making tasks are a main topic in ML, these are tasks based on deciding, the sequence of actions from experience carry out in an environment that is uncertain to achieve goals In this paper, we discuss topics such as Deep Learning (DL) and Multi-agent Systems (MAS) that are used in RL as Deep Reinforcement Learning (DRL) and Multi –Agent Deep Reinforcement Learning (MADRL). In fact, overall goal in this paper is a comprehensive explanation of the various Deep Reinforcement Learning (DRL) algorithms, and its combination with Multi-Agent methods. To achieve this goal, in section 2, we have reviewed the articles that are the founders of these methods and have also used various methods in the field of MADRL. In the third section, we look at the RL and important algorithms that exist in this area. In the fourth section, we study DRL and explain the reasons for which different algorithms have been developed in this regard. In the fifth section, we will look at the MADRL and address some of the challenges and work that has been done in this area..At the end of this section we mentioned some important papers in the table with their methods, which is used. The sixth section provides an explanation of the research currently being done by the authors, as well as interesting topics for researchers to use in future research. Given that we have tried to explain the concepts in a simple and straightforward way in this paper, we hope that the materials mentioned are suitable for novice researchers in this field.
Keywords:	Machine Learning; Reinforcement Learning; Deep Learning; Deep Reinforcement Learning; Multi-Agent Systems; Multi –Agent Deep Reinforcement Learning.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	A HYBRID RECOMMENDER FRAMEWORK FOR SELECTING A COURSE REFERENCE BOOKS
Author:	SAMAR SALEH EBRAHEEM ALQALLAF, WALAA MOHAMED MEDHAT, Prof.Dr. TAREK AHMED EL-SHISHTAWY
Abstract:	Recommender systems are receiving great attention these days, as various researchers and major companies are conducting continuous research in this field. Companies like Google and Amazon have provided different effective models for video recommendation systems, but the educational field is poorly studied as other researchers explained. Different researchers proposed various approaches showing the challenges related to recommender systems and have proposed various effective recommender systems. This paper aims to propose a hybrid recommender framework that can recommend educational courses' books to study with high accuracy and efficiency. The proposed framework is a hybrid unified approach that helps those who desire to be taught to get suitable books related to a specific course description when a course description is used as an input. This work proposes three different recommendation algorithms for building a hybrid recommendation system. One of the algorithms uses an association rule algorithm to automatically and intelligently guide the end-user to find the most relevant materials.
Keywords:	E-Learning, Recommender System, Association Rule, Data Mining
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	PERFORMANCE IMPROVEMENT OF A NEW MAC PROTOCOL FOR ULTRA WIDE BAND WIRELESS SENSOR NETWORKS
Author:	ANOUAR DARIF, HICHAM OUCHITACHEN
Abstract:	Wireless Sensor Networks (WSN) emerges as a useful networks type that completes monitoring systems. Energy, Packets Delivery Ratio (PDR) and Latency optimization in such kind of networks is essential. Further, integrating Network Coding (NC) with efficient scheduling and synchronization in the Medium Access Control (MAC) layer improves nodes functioning and copes with many problems. Mainly, essential ones are in relation with energy waste and transmission lose and collision. In this work, the benefits while introducing the network coding technique are demonstrated and evaluated. Mainly, regarding the energy consumption, PDR and Latency improvement in the MAC layer of Impulse Radio-Ultra Wideband (UWB) based WSN. Particularly, the network coding implementation is performed in the SWIMAC as a new MAC protocol and the simulation experiments are run in order to assess its resulting effect.
Keywords:	WSN; IR-UWB; SWIMAC; ALOHA; WideMac; Network Coding; Energy consumption; PDR; Latency.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	UTILITY ON ETLE AND TRUST ON ETLE AS A BOOSTER OF SOCIAL ORDER AND HABIT THROUGH TRAFFIC COMPLIANCE AND AWARENESS BASED ON INFORMATION TECHNOLOGY
Author:	M. FAHRI ANGGIA NATUA SIREGAR, ABDUL HAKIM, MARDIYONO3, SOLIMUN
Abstract:	This study aims to determine the effect of Utility on ETLE and Trust on ETLE on Social Order and Habit mediated by compliance and awareness for road users, especially in Jakarta. This study uses a quantitative approach . The research method used is a survey by taking samples from the population. The population in this study were all four-wheeled drivers and the sample in this study were some four-wheeled vehicle drivers who passed the Jalan Merdeka Selatan Intersection, Gambir, Central Jakarta. Data analysis used descriptive analysis and data analysis used SEM method with WarpPLS approach. This study found that utility on ETLE and trust on ETLE had a significant and positive effect on compliance, awareness, social order, and habit. Compliance has a positive and significant effect on social order, and awareness has a significant effect on habit. The novelty of this research is the use of compliance and awareness variables in the traffic sector in making the research model. In addition, this research is also expected to reconstruct and develop a more comprehensive and precise model of social order and habits in traffic.
Keywords:	Utility ETLE, Trust on ETLE, Compliance, Awareness, Social order
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	ESTIMATION OF DIGITAL COMPLEX SIGNAL DELAY IN TIME DOMAIN USING POLYNOMIAL INTERPOLATION
Author:	OKSANA A. GUSCHINA
Abstract:	The paper presents improved methods for estimating the complex discrete-time signal delay not multiple of the sampling period. The proposed methods are based on polynomial interpolation of a discrete complex cross-correlation function in the neighborhood of its maximum. This allows to achiving higher accuracy without iretative procedures, engaged in numerical methods. The methods are implemented as high speed algorithms, which guarantee the real-valued number for time delay estimations when processing digital complex signals. A comparative analysis of the proposed methods has been performed using interpolations by second and third order polynomials. An analytical solution for the correction applied to the time delay estimation for the method on the basis of absolute values when using third order polynomial interpolation for uniform sampling of the cross-correlation function has been obtained. The conducted numerical simulation by an example of a stationary random process generated by the first order autoregressive model made it possible to quantitatively estimate the accuracy of time delay estimation when using the proposed methods.
Keywords:	Digital Signal Processing, Time Delay, Cross-Correlation Function, Polynomial Interpolation, Root Mean Square Error.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	ENERGY BALANCING ALGORITHM FOR WIRELESS SENSOR NETWORK
Author:	GHASSAN SAMARA, MOHAMMAD A. HASSAN, MUNIR AL-OKOUR
Abstract:	A Wireless Sensor Network (WSN) is made up of a large number of nodes that are spread randomly or on a regular basis to detect the surrounding environment and transfer data to a base station (BS) over the Internet to the user. It is widely used in a variety of civil and military concerns. Because the sensor has limited battery capacity, energy efficiency is a critical issue with WSNs. As a result, developing a routing protocol that decreases energy consumption in sensor nodes to extend the lifetime of the WSN using an intelligence algorithm has become difficult. LEACH is the first hierarchical routing protocol that divides the WSN into clusters to reduce energy usage. However, it has reached its limit in selecting a suitable cluster head and the sensor nodes to be joined, as well as their quantity. Thus, this research proposes an algorithm called Wireless Energy Balancing algorithm (WEB) that works on energy balancing distribution by identifying a suitable cluster head with minimum distance and high energy. Then it uses the knapsack-problem as a novel algorithm to design the cluster members. The simulation results demonstrate that the WEB algorithm outperforms LEACH by 31% in terms of energy conservation and WSN lifetime extension.
Keywords:	Web, Energy Balancing, Clustering, Wsn, Leach.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	NON-LINEAR MODEL FOR COLOUR CORRECTION OF UNDERWATER OBJECTS BASED ON LIGHT ABSORPTION ESTIMATION
Author:	PUJIONO, PULUNG NURTANTIO ANDONO, RICARDUS ANGGI PRAMUNENDAR
Abstract:	The underwater objects provide a different quality of colour when taken from the sea's surface or in the air. The colour quality of underwater objects is deficient due to colour distortion. The leading causes of colour distortion of underwater objects are discoloration and light scattering. The colour change of underwater objects is also very dependent on the intensity of the underwater image and the wavelength of each colour of the underwater object. This article used the non-linear model approach to improve the colour quality of underwater objects based on light absorption estimation. It examined the relationship between the colour intensity of objects on the surface with a certain depth under the sea, using least squares to determine specific coefficients. Determination of coefficients in a non-linear approach using least squares. Measurement of the colour quality of underwater objects using Peak Signal Noise to Ratio (PSNR), wherein a non-linear approach the colour of underwater objects produces a PSNR value of 19.84. Visually, the results of this non-linear approach based on light absorption estimation, the quality of underwater objects up to a depth of seven meters below sea level has a colour quality similar to the colour of objects on the sea surface.
Keywords:	Non-Linear Model, Least Square, Colour Quality, Underwater Object, Light Absorption
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	PHYSICAL INTERNET: A REVIEW OF MATHEMATICAL PROGRAMMING MODELS
Author:	KHALIL JHARNI, MUSTAPHA HLYAL, JAMILA EL ALAMI
Abstract:	The development of digital technology has facilitated the growth of e-commerce and the recent pandemic has changed the purchasing process and strongly impacted supply chains. These must adapt in order to keep their performance level. As a response to this challenge, the concept of the Physical Internet, which is based on the Digital Internet, looks promising. Hence, we can take advantage of advances in information technology to develop the Physical Internet and to accelerate its implementation. In this paper, we propose a review of the Physical Internet literature based on mathematical programming to answer the following questions: (1) what is the coverage of nodes and links in a supply chain by the current literature on the Physical Internet? (2) What mathematical programming models and formulations are used for modeling and optimizing the problems of supply chains in the context of the Physical Internet? (3) How are sustainability aspects addressed by the proposed models? Following the qualitative content analysis method, we worked in detail on 60 publications up to 2022. We studied them through three categories and presented the quantitative and qualitative results. These findings led us to propose our perception of the supply chain in the context of the physical Internet and in particular the issues of considering a supply network instead of a supply chain. Finally, we raised questions and proposed research opportunities before concluding.
Keywords:	Physical Internet, Supply Chain, Logistics, Mathematical Programming, Literature Review
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	FACTORS INFLUENCING USER BEHAVIOR ON AN ONLINE EDUCATION PLATFORM BASED ON B2B2C MODE: FROM THE PERSPECTIVE OF ART EDUCATION
Author:	HOU SHAOPENG, OOK LEE, JONGCHANG AHN
Abstract:	This research analyzes whether the course design and follow-up services have an impact on customer satisfaction when an arts education institution applies the business to business to customer (B2B2C) platform for online education. The guidance on customer behavior of the B2B2C online education platform proposed in the previous literature is adopted to adapt the model framework, and provide guidance for arts education institutions when using this type of platform for online education. Questionnaires are distributed offline. In this research, 399 valid questionnaires are used for quantitative analysis, and the proposed hypotheses are verified through correlation and multiple regression analyses. The results show that excellent course arrangement and active after-school assistance behaviors have a significant positive impact on customer satisfaction. The course content of the product owner mainly plays a role in assisting decision-making during the trial phase. In the use phase, the product side can establish a community based on the analysis results, conduct follow-up one-to-one coaching, and carry out regular assessments, all of which can effectively improve customer satisfaction and expectation confirmation after class. For the invalid hypotheses, it is significant for arts education institutions to circumvent them reasonably when practicing education.
Keywords:	B2B2C platform, Course Design, After Services, E-learning, Art Education, Influencing Factor
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	INTERNET OF THINGS (IOT) FOR SMART CITY, AGRICULTURE AND HEALTHCARE
Author:	KAMAL ELHATTAB, KARIM ABOUELMEHDI, ABDELMAJID ELMOUTAOUAKKIL
Abstract:	The Internet of Things (IoT) technology has revolutionized all areas of human life, making it more comfortable. IoT refers to the current trend of The Internet of Things (IoT) technology that has revolutionized all areas of human life, making it more comfortable. IoT refers to the current trend of connecting all kinds of physical objects to the Internet, even the most unexpected ones, without human intervention, which constitutes a self-configurable network. The Internet of Things (IoT) enables organizations to automate the process and improve service delivery via Internet technology and data transfer to the cloud. Nowadays, the Internet of Things (IoT) is becoming a widely discussed topic among researchers, specialists, and experts. It is seen as the next step in the evolution of the Internet. This paper covers the application of (IoT) technology in three different areas: smart cities, health, and agriculture.
Keywords:	Internet of Things, Smart City, Smart Parking, Smart agriculture, Smart Healthcare
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	DETECTING COMMONALITY AND VARIABILITY IN USE-CASE DIAGRAM VARIANTS
Author:	RA FAT AL-MSIE DEEN, ANAS H. BLASI, HAMZEH EYAL SALMAN, SAQER S. ALJA AFREH, 4AHMAD ABADLEH, MOHAMMED A. ALSUWAIKET, AWNI HAMMOURI, ASMAA JAMEEL AL_NAWAISEH, WAFA TARAWNEH, SULEYMAN A. AL-SHOWARAH
Abstract:	The use-case diagram is a software artifact. Thus, as with any software artifact, the use-case diagrams change across time through the software development life cycle. Therefore, several versions of the same diagram are existed at distinct times. Thus, comparing all use-case diagram variants to detect common and variable use-cases becomes one of the main challenges in the product line reengineering field. The contribution of this paper is to suggest an automatic approach to compare a collection of use-case diagram variants and detect both commonality and variability. In our work, every use-case represents a feature. The proposed approach visualizes the detected features using formal concept analysis, where common and variable features are introduced to software engineers. The proposed approach was applied on a mobile media case study to be validated. The findings confirm the importance and the performance of the suggested approach as all common and variable features were precisely detected via formal concept analysis and latent semantic indexing.
Keywords:	Use-case Diagram Variants, Formal Concept Analysis, Latent Semantic Indexing, Commonality, Variability.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	DEEP LEARNING AND METAHEURISTIC ALGORITHM FOR EFFECTIVE CLASSIFICATION AND RECOGNITION OF PADDY LEAF DISEASES
Author:	SRIDEVI SAKHAMURI, DR. K. KIRAN KUMAR
Abstract:	One of the most recent agricultural research topics is the recognition and classification of diseases from a plant leaf. With the exponential advancement of smart farming, plant disease detection becomes digitalized and data-driven, allowing advanced decision support, smart examination, and preparation. The detection of agricultural plant diseases using machine learning techniques would reduce the dependence on farmers to preserve agricultural goods. This paper proposes a deep learning-based metaheuristic algorithm of paddy leaf disease detection and recognition that enhances accuracy, generality, and training performance. This paper describes field images of various kinds of paddy leaf diseases: normal, bacterial blight, brown spot, and blast diseases. In this paper, the input image is assigned to pre-processing to remove artifacts and noise from the image. The Optimized Deep Convolutional Neural Network with Cuckoo Search (DCNN-CS) Algorithm is then used to classify leaf diseases by using the pre-processed image. During both the basic pre-training and fine-tuning phases of the DCNN approach, weights and biases are optimized using a cuckoo search algorithm (CS) to reduce classification errors. This DCNN-CS technique allows the application of simple statistical optimization methods with a reduced computing workload, resulting in high classification accuracy. Finally, the proposed DCNN-CS model's classification accuracy and efficiency were evaluated and compared to other Classification Techniques.
Keywords:	Paddy Leaf Diseases, Deep Convolutional Neural network, Cuckoo Search, Classification.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	APPLICATION OF BLOCKCHAIN TECHNOLOGY IN HIGHER EDUCATION INSTITUTIONS
Author:	AIVAR SAKHIPOV , MADINA YERMAGANBETOVA , RUSTAM LATYPOV , NURZHAN UALIYEV
Abstract:	This scientific study examines the use of blockchain technology in higher education institutions in the context of the development of the technical base of the modern education system. The relevance of the study is determined by the wide spread of the latest technologies in the system of modern education and their substantial impact on the quality of education in higher educational institutions and other educational institutions. The purpose of this study is to investigate the main areas of application of blockchain technology in higher education institutions in order to create optimal learning conditions in modern realities. The main approach of this study involves a combination of a systematic analysis of the factors of theoretical justification of the use of blockchain technology in universities with an analytical study of the technology itself in relation to the realities of the modern higher education system. The main results of this study lie in the definition of the main areas of application of blockchain technology in modern higher education institutions and the justification of the practical benefits of using this technology in the modern system of higher education. The prospects for further research in this area are determined by the spread of blockchain technology in the current higher education system and the need for a comprehensive study for practical purposes. The applied value of this study lies in the possibility of practical application of the results obtained in order to ensure a real return on the implementation of this technology in the educational process of modern universities.
Keywords:	Informatisation Of The Education System, Modern Digital Technologies, Higher School System, Organisation Of Training In Higher Education, Digitalisation
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	HARDWARE-SOFTWARE COMPLEX OF INTERACTIVE TRAINING PROGRAMS ON AIRCRAFT REPAIR PROCESSES BASED ON 3D AND VR
Author:	‪ILDAR PIRMANOV, ZHARAS AINAKULOV, NATALYA ASTAPENKO, KAIRAT KOSHEKOV, IGOR FEDOROV‬‬‬
Abstract:	Inspection and maintenance processes in the field of aircraft repair are characterized by a high percentage of manual operations, small batch sizes, and a wide variety of handled components. The learning process in this field is complex and expensive. New educational tools and technologies need to be introduced to provide effective education. The paper proposes a mechanism of educational software tool on the example of aircraft equipment units’ repair, implemented with the help of VR and 3D-modeling technologies. As a result of the experiment the effectiveness for the educational system of the proposed mechanism and the VR technology in general was proved the number of errors decreased and the time of operations execution increased. The benefits of the implementation of VR in the educational process were noted by 69% of students. The described innovative approach can be useful not only for the preparation of educational VR solutions in aviation, but also in other branches of engineering.
Keywords:	Virtual Reality, Learning Tools, 3D Model, Aviation Equipment
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	COMPARISON STOCK PRICE PREDICTION BETWEEN ARIMA, MULTIPLE LINEAR REGRESSION AND LSTM MODELS BY ADDING STOCK SENTIMENT ANALYSIS AND USD/IDR FLUCTUATION
Author:	CHRYSMIEN, RIYANTO JAYADI
Abstract:	Since the COVID-19 pandemic, the number of new investors entering the Indonesia capital market has significantly increased. Director of Index Harga Saham Gabungan (IHSG) said the pandemic COVID-19 also brought several new achievements in the capital market, including in terms of the number of investors, market capitalization, to volume, frequency, and investment value. Autoregressive Integrated Moving Average (ARIMA) is a model that is commonly used to predict the movement of a stock. However, there are also some limitations of ARIMA, ARIMA model can no longer accommodate when there is a sharp spike or drops in prices and if ARIMA model used for a long time, the forecast results will be constant. This research was conduct on FREN's stock price which recently has a high trend and the price is strongly influenced by public sentiment. In this study, researchers will compare the Multiple Linear Regression, LSTM model using proposed model with ARIMA to give new insight from business side and stock investors to give a better decisions in stock investment strategies. The results show that ARIMA which predicts stock movements based on historical data alone cannot predict FREN stocks when there is a sharp spikes of stock prices.
Keywords:	Stock Price Prediction, ARIMA, Multiple Linear Regression, LSTM, FREN
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	DISTRIBUTED DENIAL OF SERVICES ATTACKS AND THEIR PREVENTION IN CLOUD SERVICES
Author:	SARAH NAIEM, 1MOHAMED MARIE , AYMAN E. KHEDR, AMIRA M. IDREES
Abstract:	Distributed Denial of services (DDOS) attacks are one of the most famous attacks that affect the availability of a service making it a serious problem especially when it comes to cloud computing as it is becoming a bigger part of our lives. Throughout this paper, we first discussed the DDOS types, categories, and approaches in terms of the targeted area of the cloud or the intensity of the attacks whether it’s the normal DDOS, the Low-rate DDOS, or Economic-DOS (EDOS). We then presented a comparative analysis between the recent studies discussing the DDOS attacks in cloud. Prevention of DDOS in cloud computing is the first step in the defense mechanism followed by detection and mitigation. The prevention of the DDOS attacks is the foremost important step in protecting the cloud from DDOS which is achieved through challenge-response, hidden servers, and restrictive access approaches. We also provided a summary of the recent studies discussing the different prevention techniques, approaches, and frameworks. The main purpose of this paper is to provide a road map of the current situation of DDOS attacks and how they take place, why they take place and its prevention techniques in cloud computing environment focusing on the true protective prevention stage.
Keywords:	Cloud Computing, Security, DDOS attacks, Low rate DDOS, DDOS prevention
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	A SEQUENCE ANALYSIS AND ALIGNMENT SOFTWARE (SAAS) FOR OPTIMAL PERFORMANCE IN DNA SEQUENCE ANALYSIS
Author:	G A INYANG, F U OGBAN, U O UDENSI, E U OYOITA1, E A EDIM
Abstract:	In recent time, there have been upsurges of DNA and Protein sequence data deposited in Genebank or databases that are subjected to analysis, which is made possible through the utilization of bioinformatics tools. However, the accuracy and informativeness of the sequences often analyzed depend on the suitability of the bioinformatics Software employed during the analysis. The thinking however, is that for phylogenetic reconstruction software for instance, using a particular method, Maximum Likelihood, for example, should display exact and similar output with same clustering/class pattern and bootstrap values. It therefore becomes urgent and imperative to delve into developing sequence analytical software whose command and algorithmic composition is the same, irrespective of the suite placed. This will aid interpretation of results, the researcher notwithstanding. This is the pivot on which this paper anchors. This paper will evaluate the extent and pattern of clustering of MEGA 7 and PAUP 4 using Maximum Likelihood, Parsimony and Neighbour-Joining Methods based on analyzing sequence data from pigeon pea (Cajanus cajan (L) Millsp) using the two analytical Software Packages (MEGA 7 and PAUP 4) with a comparative novel algorithm called Sequence Analysis and Alignment Software (SAAS), as it relates to phylogenetic reconstruction to test for species relatedness and divergence. The results from SAAS showed reduced variance of resolution into specific clusters as the number of the reads of the sequence decreases, and optimal performance in terms of runtime and accuracy of resolution into clusters.
Keywords:	Sequence Analysis and Alignment Software (SAAS), Pigeon Pea Plant, Phylogeny, Maximum Likelihood, Parsimony and Neighbour-Joining, Species Relatedness and Divergence Accuracy and Informativeness.
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text

Title:	ADOCA: A NOVEL TECHNIQUE TO DEFRAUD CREDIT CARD USING AN OPTIMZED CATBOOST ALGORITHM
Author:	KANEEZ ZAINAB, NAMRATA DHANDA, QAMAR ABBAS
Abstract:	Cashless economy has increased the demand of digital affairs. Online transactions using Credit cards is one of the most often used medium of digital transactions. Spike in recent years is seen in fraudulent transactions across the digital platform. The researchers have suggested many techniques in the past for detection of fraudulent transactions. But due to the key challenges like the changing profiles of both fraudulent and non-fraudulent transaction and data being unbalanced hinders technologies like data mining and major algorithm of machine learning (such as KNN, SVM, Random Forest and Decision Tree) and models of deep learning. Therefore, a novel proposal has been suggested for detecting the credit card fraud transaction using an optimized CatBoost Algorithm for determining that whether the transaction is legitimate or fraudulent by optimizing the Bayesian-based hyper parameter to tune the parameter of the CatBoost Algorithm. Hence, we suggest this novel approach as ADOCA (Anomaly Detection using an Optimized CatBoost Algorithm). Based on that, we compare our approach from the different binary classification algorithms that includes Logistic Regression, KNN, SVC, Decision Tree and Random Forest.
Keywords:	Credit card fraud, Binary Classification, Machine Learning, CatBoost, Optimized CatBoost
Source:	Journal of Theoretical and Applied Information Technology 28^th February 2022 -- Vol. 100. No. 04 -- 2022
Full Text