		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
July 2022 | Vol. 100 No.13

Title:	DDOS ATTACKS DEFENSE APPROACHES AND MECHANISM IN CLOUD ENVIROMENT
Author:	SARAH NAIEM, AMIRA M. IDREES, MOHAMED MARIE, AYMAN E. KHEDR
Abstract:	Cloud computing is becoming a very vital part of any business nowadays and the business sector s main concern is the security in terms of availability, authenticity, and confidentiality. Distributed denial of services (DDOS) is becoming the main security threat in cloud where DDOS targets the cloud services and structure to obstruct the access of the rightful users. The protection of cloud from this attack is becoming very challenging, throughout this paper we first discussed the different prevention, detection, and mitigation approaches along with the techniques used for each approach. The prevention approaches include hidden servers, restrictive access, resource limitation, and challenge response, while the detection approached include signature and anomaly-based detection, data mining, resource usage and filtering techniques. Moreover, we discussed the recent defense mechanisms in the different approaches, and it was obvious that most of the defense mechanisms are only based on detection of the DDOS and there is a huge gap in terms of the prevention and mitigation approaches.
Keywords:	DDOS Attacks, DDOS Defense in Cloud, Prevention, Detection, Mitigation.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	OSMOTIC COMPUTING ENHANCEMENT BASED ON BLOCKCHAIN APPROACH
Author:	ISLAM GAMAL, HALA ABDEL-GALIL, ATEF GHALWASH
Abstract:	Osmotic computing is an emerging concept for managing aggressively distributed IoT applications facilitating IoT ecosystem to compensate the limitation of computational, power consumption resources capabilities offer the extension for IoT system to use the power of IoT, edge, and cloud resources within a federated environment to grantee utilization and efficiency of these re-sources. In essence, osmotic computing solves end-to-end IoT solution issues related to the orchestration, deployment, and reconfiguration of osmotic abstraction microelements (MELs) that are constructed and federated across cloud, edge and IoT infrastructures. In consequence, while enabling the dynamic orchestration of the osmotic resources, there is opportunity for attacks and security threats resulting from the continuous reconfiguration of the osmotic topology where providing security and privacy is a key issue in which malicious software/hardware injection at-tacks are compromising data security, integrity, and confidentiality. Blockchain is a fundamental technology, as a distributed and decentralized ledger, is a nominated solution to face the security limitations of osmotic computing solution. The objective of this research is to propose a new blockchain based osmotic computing architecture to leverage private permissioned Hyperledger Fabric (HLF) blockchain aiming to present a security guard by tracking MELs operations into the blockchain ledger to offer authorized access control and establish the root of trust for applying the principal features of traceability, immutability, transparency, and auditability. The implemented architecture prototype is tested on both simulated and real-life environments to validate the architecture hypothesis of running a transparent and traceable osmotic IoT ecosystem maintaining the required security levels.
Keywords:	Osmotic Computing, Blockchain, Hyperledger Fabric
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	DETERMINANTS OF BYOD PROTECTION BEHAVIOR: AN EMPLOYEE S PERSPECTIVE
Author:	IBRAHIM MOHAMMED AL-HARTHY, NOR ASHIKIN ALI
Abstract:	Bring Your Own Device (BYOD) allows employees to access the organizational network via their devices/technology. This trend is beneficial to the employees in terms of greater flexibility, apart from productivity and cost savings for the company. Enabling employees to use their own devices at the workplace may lead the company to become vulnerable to information security threats as employees do not possess the right understanding of protecting their devices. This study analyzed the factors that determine employees behavioral intention and their actual protection behavior in protecting their devices in BYOD environment. A self-administered questionnaire was conducted with 383 government employees in Oman. The results indicated that perceived vulnerability, perceived severity, response cost, subjective norm, perceived behavioral control, and knowledge influenced employees BYOD intention protection behavior while perceived vulnerability, perceived severity, response efficacy, response cost, attitude, subjective norm, and perceived behavioral control were found to influence BYOD protection behavior. Contrarily, response efficacy, security self-efficacy, attitude, and information security awareness were found to be nonsignificant on protection intention. The findings also revealed that the mediator (protection intention) has a considerable beneficial impact on the dependent variable (protection behavior). Hence, employers should develop an all-encompassing approach to improve their employees BYOD usage protection behavior to secure the organization s assets.
Keywords:	BYOD, Protection Behavior, Protection Intention, Survey, Structural Equation Modelling
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	A BLOCKCHAIN FOR SECURE DATA STORING WITH MULTI CHAIN ON SMART HEALTHCARE SYSTEM
Author:	SYAFIQ MUHAMMAD, BENFANO SOEWITO
Abstract:	The development of the smart healthcare industry requires them to adapt to new technologies, because every year a lot of data is stolen or used by other parties, because the smart healthcare industry deals with very sensitive data that must be managed in a secure way. Electronic Health Records (EHRs) store various types of personal and sensitive data. there have been many surveys that prove the loss of data stolen and used by other parties. Therefore, we propose a new technology to be used in sensitive data storage in smart healthcare systems, namely blockchain. but we also apply another method in blockchain to store data that is with multi-channel. The advantage of blockchain also is that it provides transparency, security and privacy using consensus-based decentralized data management on top of a peer-to-peer distributed computing system. then the use of the multi-channel method can also make data storage possible with several channels at once where each channel has its own data. By proposing a blockchain technology and multi-channel method, we will experiment and evaluate the results of the experiment.
Keywords:	Blockchain, Smart Healthcare, Hyper Ledger, Multi-Channel,
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	MEAN SHIFT DEMING REGRESSION-BASED DEEP MULTILAYER PERCEPTIVE NEURAL LEARNING FOR RESOURCE OPTIMIZED DATA TRANSMISSION IN WSN
Author:	Mrs.A.VIJAYASARATHI, Dr.N.ELAMATHI
Abstract:	A Wireless Sensor Network (WSN) is incorporated with multi-capabilities to sense, calculation, data gathering, and communication. The network consists of small sensor nodes which are capable of monitoring and processing the data from a particular geographical position and transmits it to a remote location i.e. sink node or Base Station (BS). During the communication, extending the lifetime and stability of WSN remains challenging issue. Therefore, resource efficiency is a crucial factor in WSN to extend the network lifetime. In order to develop a Mean Shift Deming Regression-based Deep Multilayer Perceptive Neural Learning (MSDR-DMPNL) Model for dual cluster head selection to perform resource optimized data transmission in WSN. MSDR-DMPNL model comprised five layers, namely one input, three hidden layers, and one output layer for performing energy-efficient data transmission. The number of sensor nodes is considered as input in the input layer. After that, the energy and memory of the sensor node are computed in the hidden layer 1. Then, the information is transmitted to the hidden layer 2. In that layer, Mean Shift Node Clustering is carried out to perform the clustering process based on energy and memory. After that, the number of clusters is transmitted to the hidden layer 3 where Deming Regression is performed to select the dual cluster head (i.e., primary cluster head and secondary cluster head) in every cluster. Then the sensor node transmits the data packets to the primary cluster head through a neighboring node with high bandwidth availability. The primary cluster head transmits the collected data packets to the secondary cluster head. Finally, it transmits the received data packets to the base station. In this way, efficient resource-efficient data transmission is carried out. Simulation is conducted on factors such as clustering accuracy, energy consumption, packet delivery ratio, and delay with respect to a number of sensor nodes and packets.
Keywords:	WSN, Resource Optimized Data Transmission, Deep Multilayer Perceptive Neural Learning, Deming Regression, Mean Shift Node Clustering.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	END2END UNSTRUCTURED DATA PROCESSING, CONFIDENTIAL DATA STRUCTURING & STORAGE USING IMAGE PROCESSING, NLP, MACHINE LEARNING, AND BLOCKCHAIN
Author:	MADHURA K, MAHALAKSHMI R.
Abstract:	The expediting magnification of automating the manual jobs into automated is incrementing day by day, as there are approximately 2.5 quintillion bytes of data exchanged over the cyber world per day. With the incrementing need for process automation and immensely colossal unstructured data, there is increasing demand for incorporating automated objectives-specific classifiers for businesses. To make better and improvised automated end-to-end solutions, data structuring utilizing advanced technologies such as ML, Big data processing, data science, etc. will avail in abbreviating the resource consumption extracting better data semantics, handle multiple parallel requests which result in high-end organized automated solutions with efficient data processing. This paper demonstrates an objective-specific classifier will accommodate as a commencement point in automating any process. In this paper confidential data processing is demonstrated on confidential data of students, dataset contains unstructured data from the university library which will then be structured into confidential data and non-confidential data automatically. Image processing is utilized to extract features and ML algorithms are acclimated to train the classifier. This intelligent classifier can further be used along with encryption methodology to protect and store confidential data. The article is organized as an introduction section, literature review, methodology section, result-implementation details, and last section conclusion. The introduction section introduces the importance of artificial intelligence in the field of the education system, literature review section covers the background work carried out on artificial intelligence in the field of education, methodology section covers the proposed method of applying machine learning algorithm to perform the automatic classification of documents in the education system, result-implementation section shows the result analysis from different machine learning algorithms and end the conclusion section provides the summary of overall work.
Keywords:	Artificial Intelligence, Data Management, Meta-Data Management, Machine Learning, NLP, Data Protection, Data Science, Unstructured Data.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	USING SYNERGETIC INFORMATION THEORY FOR SPEECH DIAGNOSTICS OF SPECIALISTS BY MEANS OF DIGITAL TECHNOLOGIES
Author:	BIKESH OSPANOVA, АINUR SEILKHANOVA, АZAT ABDIN
Abstract:	The article deals with the use of entropy criteria to identify language mistakes in spontaneous oral speech. The key problems of synergetics as an interdisciplinary scientific trend are analyzed. Speech in the form of an oral statement (text) is studied as a complex multi-level synergistic system. Its structure is analyzed within the framework of multidimensionality. Some aspects of the experimental approach to calculating entropy in the oral speech of bachelor, master, doctoral students and specialists are outlined, and experimental data demonstrating the results are presented. A linguo-mathematical model for speech diagnostics of specialists is proposed. It is built on the basis of the fundamental law of conservation of the sum of information and entropy using the Shannon formula. In addition, the article shows the importance of synergetics in linguistics that represents today a new unifying trend, the purpose of which is to identify common ideas, methods, patterns of language transition from one level of organization to another. It should be noted that present day linguistic research requires the use of digital technologies, computer science, mathematics and other methods of information processing to identify the essence of linguistic phenomena. Today computer technologies play the key role in all the spheres of social life, so the main type of human activity is increasingly the ways and methods of obtaining, storing and expanding knowledge and information. Thus, the most urgent task of present day linguistic education is the use of digital technologies in scientific research. Alongside with this, there arise new aspects of discussing and considering the synergetic approach to analyzing a language. At the present stage of language education one of these issues is studying speech diagnostics in the flow of professional communication.
Keywords:	Information, Linguistics, Digital Technologies, Diagnostics, Speech.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	DIAGNOSIS OF DIABETES MELLITUS BASED COMBINED OF FEATURE SELECTION METHODS
Author:	SHAIMAA HAMEED SHAKER, AL-KHALIDI FARAH Q. , AMMARFAKHRI MAHDI
Abstract:	Diagnosis of Diabetes-Mellitus in human given a chance to know a person that may be at risk of lengthened tricky situation. This work proposed to diagnosis diabetes mellitus based on a hybrid of carefully selected features method to reduce the features by combining Chi square test and Recursive feature elimination methods, so this was the first stage. Then the output of first stage is the input to the classification stage to obtain the true accuracy as the second stage. Logistic Regression(LR), K-Nearest-Neighbor(KNN), and Naïve-Bayes(NB) methods are used to classify nonappearance or appearance of diabetes mellitus disease. So the contribution of this research was to determine the optimal number of extracted and approved characteristics for rapid accurate diagnosis of disease by using two methods of information reduction and to benefit from the data collected in real in addition to standard data.This work has deal with PIDD from UCI and another dataset that collected from some patients. All the results is evaluated using accuracy(ACC), precision(PR), recall(RE), and f-score(FScore) measures. Algorithms LR, KNN, and NB achieved accuracy about (95% -98%) with combined feature selection method. So LR and NB achieved maximum accuracy(98%)with proposed method based on five and six features of 400 patient records, while KNN algorithm achieved accuracy (87%)with Chi-square test and Recursive feature elimination on diabetes-dataset.
Keywords:	Diabetes Mellitus, classification, LogisticRegression, K-Nearest-Neighbor, Naïve-Bayes, Feature Selection.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	A DETECTION OF UNFAIRNESS ONLINE REVIEWS USING DEEP LEARNING
Author:	N.DESHAI , Dr B.BHASKARA RAO
Abstract:	In Todays internet world, online activities are growing exponentially and generating a tremendous number of online reviews and ratings, which are a valuable source of information for customers primarily associated with the purchase of marketing, selecting a restaurant, finding products, health, and services, etc. Therefore, online reviews are a crucial part of people's everyday decisions on what to buy, where to buy, where to eat, where to stay, which doctors to see, and what to select based on positive, negative, and neutral. Fake reviews not only mislead innocent clients and influence customers choice, leading to inaccurate descriptions and sales. However, there is still a significant requirement for a survey that can examine and summarize the various methodologies that are now available. This paper summarizes the existing datasets and the techniques they have acquired to represent the task of fake review detection. In addition, it examines the various feature extraction strategies that are currently available. Finally, we discuss the present gaps in this research area and potential coming directions in this field. We analyze and compare two various features extraction strategies and six various machine classification techniques.
Keywords:	Machine Learning, Deep Learning, Fake Review Detection, Feature Engineering
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	VOLLEYBALL PRACTICE SKILLS WITH INTELLIGENT SENSOR TECHNOLOGY MODEL TO DEVELOP ATHLETES COMPETENCY TOWARD EXCELLENCE
Author:	CHANITA SATTABURUTH, PALLOP PIRIYASURAWONG
Abstract:	In this research article, the researcher investigated the skills training process for volleyball players using intelligent sensor technology to develop athletic performance and to achieve the goals or specified criteria. There were three processes in this research. The Volleyball Intelligent Sensor Technology (ViST) Model was evaluated by specialists, which showed that it was consistent and could be used to improve the skills of volleyball players at the highest level. Therefore, the ViST Model process was used to develop an intelligent sensor technology system for volleyball skills training, with a system that could perform training according to a predetermined training program. This allowed volleyball players to practice every time with a robot as a training partner, working according to the training program and acting as both a trainer and a coach. This evaluated the results of the training, suggest-ed procedures, corrected mistakes, and improved the athletes training, thus making it more effective. The athletes were able to develop their skills at any time, as needed, depending on their availability. Hence, the athletes gained discipline in training and developed their performance and potential quickly.
Keywords:	Practice skills, Competency, Intelligent Sensor Technology, Volleyball
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	A STACKING BASED HYBRID TECHNIQUE TO PREDICT STUDENT DROPOUT AT UNIVERSITIES
Author:	ALFREDO DAZA
Abstract:	University dropout is a very complex problem that affects the Government, Institutions and students and families in the world. The prediction allows to identify the students who are going to desert early, so that the directors of the Universities can establish strategies to mitigate it. Machine Learning methods are the most recent and effective for this problem. However, so far these methods have been applied independently and not in combination. This paper proposes a hybrid model based on decision trees and neural networks, designed following the KDD methodology, to predict with high precision the university student dropout. The proposal was implemented in Rapid Miner Studio 6.4 and applied to a dataset with 1761 student records and 53 variables for training. Through a variable selection procedure that includes 8 algorithms, 27 variables were selected. The results on 100 new records show an accuracy of 87%, 91%, 98% for decision tree models, neural networks and stacking respectively. In addition, the result of sensitivity is 90.6%, 93.3%, 98.7% for decision trees, neural networks and stacking respectively. Regarding specificity, 76%, 84% and 96% have been obtained for decision trees, neural networks and stacking respectively. The results of accuracy, sensitivity and specificity also show that the hybrid model presents better results than the separate models.
Keywords:	Decision trees, University Dropout, Hybrid Model, Prediction, Neural Networks, Stacking.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	HOW DOES LIVE SHOPPING PLAY A ROLE BY INCREASING ONLINE PURCHASE INTENTION?
Author:	MICHAEL BHUDIAWAN, VIANY UTAMI TJHIN
Abstract:	The purpose of this research is to determine the factors that affecting marketplace users in intention to purchase through the use of live shopping / live commerce. The structural model of this research includes various variables such as Information Quality, System Quality, Trust, Perceived Ease of Use, Perceived Enjoyment, and Satisfaction. In this study, the data was taken using a questionnaire and obtained 160 valid respondent data and can be processed for analysis. The data were analyzed using Smart PLS and the results found that the Trust, Perceived Enjoyment & Satisfaction variables had a significant effect on Purchase Intention. All variables used in this research explain the variability in Purchase Intention of 38,4% and Satisfaction of 67,9%. Furthermore, the researcher also provides implications and suggestions for companies and developers to improve the quality of the live shopping feature.
Keywords:	Purchase Intention, Live Commerce Shopping, Information Quality, Satisfaction, E-commerce
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	THE USE OF AUGMENTED REALITY IN E-COMMERCE: A BIBLIOMETRIC STUDY
Author:	TRAVIS MONIAGA , VIANY UTAMI TJHIN
Abstract:	Online shopping is increasingly being used by many people because of the easy and fast accessibility factor. In this modern era, the technology applied to e-commerce innovations is increasingly diverse, one of which is using the AR or Augmented Reality feature. This study aims at analyzing bibliometric studies using VOSViewer systematically for the Augmented Reality in E-commerce topic. This paper provides data analysis regarding augmented reality in e-commerce throughout ten years (2010–2021) by utilizing mapping tools in VOSViewer. From the search results, 962 relevant published journals were found, from 2010–2021. The results show that the number of publications on this topic continues to increase from 2010 to 2021 and most of the publications are from Elsevier and Emerald. In 2019, the number of publications related to augmented reality in e-commerce increased significantly compared to previous years, and continued to grow until it peaked in 2021 to reach 308 journals. From the result from VOSviewer tools, the research of augmented reality in e-commerce is divided into 7 clusters. Each cluster explained the network connection among keywords. This means that augmented reality in e-commerce is a topic that can be combined with other topics to research and study. Furthermore, this research is expected to be a resource for researchers who conduct research on related topics.
Keywords:	Bibliometric, Augmented reality, E-commerce, VOSviewer
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	INSIDER THREATS: PROFILING POTENTIAL MALICIOUS ATTACKS, SEVERITY AND IMPACT
Author:	ZUL-AZRI IBRAHIM, FIZA ABDUL RAHIM, ANIS ALIAH ALAUDDIN, NORZIANA JAMIL, HARIS ISKANDAR MOHD ABDULLAH
Abstract:	The insider threat that organizations and cooperation face today is a real and serious issue that has become increasingly difficult to address as time has passed. More complex approaches must be researched and developed for reliable recognition, detection, and response to insider threats. One way to achieve this is by identifying and classifying diverse viewpoints of insider threats. Various studies focused on comprehending and mitigating insider threats by developing different taxonomies and terminologies relating to insiders, insider threats, and insider attacks. However, few are concerned about the severity and impact of insider threats to an organization. Therefore, this paper proposes a taxonomy for profiling potential malicious attacks, highlighting severity to determine the impact of insider threats and the prioritization of vulnerability remediation activities.
Keywords:	Insider threat, Insider Threat Detection, Taxonomy, Severity, Impact
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	STOCKS FORECASTING EXPLORATION ON LQ45 INDEX USING ARIMA(p,d,q) MODEL
Author:	RADEN GUNAWAN SANTOSA, ANTONIUS RACHMAT CHRISMANTO, YUAN LUKITO
Abstract:	Up to now, there are 700 stocks listed on the Indonesia Stock Exchange (IDX). An example of an index listed on the IDX is the LQ45 stock index. LQ45 index contains 45 stocks, and these stocks are grouped because of their high liquidity, large market capitalization, and good company fundamentals. Since this index is a fundamental reference index for passive investors, it is necessary to model the prediction of LQ45 stocks to predict these stocks' movement accurately. One form of modeling used is the ARIMA (p, d, q) model. In this study, ARIMA (p, d, q) modeling was conducted to predict the price of 45 stocks in LQ45. The ARIMA (p, d, q) model is a time series model that is suitable for modeling LQ45 stocks because it is only based on the relationship with previous data (AR), and the resulting error is assumed to be related to the previous error (MA). The problem that arises is that the movement of shares can be seen from the visual image (plot), while the function of the movement is unknown. This modeling is expected to help observe the ARIMA functional form of each LQ45 stock and measure the Mean Absolute Percentage Error (MAPE) of each stock. ARIMA (p, d, q) consists of AR(p) and MA(q) models as well as combining d differencing processes. ARIMA (p, d, q) modeling briefly contains several processing stages: parameter estimation, residual test, and prediction. This study showed that the mean forecast error using MAPE for LQ45 stock was 10.088%, with a standard deviation of 8.968%. Furthermore, BBCA stocks had the lowest forecast error of 2.1797%, and MDKA stocks had 44.49%. The highest forecast error was due to MDKA stocks having visually and exponentially increased. Therefore, it can continue increasing exponentially or even decreasing sharply in the future price period.
Keywords:	ARIMA, parameter estimation, residual test, prediction, MAPE
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	A HYBRID VERIFIED RE-ENCRYPTION INVOLVED PROXY SERVER TO ORGANIZE THE GROUP DYNAMICS: SHARING AND REVOCATION
Author:	P RAJA SEKHAR REDDY, K RAVINDRANATH
Abstract:	The Maintenance of Group Dynamics is a crucial element to any cloud service provider because of the continuous in and outflows that happen in the organizations. In group dynamics, sharing of data in encrypted format is taken care of by the attribute-based encryption (ABE), and the revocation process achieves by performing the hybrid verification procedure by the proxy server, which supports the re-encryption mechanism, which reduces the computational latency involved to double encrypt the data. The proxy server communicates with TPA to identify the malicious users or attackers. If any such users get identified immediately, the proxy server revokes the user bypassing the necessary information to the Primary Group Manager (PGM). The main advantage of the proposed system is that it performs an identity check using the primary and vital information that uniquely represents the group administrators. Also, the process involves the combination of message digest with AESWrap in a secure random key generation environment. The TPA also performs batch auditing to perform multiple audits on different groups simultaneously and increase the system's performance.
Keywords:	Group Dynamics, Re-encryption, Proxy Server, AESWrap, Secure Randomness, Revocation
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	ENSEMBLE FEATURE EXTRACTION MODEL WITH OPTIMAL KERNELIZED CLUSTERING ALGORITHM FOR IDENTIFYING THE CANCER FROM CERVICAL HISTOPATHOLOGY IMAGES
Author:	BAGHIALAXMI R, DR. KIRUBAGARI B, DR. LAKSHMANA PANDIAN S
Abstract:	Cervical cancer, a disease that affects women the most. When a woman's cervix undergoes some modifications, this is visible. These cancer cells have the ability to spread to another parts, including bladder, livers, lungs, rectum, further complicating situations. Higher rates of recovery have been reported with earlier discovery, screening, and rigorous procedures. This paper proposes a novel technique to detect cervical cancer utilizing deep learning techniques. The idea is to provide improvement in the efficiency, the network used to cluster the images using Optimal Kernelized Fuzzy C-Means (OKFCM) clustering along with classified image to give high-resolution image classification.Then to build an accurate cervical cancer histopathological image ensemble based feature extraction model, which is the very first and most important procedure in our system. An artificial neural network is used to distinguish between normal, abnormaland malignant cells, producing accurate findings than manual testing procedures like Pap test and LBC (Liquid Based cytology). Database of 962histopathological cervicalimages used to test our technique.The outcomes of all trials proved that this technique produced the best results inPrecision, Specificity,Recall, AUC,Accuracy, FPR and FNR. This strategy can help pathologists with cervical disease categorization by reducing their cognitive load and increasing their diagnostic efficiency and accuracy. It will have the ability to be used in medical care for the diagnosis of cervical cancer histology.
Keywords:	Cervical Cancer, Deep Learning, Classification, Feature Extraction, Histopathological Image
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	INSURANCE UNDERWRITING AND ECHNOLOGY RELATIONSHIP: A BIBLIOMETRIC ANALYSIS
Author:	CAHYONO BUDY SANTOSO, HARCO LESLIE HENDRIC SPITS WARNARS, AHMAD NURUL FAJAR, HARJANTO PRABOWO
Abstract:	This study aims to determine the direction and objectives of current research on insurance underwriting and its relationship to the technology domain. We used a five-phase bibliometric analysis method. We extracted 4983 documents from the Scopus database for the period 1987 to 2021 and refined the keywords by adding inclusion criteria to generate 256 documents. We analyze the document metadata with features from the Scopus website, export it to a RIS-type data set, and then process it using VosVewer to visually map keywords for further analysis. As a result, we found publication trends related to this topic by time period, most influential publications, main topic trends, and potential topics for future research. The conclusions of research in this domain have increased publication interest from year to year, and the density diagram for the field of information technology is quite dark, which indicates that the level of novelty is still high for further research.
Keywords:	Underwriting, Insurance, Bibliometric, Visualisation, Technology, VosViewer
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	THE IMPACT OF ELECTRONIC MONEY BALANCE TOP UP FEATURE ON SMARTPHONE IN TRANSACTIONS ON PUBLIC SATISFACTION USING TAM
Author:	WILLIAM ADRIANUS, ADINDA PUJI RAHMAWATY, ANTONI KURNIAWAN1, NOERLINA
Abstract:	The purpose of this research was to identify and analyze public interest in the transaction process using Near Field Communication (NFC) in people who often use public transportation in performing their daily activities. This research focused on the NFC feature that was used for transactions using electronic money. The design method used in this research is descriptive associative which questions the relationship between two or more variables because the model used in this research is the Technology Acceptance Model which refers to the explanation of the main factors from user behavior towards user acceptance of NFC technology. The analysis was conducted on people regarding their daily activities in performing transactions using electronic money. The results achieved are data that can be seen from the people s interests and needs towards smartphones with NFC features gathered from the responses given by the people. The conclusion is that the data from this research can help existing smartphone producers to implement NFC features on affordable smartphones for the public.
Keywords:	NFC, Information Systems, Smartphone, Technology Acceptance Model (TAM)
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	CLASSIFICATION OF SECURITY ISSUES AND CYBER ATTACKS IN LAYERED INTERNET OF THINGS
Author:	DEEPTI RANI, NASIB SINGH GILL, PREETI GULIA
Abstract:	Internet of Things (IoT) has emerged as a very significant research area. In IoT, billions of ‘things are connected which communicate with one another over a network. While communicating among ‘things , their users face several types of application and technical challenges. IoT system infrastructure comprises several layers. Different researches have been conducted so far to detect vulnerabilities, threats, and attacks arising in the IoT environment. Modern IoT architectures consist of physical and network components apart from different kinds of services and solutions. IoT systems face several services and security challenges. Privacy and security problems in IoT systems are quite unpredictable. The main objective of this paper is to identify and classify various security challenges faced by IoT users. Several types of security and privacy issues have been addressed in the present paper. This paper also presents a classification of security and privacy issues considered in different levels of IoT architecture.
Keywords:	Internet Of Things, Layers Of Iot Architecture, Classification Of Security Issues And Cyber-Attacks in IOT
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	APPLICATION OF INTERNATIONAL SCIENTOMETRIC DATABASES IN THE PROCESS OF TRAINING COMPETITIVE RESEARCH AND TEACHING STAFF: OPPORTUNITIES OF WEB OF SCIENCE (WOS), SCOPUS, GOOGLE SCHOLAR
Author:	NATALIIA BAKHMAT, OLENA KOLOSOVA, OLENA DEMCHENKO, IRINA IVASHCHENKO, VIKTORIA STRELCHUK
Abstract:	Currently, the importance of bibliographic databases (DBs) has increased significantly, as they are the main providers of publication metadata and bibliometric indicators used for both research evaluation and research. Since the reliability of these tasks primarily depends on the data source, all DBs users should be able to choose the most appropriate one. Web of Science (WoS), Scopus, and Google Scholar are the main bibliographic databases. The aim of the study is to analyze the capabilities of Web of Science (WOS), Scopus, Google Scholar, as well as to characterize the use of international scientometric databases in the process of training competitive research and teaching staff. Methods. The research is based on systematic and comparative analysis, dialectical methods, as well as methods of classification, generalization, and comparison. Results. Web of Science (WoS), Scopus, and Google Scholar (DBs) databases are still the main and most complete sources of publication metadata and impact metrics. It is shown that Scopus provides a broader and more comprehensive coverage of content. For the second reason, the availability of individual profiles for all authors, institutions, and serial sources, as well as the interconnected DB interface, make Scopus more user-friendly for practical use. Conclusions. A comparative study of publications, citations, and the h-index among 146 scientists from five major disciplines showed a consistent and fairly stable increase in both publications and citations in Web of Science, Scopus, and Google Scholar. This suggests that all three databases provide sufficient coverage stability to be used for more detailed interdisciplinary comparisons. But, it is concluded, that Scopus is better suited for investigators and day-to-day tasks for several reasons.
Keywords:	Scientometric Databases, Metadata, Publications, Citations, Scientific Research
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	IMPROVED DEEP LEARNING APPROACHES FOR COVID-19 RECOGNITION IN CT IMAGES
Author:	HAMZA ABU OWIDA
Abstract:	Since the increasing risk of COVID-19, a set of actions have been achieved to develop tools to handle the spreading of the COVID-19 disease. Though testing kits were being used to diagnose the COVID-19 infection, the process requires time and the test kits suffer from being lack. In COVID-19 management, the computed tomography (CT) is considered an important diagnostic method. Taking into account large number of exams performed in high case-load situations, an automated method may help to encourage and save time for diagnosing and identifying the disease. Several deep learning tools have recently been developed for COVID-19 scanning in CT scans as a technique for COVID-19 automation and diagnostic assistance. This article aims to explore the rapid recognition of COVID-19 and proposes an advanced deep learning technique, derived from improving the ResNet architecture as a transfer learning model. The architecture design of the proposed model is based on alleviating the connections between the blocks of the ResNet-50 model. This reduces the training time for scale-ability and handles the problem of vanishing gradient with relevant features for recognizing COVID-19 from CT images. The proposed model is evaluated using two well-known datasets of COVID-19 CT examined with a patient-based split. The proposed model attains a total back- bone accuracy of 98.1% with 97%, and 98.6% specificity and sensitivity, respectively.
Keywords:	COVID-19; CT Images; SARS-Cov-2; Deep Learning; Transfer Learning Model.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	ARTIFICIAL INTELLIGENCE APPROACH FOR SMART SHARIA TOURISM: A REVIEW
Author:	FRISTI RIANDARI, SARJON DEFIT, YUHANDRI
Abstract:	The main purpose of this research is to increase the awareness of halal tourism developers on the factors that support the sustainability of this tourist area. Halal tourism is a dynamic and complex sustainable tourism that involves many stakeholders in practice. The large number of stakeholders involved can create conflicts and gaps that threaten tourism sustainability. So not only thinking about the application of the halal concept in tourism, halal tourism developers must also be able to manage the many factors involved in its implementation. And the negative impact that can arise due to the many factors involved can be minimized. This study uses secondary data derived from previous studies. This research also provides recommendations that have implications for practitioners.
Keywords:	Artificial Itelligence, Smart, Sharia Tourism; Halal Toursim, Toursim Recommendations
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	E-COMMERCE WITH FOG-ENABLED CLOUD COMPUTING: FRAMEWORK, OPPORTUNITIES, AND CHALLENGES
Author:	SUNEET WALIA, RANJIT RAJAK, MOHAMMAD SAJID
Abstract:	Competition now covers the geographical distances and stretches to customers irrespective of region, locality, and country. Cloud computing technology has sustained the E-commerce sector with speed, efficacy, and maintaining and serving the extensive customer database. However, speed, data maintenance, and security have become pertinent questions in the e-commerce business and the role of cloud computing. In this work, an E-commerce framework based on Fog-enable cloud computing is proposed, which is helpful to speed up the communication between customers and E-commerce companies due to the involvement of edge nodes as well as fog nodes. The elements, challenges, and role of cloud computing technology in upholding and fulfilling the requirements of e-commerce are also explored and discussed. The proposed E-commerce framework based on Fog-enable cloud computing would enhance the e-commerce business with better customer satisfaction, minimal cost, enhanced security, and easy and secure data maintenance.
Keywords:	E-Commerce, Fog Computing, Cloud Computing, Performance, Security, Privacy
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	A VILLAGE MONOGRAPH INFORMATION SYSTEM MODELING: CASE STUDY MARTAPURA SUB-DISTRICT, SOUTH SUMATERA, INDONESIA
Author:	LUIS MARNISAH, HERRI SETIAWAN, JOHN RONI COYANDA
Abstract:	Village monographs are data collection carried out by the village government that is systematic, complete, accurate, and integrated in the administration of government. In Indonesia, one of the local government agencies that are obliged to update their monograph data are villages in the Martapura District, Ogan Komering Ulu Timur Regency, South Sumatra Province. The village monograph aims to make it easier for the government, community or interested parties to obtain data and information from an area, especially village data contained in the Martapura sub-district. In this case, a data and information management model is needed to manage village data which encourages researchers to build a monographic information system. This research focuses on the development of a village monograph information system model which is implemented using a software prototype. The strategy and contribution in this research is the creation of a village monograph information model that can inform all existing village potentials using the Research and Development (R&D) method, while the application prototype development uses the Unified Process (UP). The modeling system used in this study is shown in the form of a UML diagram consisting of activity diagrams, entity relationship diagrams, and use case diagrams, the results of this study are presented in the form of data in the form of village monographs in the Martapura sub-district, Ogan Komering Ulu Timur Regency which are listed in government website, so that the data presented can be reprocessed and can be updated at any time.
Keywords:	Monograph, Modeling, Information System, Unified Process
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	UPPER GAIT ANALYSIS FOR HUMAN IDENTIFICATION USING CONVOLUTIONAL – RECURRENT NEURAL NETWORK
Author:	SALISU IBRAHIM YUSUF, STEVE A. ADESHINA, MUOSSA MAHAMAT BOUKAR
Abstract:	The human gait as a source of biometric data has improved identification at father distance, however it only full body gait data has been explored with deep learning models, which is resource demanding not always available due obstacles as in environment of deployment. In this research, we explored the use of upper gait analysis for identification with deep learning model convolutional recurrent neural network- Long Short Term Memory CRNN-LSTM and evaluate the reliability of using half gait against full gait, primary dataset was collected from 26 subject 12 females and 14 males. The result returns better accuracy with upper half gait than full body gait, hence, lower computation demand.
Keywords:	Gait, Gait Analysis, C-RNN, Human Identification, Computer Visions
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	ROUTING METHOD IN MULTI DOMAIN SOFTWARE DEFINED NETWORKS
Author:	ASAD MAHMOUD ASAD ALNASER, HAZEM (MOHD SAID) HATAMLEH, YURII KULAKOV
Abstract:	This article examines the issues of routing in multi-domain software-defined networks (SDN) of large size. The advantages of routing with the help of software-defined networks technology are given. The expediency of using multipath routing in computer networks of large size is justified. A method for dividing the network into domains by the k-means method is proposed. The division of the network into domains and the use of intra-domain and inter-domain routing can reduce the time complexity of routing. A centralized routing information method in the SDN controller is proposed. A modified algorithm for multipath routing along the distance vector is proposed and substantiated. In the routing process, with the formation. of a given route, routes from all intermediate sites to the destination node are formed simultaneously. This eliminates the repeated formation of routing information for the previously formed paths. Algorithms for inter-domain and intra-domain multipath routing are proposed to simplify the re-routing procedure if the network topology changes.
Keywords:	Multipath Routing, Software-Defined Networking; SDN controller, Routing domains, Domain controller, Time Complexity, Routing Algorithm, Distance Vector, re-routing
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	BIG DATA ANALYTICS FOR PREDICTION USING SENTIMENT ANALYSIS APPROACH
Author:	SRI REDJEKI, SETYAWAN WIDYARTO
Abstract:	Extraction of public opinion is a way of gathering knowledge based on short texts written by users to provide attitudes. This condition encourages a lot of research using social media, especially the sentiment analysis approach in conducting initial identification or predictions. Social media is a dynamic medium to get public opinion which is very cheap and very large in number. This research aims to provide a review of predictions using sentiment analysis, one of the analytical methods in big data analytics. Sentiment analysis techniques are used to predict customer review, market, health, and social behavior. The sentiment analysis approach sourced from social media is able to contribute to making predictions in the form of an early warning system of problems so that it can help decision-makers based on big data analytics.
Keywords:	Big Data Analytics, Predictive, Sentiment Analysis, Social Media
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	RECENT ADVANCES AND APPLICATIONS OF DEEP LEARNING TECHNIQUE
Author:	ADITYA DUBEY, AKHTAR RASOOL
Abstract:	Deep learning is a predominant branch in machine learning, which is inspired by the operation of the human biological brain in processing information and capturing insights. Deep learning uses several layers of neurons; each layer of neurons is connected to the successive layer, which helps to provide better accuracy for complicated tasks. Machine learning evolved to deep learning, which helps to reduce the involvement of an expert. In machine learning, the performance depends on what the expert extracts manner features, but deep neural networks are self-capable for extracting features. Deep learning performs well with a large amount of data than traditional machine learning algorithms, and also deep neural networks can give better results with different kinds of unstructured data. Due to these advantages, deep learning algorithms are applied to a variety of complex tasks. With the help of deep learning, the tasks that had been said as unachievable can be solved. Now deep learning is an inevitable approach in real-world applications such as computer vision where information from the visual world is extracted, in the field of natural language processing involving analyzing and understanding human languages in its meaningful way, in the medical area for diagnosing and detection, in the forecasting of weather and other natural processes, in field of cybersecurity to provide a continuous functioning for computer systems and network from attack or harm, in field of navigation and so on. This paper describes the brief study of the real-world application problems domain with deep learning solutions.
Keywords:	Conceptual based Information Retrieval, Ontology, Semantic Search, Convolutional Neural Network, Deep Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	CLUSTERING AND DATA MINING ON THE EXAMPLE OF HIV-INFECTED PEOPLE DATA
Author:	AIGUL DAULETOVNA KUBEGENOVA, AIZAT GARIFULLAYEVNA ZHAKHIENA, SAYA KUBAIDULIEVNA BAIGUBENOVA, GULNARA SHAVKATOVNA UTYASHEVA, AKYLBEK NURLYBEKOVICH OMAROV
Abstract:	The paper discusses aspects of data research, in-depth data analysis, knowledge acquisition, methods of data processing in the knowledge base, methods of intellectual analysis, and application of data mining in the field of medicine. A group of HIV-infected patients was identified, an analysis with a medical history was carried out, models and an algorithm of actions (input data) were developed, and analysis and experiments with data search methods were carried out. All diseases were presented as a set of numerical vectors and were grouped into clusters, according to the described methods, and with the help of this distribution, the Hopkins statistics value was calculated. Clustering itself was carried out using the usual tools of the sklearn library. Various methods of representation of multidimensional data in a two-dimensional plane are proposed, such as the method of basic components, the Kohonen line, etc. Two different clustering methods were considered, namely, the k-Medium method (using the Kmeans function from the Python sklearn library) and density-based clustering methods with autoconfiguration (from the HDBSCAN function from the Python Hdbscan library). In the case of comparison, the cluster structure is evaluated by changing various parameters of one algorithm (for example, the number of k groups); a model (or several) is built on the received and prepared objects, and its parameters are adjusted. After that testing and analysis of the results were carried out.
Keywords:	Clustering, Vectorization, Correlation, Sklearn, Manipulation.
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	INTERNET OF THINGS IN THE SUSTAINABLE SUPPLY CHAINS: A SYSTEMATIC LITERATURE REVIEW WITH CONTENT ANALYSIS
Author:	KENZA IZIKKI, JAMILA EL ALAMI, MUSTAPHA HLYAL
Abstract:	Sustainability is at the heart of the world's concerns and has become a major challenge in this industrialized era. Committing to more sustainable practices became imperative in all sectors, and particularly in the complex supply chain field. Many industry 4.0 technologies have proven their potential in improving organizations performance. In this context, researchers and practitioners have showed extensive interest in the impact of shifting to a data-driven supply chain operations. However, few works have systematically reviewed how the technologies, and in particular the internet of things, impact the sustainability of the supply chains. A total of 58 papers have been reviewed and categorized in order to identify the evolution of research developments in the field of sustainable supply chain. By the bias of a systematic review, this study tried to map the correlation between the use of the internet of things technologies and the sustainability of supply chains. The findings and discussions aim at highlighting the research trends in our chosen scope of study.
Keywords:	Internet of things, Industry 4.0, Sustainability, Supply chain, Systematic review
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	APPLICATION OF FUZZY MODELS FOR ANALYSIS AND EVALUATION OF QUALITY OF SOFTWARE FOR SPACE PURPOSES
Author:	E.E. ISMAIL, N.K. UTELIEVA, R.Z. MULAEV, T.S. AUELBEKOV
Abstract:	This article presents a method for quantifying software quality attributes using fuzzy set theory methods. The purpose of this work is a substantiation of possible approaches and the feasibility of using fuzzy models for assessing the quality of software for space purposes (Software for Space Purposes). The paper substantiates the feasibility of using fuzzy models for evaluation of the quality of Software for Space Purposes. An approach and a method for the integrated assessment of the quality of the Software for Space Purposes are proposed, which differs from the known ones in the use of fuzzy models for assessing the quality attributes. The novelty of our work lies in the application of fuzzy modeling methods to a new class of problems - the evaluation of the quality of Software for Space Purposes, described by a special hierarchical attributive model, taking into account their features, high requirements for reliability and safety. It is shown that the use of fuzzy models makes it possible to carry out an integral assessment of the quality of PSCN taking into account fuzzy quantitative and qualitative indicators of quality. The paper uses the basic provisions and methods of fuzzy set theory, graph theory, utility theory, numerical methods.
Keywords:	Evaluation Of The Quality Of Software For Space Purposes, Using Fuzzy Models, Integral Fuzzy Quantitative Indicator Of Quality
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text

Title:	INFRASTRUCTURE SHARING PLANNING IN DEF INDUSTRIAL AREA USING PPDIOO FRAMEWORK
Author:	GAPURENDRO ARDHYOGI, BENFANO SOEWITO
Abstract:	Initially, the Industrial Estate allowed each operator and service provider to pull cable Fiber Optic from outside the industry area to the tenant's factory location. This treatment makes utilities in the Industrial Estate full and difficult to maintain. As a result of the full utility, it results in a slow process of handling disturbances. So that 56% of tenants in industrial estates are dissatisfied with ICT services because the SLA delivered is not more than 90%. Therefore, it is necessary to study the interconnection method and the selection of devices that can meet the demands of customers and service providers. This study presents a step-by-step design and implementation of the network construction used as a Sharing Infrastructure. Researchers use the PPDIOO framework in designing the network to be implemented. This research is used to design a reliable, scalable and can be monitored. Furthermore, especially to meet the expectations of Industrial Estate Management, Service Providers and tenants.
Keywords:	Infrastructure Sharing, Network Planning, PPDIOO
Source:	Journal of Theoretical and Applied Information Technology 15^th July 2022 -- Vol. 100. No. 13 -- 2022
Full Text