		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
November 2022 | Vol. 100 No.21

Title:	HOW DO MUSLIM SCHOLARS AND EXPERTS POSIT CRYPTOCURRENCIES IN SOCIAL MEDIA
Author:	ROSLINA BT. OTHMAN, MOHAMAD FAUZAN BIN NOORDIN, MAHFOOZ AHMED, NADZRAH BINTI AHMAD, SALINA BT. KASSIM
Abstract:	The advancement in technology since its inception has brought a lot of innovations in how several things are being done in communities. The current 4th industrial revolution in technology has not only affected the system of interactions but has also introduced a new model of financial exchange called cryptocurrency. The Muslim community has always assumed Sharia as the guide for all its activities, based on the depiction of the prophet, the companions, and, subsequently, the Muslim scholars and experts in society. There have been several speculations on the permissive and prohibitive issues related to cryptocurrency among the Muslim communities since its inception. Social media platforms have also become a medium through which Muslim scholars and experts communicate their views, advice, and justifications on contemporary issues to the community. Therefore, this research aims to identify some of the topic communities and analyse the sentiments of some well-known Muslim scholars and experts in Malaysia on topics related to cryptocurrency. To do this, commentaries made by these scholars and related experts on cryptocurrency were collected from their social media platforms from which they have a range of followers from more than a thousand to millions. Analysis was carried out using some text mining techniques. 126 commentaries were retrieved from the Facebook and Twitter accounts of the indicated scholars and experts, after which a Provalis QDA miner, WordStat, and LightSide content analysis software were applicable for the analysis. The results of the analysis revealed the thematic structure of the commentaries, in which topics like “Cryptographic Halal”, “Authorities Official”, “Blockchain System” and “Buy Goods” were mentioned in 100% of the cases, and topics like “Medium of Exchange Goods and Services”, “Scholars Point of View” and “Legal Tender” were mentioned in 88.9% of the cases. The topic “Legal Tender” as used in the commentaries makes it clear that most of the scholars and experts in Malaysia today were in support of the argument that cryptocurrency can be used as a legal tender in Muslim communities. Similarly, the results of the sentiment model also show a strong percentage of accuracy in which most of the commentaries made were positive about the subject matter.
Keywords:	Topic Community, Sentiments, Muslim Scholars and Experts, Cryptocurrencies, Social Media Platforms, QDA miner, WordStat, LightSide
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	STRATEGIC MANAGEMENT FOR DETERMINATION OF SHIP FACILITIES LOCATION BASED ON OPERATIONAL AND ENVIRONMENTAL FACTORS
Author:	SUTRISNO, OKOL SRI SUHARYO, AYIP RIVAI PRABOWO
Abstract:	To support the presence of elements of naval vessels in the North Natuna Sea, it is necessary to have supporting facilities for Ship Maintenance and Repair Facilities that function as logistical support, especially ship repair and maintenance. Mileage The nearest ship maintenance and repair facility from the North Natuna Sea is the Mentigi City area which is approximately 510 Nautical miles. This becomes an obstacle if the presence of the shipping element in the North Natuna sea operation area requires logistical support. Because the distance is too far to carry out ship maintenance and repairs, it is deemed necessary to have another location for ship maintenance and repair facilities to support ship operations in the North Natuna waters. In selecting the location for ship maintenance and repair facilities, several factors must be considered, especially the Environmental Requirements & Operational requirements. The method that can be used to solve these problems is the Fuzzy Multi-Criteria Decision Making (Fuzzy MCDM) method. The Environmental Requirement factors consist of the Earthquake Threat, the distance of the operating field, the distance to the city center, and the hydrographic and oceanographic factors (sea depth, tides, and ocean current speed). While the Operational Requirement factors are influences on other countries, threats from other countries and community conflicts, transportation access to public ports and airports, supporting facilities (water facilities, communication facilities, electricity facilities, transportation facilities, and sea lanes), and operational costs. For alternative locations, ship maintenance and repair facilities consist of the Pontianak area (DP), the Ranai area (DR), and the Tarempa area (DT). From the three alternative locations, the best alternative for the location of ship maintenance and repair facilities is Ranai Region (DR) with the highest-ranking value of 0.403, then Pontianak Region (DP) with a value of 0.302, and Tarempa Region (DT) with a value of 0.295.
Keywords:	Location Determination, Fuzzy MCDM, Environmental Requirements, Operational Requirements
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	THE INFLUENCE OF SALARY, WORK FACILITIES, AND LEADERSHIP FACTORS ON EMPLOYEE PERFORMANCE
Author:	ADI BANDONO , SUKMO HADI NUGROHO , OKOL SRI SUHARYO , APRIL KUKUH SUSILO
Abstract:	Government agencies in carrying out work operations should provide work facilities to motivate employees in carrying out their work so as to improve employee performance. The important thing that concerns employees in any institution today is the issue of wages and salaries, including in government institutions. In addition, the leadership style of leaders in government institutions can also be a driving force and encouragement for employees at work. Employee performance is a must in government institutions so that it is easy to carry out their activities to provide services to the wider community. The problem is whether the salary factor (X1), work facilities (X2) and leadership style (X3) partially and simultaneously affect the performance of employee personnel in government institutions (Y). Of the three factors, it is sought which factor has the most dominant influence on employee performance. This study aims to determine partially and simultaneously the variables of salary, work facilities, and leadership style on employee performance in government institutions. And to find out from the three research variables, namely salary, work facilities, and leadership style are variables that have a dominant influence on employee performance. The population in this study were all employees, totaling 100 employees of a government institution. The research sample is 85 respondents. Data collection techniques using a questionnaire. The data analysis technique consists of a validity test, reliability test, classical assumption test, multiple linear regression analysis, t-test, and F test. The results obtained are that the multiple regression analysis shows that the variables of salary, work facilities, and leadership style have a partial and partial effect simultaneously on employee performance. While the dominant influencing variable is the salary factor.
Keywords:	Salary, Work Facilities, Leadership Style, Employee Performance, Government Institution
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	ANALYSIS OF FACTORS AFFECTING FIN-TECH FORENSIC ON APPLICATION OF QRIS IN PAYMENT SYSTEM
Author:	ARYANTI WARDAYA PUSPOKUSUMO, BAMBANG LEO HANDOKO
Abstract:	Disruption of the use of financial technology is undoubtedly unavoidable. One of the pieces of evidence is developing the primary business model of financial technology, specifically digital payments. Various applications offer convenience in making payments, applying the QR code scan payment method. The variety of QR Codes provided by the application is why Bank Indonesia standardizes the QR Code into QRIS (QR Code Indonesian Standard). Behind the good hopes at digital payment services, of course, it cannot be denied that the development of cybercrime is also increasing. Fin-tech Forensics, a combination of fin-tech and digital forensics science, aims to investigate and reconstruct criminal financial activities. Our research want to test effects implementation of QRIS on fin-tech forensics in Jakarta using indicators based on previous literature studies. The method used in data collection is by distributing questionnaires. All data were processed using Smart PLS 3. This study indicates that two variables perceived guardianship and perceived cyber threats each has significant and positive effect on fin-tech forensics. On the other hand, security and trust not significantly affects fin-tech forensics on application of QRIS in payment system.
Keywords:	Digital, Payment, Cybercrime, Fin-tech, QRIS, Forensic.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	ANALYZING THE INFLUENCE OF CRYPTOCURRENCY ON THE SWITCHING INTENTION OF GEN Z AND MILLENNIALS TO USE CRYPTOCURRENCY AS AN INVESTMENT ASSET
Author:	WILLY SANDI, TANTY OKTAVIA
Abstract:	Cryptocurrency are proven as assets that have high risk but the owner of the cryptocurrency himself can set the level of risk that suits himself, therefore this study will focus on society and the younger generation where interest in crypto is very large and can be an interest in the future. This study adopts a model based on the Push-Pull-Mooring (PPM) theory. As a result, personal innovativeness, reward sensitivity, and knowledge have proven to have a positive and effective effect on switching intention. The reason that variable play a role in switching intention and ignoring risk factors is that it could be that the individual has more curiosity, and personal motives is tempted by returns so they are competing to try cryptocurrency as their investment. Moving to cryptocurrency become important but there are risks that people need to know before indeed plunging completely into cryptocurrencies. The knowledge that individual investors are trying to acquire is only knowledge related to trends or following and not seeking risk-related knowledge from the cryptocurrency itself.
Keywords:	Cryptocurrency, Investment, Gen Z, Millennials, Asset, Ppm, Switching Intention, Perceived Risk, Personal Innovativeness,
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	NEURAL NETWORK AIDED OPTIMIZED AUTO ENCODER AND DECODER FOR DETECTION OF COVID-19 AND PNEUMONIA USING CT-SCAN
Author:	SRINIVASA REDDY K, P. VENKATESWARA RAO, A.MALLIKARJUNA REDDY, K SUDHEER REDDY, DR. J. LAKSHMI NARAYANA, SRI SILPAPADMANABHUNI
Abstract:	Most of the countries in the world are now fighting against Covid-19 and many of the people are losing their life because of the less immunity or due to the late diagnostics and it is especially in the case of old age people and people with other medical issues. The concept of early detection of disease is really important in the case of the Covid-19 scenario because along with the infected people, the other people who are in close contact with the infected persons will also have life risk. During this pandemic, pneumonia and Covid-19 people suffers from almost the same symptoms. So, the proposed work designs an automated system that can perform multi-classification on general health, pneumonia and Covid-19 through Chest X-Rays by designing an optimized auto encoder- decoder network. Most of the earlier approaches which are used to perform the binary classification couldn’t differentiate the Covid-19 and Pneumonia effectively because the traditional CNN extract the high level features, which are similar in case of COVID-19 & Pneumonia. These two have variations in the case of low level features. The major focus of this paper is to construct a hyper-parameterized auto encoder-decoder system that can help the user to detect level of lung infection. The level of infection helps the model to accurately classify the model. This method helps doctors and other medical-related people with the early diagnosis of disease.
Keywords:	Neural Networks, Augmentation, Auto Encoder Decoder, Latent Space Representation, Hyper-Parameters
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	MEASURING PUBLIC TRANSPORT ACCESSIBILITY IN CASABLANCA ACCORDING TO UNITED NATIONS SUSTAINABLE DEVELOPMENT GOALS USING A GEOGRAPHICAL INFORMATION SYSTEM
Author:	ELHASSAN ELBRIRCHI, ISHAK HBIAK
Abstract:	Casablanca is the biggest city in Morocco. it contains 40 % of national mobility. Thus, accessibility to public transport network is a key factor for the development of the city. It is also very crucial to maintain a minimum quality of transportation services over time. United Nation Sustainable Development Goals (SDG), adopted in September 2015, highlight the importance of urban transport accessibility in goal number 11 and propose the indicator number 11.2.1 to monitor the accessibility to services, goods and opportunities for all. The objective of this research is to estimate this indicator value for Casablanca city center and surrounding provinces: Mohammadia, Mediouna and Nouaceur. This research thus contributes to the efforts to implement the objectives of the 2030 Agenda in Morocco, particularly concerning urban transport. We also seek to compare results for different public transport modes available in the city, namely the tram and the bus. To achieve these goals, we first propose an adapted methodology based on the metadata of the SDG indicator 11.2.1. To do this, we have created a Geographic Information System (GIS) database containing needed data such as administrative districts, urban roads, bus network lines, tram lines and population statistics. As a result, we found that 74,38% of the population in all our study area has access to bus network while 95.51% of the population of the center has access to bus and tram networks. The detailed results by sector highlight the imbalance in the access to transport between the city center and the surrounding areas.
Keywords:	Urban Transport, Sustainable Development Goals, Accessibility, Geographic Information Systems, Casablanca
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	USABILITY EVALUATION PRACTICES WITHIN AGILE DEVELOPMENT: ENGAGING WITH USABILITY AGILE PRACTITIONERS' CONCERNS
Author:	AZIZ BIN DERAMAN, FOUAD ABDULAMEER SALMAN
Abstract:	The success of developing software systems largely depends on the effectiveness of coordination between software developers and usability engineers. Yet its integration has shown not to be straightforward because of various priorities and approaches which make it further complicated. This paper proposes an approach for improving the coordination between agile developers and usability engineers. The contribution of this paper is to investigate the challenges that prevent such integration. The investigation involved a combined questionnaire survey and interviews with participants from software development companies. The result reveals that during the development process, there is a lack of collaboration between usability practitioners and agile developers. This lack is classified into three main aspects: activities management, artifacts management and communication management. Also, the authors describe an integration model to be used as a solid basis to mitigate the challenges and propose a policy agenda for future work toward improving the coordination in multidisciplinary agile usability software teams.
Keywords:	Usability, Usability Evaluation, Software Development Process, Usability Management
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	IDENTIFICATION AND CLASSIFICATION OF DISEASES IN BASIL AND MINT PLANTS USING PSORBFNN
Author:	V. SATHIYA, DR. M.S. JOSEPHINE, DR.V.JEYABALARAJA
Abstract:	The world is a place for many living things apart from human beings, like plants, trees, animals, bacteria, insects, mammals, reptiles, etc., in which plants and trees are the vital source for oxygen for us humans. Every organism has its own life-time where it could live prolong for several hundred/ thousand/ billion years like a ‘Bristlecone pine-tree’ or algae like ‘Proterocladusantiquus’. During their lifespan each plants and trees also experience sickness or illness due to diseases which results in withering away, fruits and leaves drop. Studying these factors affecting the plants, plant’s lifespan, solutions and classifications of plants and diseases are known as “Plant Pathology”. Though the Plant Pathology could be achieved through machine languages and automated machine approaches, the involvement of humans for classifying and categorizing diseases have been the only approach till-date. It is costlier, time consuming and labour intensive. Hence the proposed research aims at developing an algorithm that could automatically identify, classify and categorize the plant inputs through RBFNN (radial basis function neural network) with image segmentation through weighing function, where the optimization is done through PSO aiming at efficient and higher accuracy rate based rapid results. The developed RGM (region growing algorithm) increases network efficiency for speed and clustering the common attribute-based seeds towards extraction process of plant’s feature. By focusing on fungal diseases classification with factors like, leaf spots, leaf curl, late blight, common rust, early blight and cedar-apple rust the study was carried-out. The developed algorithm and outcome through test and train method shows efficiency, accuracy in classifying and categorizing the plant diseases.
Keywords:	K-Means, Particle Swarm Optimization, Radial Basis Function, Neural Networks, Region Growing Algorithm
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	DECOMPOSITION OF MEASURED DATA ON THE NETWORK SEGMENT BETWEEN LAN AND ISP
Author:	AMREEV M., NAUBETOV D.A. , YAKUBOVA M.Z., MIRZAKULOVA S.A., SERIKOV T.G.
Abstract:	Functioning packet trunks experience a constant increase in load in wired access networks, which in turn are transformed and becoming more and more optical in accordance with GPON (Gigabit Passive Optical Network) technology. It is established that numerous studies of the measured data on packet network trunks confirm that they are not stationary, and their structure is multicomponent, and there are no studies of the structure of network access traffic. Therefore, this article is devoted to the study of network traffic between LAN and ISP. On the basis of the measured data, scattering diagrams are constructed, a statistical assessment of the correlation of the measured series to the general population of the normal distribution is carried out, a correlogram is constructed and the decomposition of the time series is performed by the SSA (Singular spectrum analysis) method, which has a strict justification within the framework of the theory of dynamical systems. Also, it is concluded that the traffic entering the backbone network also has a complex structure, with its decomposition into the main components of the time series.
Keywords:	LAN, ISP (Internet service provider), SSA (Singular Spectrum Analysis), Time series analysis, OPNET Modeler, Wireshark
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	QR CODE DETECTION AND RECTIFICATION USING PYZBAR AND PERSPECTIVE TRANSFORMATION
Author:	FRANCISCO CALVIN ARNEL FERANO, JAN KEANE OLAJUWON, GEDE PUTRA KUSUMA
Abstract:	The increasing and widespread use of QR codes in everyday life has led to an increase in the activity of counterfeiting the QR code itself. Authentication of QR codes is not easy. For this reason, a proper QR code detection method needs to be given to the QR code image. However, the performance of QR code detection is highly dependent on the pre-processing method used. An appropriate pre-processing method is needed to be given to the QR code image so that the QR code becomes easier and faster to detect. This paper proposes the preparation of various pre-processing methods for a QR code dataset containing 1350 QR code photos so that they can be detected properly using Pyzbar. Several pre-processing methods are chosen to be performed in the experiment, which are: images gray scaling, conversion into RGB images, binarization through thresholding, gaussian blur combined with Otsu threshold, Otsu threshold only, a combination of the five methods, and a combination of the three best methods. This set of pre-processing methods improves detection performance using Pyzbar which allows QR code datasets to be rectified properly using a perspective transformation. The experimental results show that the proposed method produces a good percentage of detection results with the best value of 95%. All detected QR codes have been successfully rectified using perspective transformation and produced good alignment accuracy with the best value of 85,661%. The accuracy increases after being evaluated with one-pixel misalignment tolerance with the best value of 92.144%.
Keywords:	QR Code Detection, Image Pre-Processing, Pyzbar Library, Image Rectification, Perspective Transformation.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	TOMATO PLANT OBSERVATION AND DISEASE DETECTION USING MACHINE LEARNING AND IOT
Author:	JOHANNES FARRELL LANDUTAMA, GALUH PUTRA WARMAN, BENFANO SOEWITO
Abstract:	The development of technology in the agriculture sector has shown promise in the last few years. Crop management, disease detection, and irrigation management are examples of activities that can be implemented with modern technological approaches using artificial intelligence and IoT. Modern disease detection in agriculture uses machine learning to classify the health condition of plants by processing input images of leaves or branches into pre-trained machine learning models. Studies for plant disease detection have been done by other researchers using high computing capability devices; in contrast, there is still little research on implementing such machine learning models for mobile or small IoT-based devices. This study explores and proposes a model of machine learning algorithm namely CNN MobileNet and SVM, to run on small IoT-based devices. After some experiments, it was found that MobileNet can be used for this particular purpose. Furthermore, this research also shows a new contribution regarding the implementation of machine learning for disease detection into an IoT microcontroller commonly used for irrigation and soil moisture observation. The proposed model in this study has been tested in real-world experiments for Tomato plant disease detection with an approximate accuracy of 91.45%.
Keywords:	Disease Detection, Machine Learning, IoT, MobileNet, Arduino
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	CLOUD SERVICE OPTIMIZATION BASED ON REVERSE AUCTION METHOD
Author:	R. ANANTHA KUMAR, K. KARTHEEBAN, G. SUMATHI, S. RAJESH
Abstract:	Cloud administrations have been progressively applied to give accessibility on on-demand basis to a tremendous quantity of computing demands, like resources, information, computing, etc, in which accurately choose and relegate the correct resources to an application or workload. Our manuscript proposes an Original Web based Reverse Auction Method (OWRAM) dependent on web-based calculation for distributing Cloud Computing (CC) applications, which may assist clients as well as suppliers to construct workflow applications in CC scenario. OWRAM comprises of 3 sections: design of web algorithm, compete proportion estimation, and execution evaluation. OWRAM is presented for the cloud client mediator to select the last champ’s dependent on web-based algorithm (WA) and VickreyClarkeGroves (VCG) system. Compete investigation is utilized to compute the compete proportion of the proposed algorithmic program contrasted include the online algorithmic program. This examination technique is important to evaluate the execution of proposed algorithmic program, excepting the supposition of the allotment of cloud suppliers' bid prices. This outcome demonstrates that the proposed OWRAM is the proper technique since it permits the cloud client mediator to settle on buy choices through unknown future bid prices. The variation of auction cycles and exchange price can astonishingly impact and work on the execution of the presented reverse auction algorithmic program.
Keywords:	Reverse Auction, Cloud Computing, Optimization, Resource Allotment
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	MODELLING A DEEP KERNEL-BASED LEARNING APPROACH FOR SPINAL CORD INJURY PREDICTION
Author:	P.R.S.S.VENKATAPATHIRAJU, Dr.V.ASANAMBIGAI, Dr. SURESH BABU MUDUNURI
Abstract:	Deep Learning (DL)-based spinal cord injury (SCI) prediction is an unswerving model in medical imaging. However, the prediction process is challenging during the segmentation and classification process. Conventionally, radiologists examine the spinal cord images to indicate the abnormalities in the spinal cord manually. The manual high dimensional spinal cord feature space interpretation makes it complex to identify the severity level. However, DL approaches help in faster and more accurate predictions. The model intends to predict the abnormal and normal spinal cord images automatically. Under certain conditions, the weight of the training images is based on similarity distribution which is likely to show better performance. It does not deal with unrepresentative data. Thus, the kernel-based learning process intends to reduce the difference between the testing and training data and explore the kernel learning value for image weighting. Here, a novel kernel-based weighting method reduces the maximal mean discrepancy (MMD) among the testing and training data, facilitating kernel and weighted image optimization. Experimental results demonstrate that the anticipated kernel-based image weighting model has a higher computational disorder prediction ability than other approaches. The numerical outcomes prove that the model has superior performance to the prevailing approaches regarding prediction accuracy, recall and precision.
Keywords:	Deep Learning, Spinal Cord, Weight Computation, Kernel Learning, Discrepancy Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	DIGITAL LEARNING RESEARCH DURING COVID-19 PANDEMIC: CONTRIBUTED TO ACTUALIZATION OF VISIONARY POLICYMAKERS OF SENIOR HIGH SCHOOL
Author:	TRI WAHYU LISWATI, MUSTAJI1 , NUNUK HARIYATI
Abstract:	This research will analyzed on obtaining a visualization and profile of Digital Learning (DL) during the COVID-19 pandemic. This research employed a purpose with bibliometric analysis of publications, which we think will be useful for future research. In general, this research findings indicate that the COVID-19 pandemic has a favorable influence on the acceleration of digitalization in poor nations. Scopus by Elsevier meta-database, is the world's largest academic meta-database, was used by the researchers. Another conclusion is that there is a movement in the face-to-face learning paradigm approach to digital technology-based learning, which has been shown to be successful in enhancing student learning outcomes. Fundamental research implications: educational transformation can happen in online education, changes to distance learning, changes in roles, also ways both now and after the COVID-19 pandemic. In today's educational policy, technology will play a significant role. In addition, to open opportunities for the actualization of visionary policymakers in senior high schools.
Keywords:	DL, COVID-19 Pandemic, Trend Research, Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	PERFORMANCE ANALYSIS OF DECISION TREE EXTENDED CLASSIFIERS (DTEC) ON CLINICAL DATASET OF COVID PREDICTION USING OPTIMAL FEATURE SELECTION
Author:	DR. P.S.S. AKILASHRI, G NITHYA
Abstract:	In Computer Science Technology, Artificial Intelligence, Data Analytics and Machine Learning plays a predominant role in decision-making strategies. By choosing suitable method and algorithms from any of these fields, a good decision can be taken. In health care industry, at present, prediction of Covid 19, is still a very big challenge, since false positive, false negative metrics are occurring frequently through various covid test. Our main aim, in this proposed work is to increase the prediction of accuracy of Covid, by considering the optimum number of features alone, by taking into consideration the laboratory measurement, and also by clinical test understanding. When target variable is binary, the classification algorithm based on Tree Based Extended Classifiers like Random Forest, AdaBoost, XGBoost can be proposed with necessary features. The results are observed from the proposed algorithms, that gets trained using the training dataset using standard data repository and it is being tested with the testing dataset. By analyzing the performance metrics, the obtained results showed that the prediction accuracy is increased and also false positive and false negative are reduced. In the proposed work, the tree based extended classifiers of Random Forest and Extended Gradient Boosting produces maximum 92% accuracy with 11 features using Gini Index. Apart from accuracy, the metrics such as false positive and false negative are playing the important role. In this proposed work, the false negative is as low as 5 out of 14 by XGB, and false positive with the minimum value of 3 out of 106 using Random Forest. Thus, these methods of covid predictions are useful for health care community, if it is being utilized in an efficient manner.
Keywords:	Feature Selection, Binary Classification, Tree Based Classifier, Covid, Clinical data, Confusion Matrix.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	UNERRORIC OF TURBOJET ENGINES THRUST ASYMMETRY CONTROL FOR FLIGHT SAFETY
Author:	ADELIYA BUROVA, ANATOLY RYAPUKHIN
Abstract:	This article shows a good idea to digitalize any unerrorics for software of turbojet engine thrust asymmetry control. The well-known results of scientific developments presented in the publications used confirm the practical usefulness and relevance of digitalization of measurement results processing methods for the software unerroric of applied algorithms for system analysis and approximate synthesis. However, the equality of addition and multiplication speeds in digital signal processors and programmable logical devices is achieved mainly by hardware. Therefore, the need to reduce hardware costs for digital signal processing increases the role of IT-research on the possibility of flight safety analytics by software. The article purpose is a research of software for unerroric of such control. The used methods of that research are the methods of system analysis and the methods of the software modeling. To achieve the stated goal, the following tasks have been set and solved: the task of directional search and comparative evaluation of digital methods for ensuring unerroric of control of mutual compliance of controlled values of thrust parameters of two-shaft turbojet two-circuit engines of the same series; the task of adapting deductive algorithms for digital processing of measurement results of controlled values of thrust parameters of two-shaft turbojet two-circuit engines for the software of an unerroric of the flight of a twin-engine aircraft with such engines; the task of selecting the element base for hardware and software experimental modeling of digital algorithms for software unerroric of thrust asymmetry of turbojet two-circuit engines. The formulation and solution of problems of selection and adaptation of methods and algorithms for digital processing of measurement results contributed to the development of software for flight safety unerroric of a twin-engine airliner with twin-shaft turbojet engines by tightening the control of the mutual correspondence of the controlled values of their thrust parameters. The results of experimental modeling of adapted algorithms have confirmed the practical feasibility of such software and the high importance of IT-research in its design. It is described the possibility of turbojet two-circuit engines tractions forces asymmetry analysis unerroric. A set of formulas for digital processing of control signals from rotors speeds sensors of civil airplane with two turbojet two-circuit engines is presented.
Keywords:	Airliner, Engine, Thrust, Quality, Unerroric.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	ACCEPTANCE OF THE MADRASATI (M) LMS AMONG PUBLIC SCHOOL TEACHERS AS AFFECTED BY BEHAVIORAL INTENTION IN RIYADH
Author:	HAMAD MUAYBID ALHARBI, HABIBAH AB JALIL, MUHD KHAIZER OMAR, MOHD HAZWAN MOHD PUAD
Abstract:	The utilisation of Madrasati (M) LMS among school teachers has become crucial in teaching and learning in Saudi Arabia, specifically in Riyadh. However, the acceptance and utilisation of the M LMS are still poor in KSA. Teachers' acceptance and use of M LMS are linked to the Unified Theory of Acceptance and Use of Technology (UTAUT) and Technology Acceptance Model (TAM) factors. This study aims to determine whether performance expectancy (PE), effort expectancy (EE), social influence (SI), facilitating conditions (FC), attitude, and competence to use M significantly influence behavioral intention (BI) to utilise M among teachers in Saudi public schools in Riyadh. Consistent with this objective, the quantitative research design, specifically the survey technique, was used to collect data from a sample of 374 public school teachers in Riyadh. The results revealed that UTAUT (PE, EE, SI, FC) and TAM (competence) factors significantly affected M LMS utilisation among teachers, while attitude had no significant effect on M LMS utilisation. The study found that out of six tested hypotheses, H1, H2, H3, H4, and H6 were accepted, while H5 was rejected. It can be concluded that PE, EE, SI, FC, and competence significantly affect M LMS utilisation among teachers in Riyadh.
Keywords:	Acceptance, LMS, Madrasati, School Teachers, TAM
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	DETECTING AUTISM SPECTRUM DISORDER FOR TODDLERS USING MACHINE LEARNING TECHNIQUES
Author:	RIHAM ALBARAZI, Dr. BASSEL ALKHATIB
Abstract:	Autism is a disorder characterized by difficulty in social interactions, communication challenges, and repetitive behaviors. In recent years, treatments for autism have been constantly evolving, therefore, it is essential to diagnose children at an early age to be able to control their symptoms. We have used information about signals that will help us in early detection of autism, to help affected children to integrate into society and live independently. For these reasons, this article focused on the use of data for only toddlers, and it compared deep learning and traditional classifiers for achieving efficient and accurate classification in the environment of machine learning, in contrast to previous research that focused on using traditional classifiers for different older ages. Among all applied algorithms, Support Vector Machine (SVM), Logistic Regression (LR) and Multilayer Perceptron (MLP) are perhaps worthy of further study on this problem in terms of only scores (Accuracy, Recall, Precision and F1), and only LR in terms of both scores and training runtime.
Keywords:	Autism Spectrum Disorder, Traditional Machine Learning Algorithms, Deep Learning, Classification, Toddlers.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	CLASSIFYING AND EVALUATING PRIVACY-PRESERVING TECHNIQUES BASED ON PROTECTION METHODS: A COMPREHENSIVE STUDY
Author:	SHERMINA JEBA, MOHAMMED BINJUBIER , MOHD ARFIAN ISMAIL, RESHMY KRISHNAN, SARACHANDRAN NAIR , GIRIJA NARASIMHAN
Abstract:	Many data analysis applications encounter the challenge of preserving the privacy of information. Over the past few years, many partially published data have become subjects of various concerns, ranging from unlawful access to private data to privacy breaches and unintended use of personal information. This problem has limited progress in advancing published data, prompting the need for robust privacy-protection techniques, which can minimize the chances of identifying sensitive individual information by unauthorized persons. The simplest solution to preserving sensitive information is to avoid public disclosure of such information. However, this might constitute a problem for data analysis, as there may not be available datasets to analyze and discover interesting patterns. Sometimes, the dataset must be disclosed under government regulations to enable access and subsequent analysis. Sometimes, the data owner may modify the data to ensure privacy and retain sufficient information for a safe release to the public. This process is usually referred to as privacy-preserving data publishing (PPDP). The review in this paper has rigorously evaluated some existing preserving privacy techniques and classified them based on their methods to reduce the risk of disclosing information. Moreover, the review focused on the methods of the current preserving privacy techniques to protect data and preserve the privacy of sensitive information, which is considered a key contribution of this study as it is expected to guide scholars to gain a deeper knowledge of the existing privacy preservation methods. This study also compared and analyzed various privacy-preserving techniques in terms of their advantages and drawbacks.
Keywords:	Big Data Privacy Preservation; Anonymization; Data Publishing.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	PREDICTING EMPLOYEE ATTRITION AND PERFORMANCE USING DEEP LEARNING
Author:	SAMER M. ARQAWI, MOHAMMED A. ABU RUMMAN, EMAN AKEF ZITAWI, ANEES HUSNI RABAYA, AHMAD SALEH SADAQA, BASEM S. ABUNASSER, SAMY S. ABU-NASER
Abstract:	Making decision can have a vital role in the administration and might indicate the most significant constituent in the route of planning. Attrition of employees is a well-known issue that requires the correct judgments from the management to keep highly skilled employees. Excitingly, Artificial Intelligence (AI), Machine and Deep Learning were applied broadly for instance like an effective means for the prediction of employee attrition. The aim of this study was to utilize machine and deep learning models to predict employee attrition with a high accuracy; furthermore, to identify the most influential factors affecting employee attrition. The dataset used in this study was collected from Kaggle Depository. The dataset was created by the IBM analytics that consists of 35 features from 1,470 employees. To get the best accuracy of prediction of employee attrition, we preprocessed the dataset, balanced it and split it into three sets: train, valid, and test datasets. Several experiments were carried out to show the practical value of this study. The deep learning model archived f1-score of (94.52%), recall (94.52%), and precision (94.58), accuracy (94.52%), whereas the best machine learning model archived f1-score (92.52%), recall (92.55%), precision (92.52), and accuracy (92.55%) for the prediction of employee attrition.
Keywords:	Employee Attrition; Machine Learning; Deep learning; Prediction
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	PREDICTION FOR NON-REVENUE AND DEMAND OF URBAN WATER USING HYBRID MODELS OF NEURAL NETWORKS AND GENETIC ALGORITHMS
Author:	BURHAN FARAH, MOHAMMED AWAD, AMJAD RUTROT
Abstract:	Palestine faces continuous struggles in maintaining the proper water supply in the water sector. Therefore, “Non-Revenue water” and supply demands are necessary to reduce the water losses and save the financial resources to strengthen the water sector. To do that we must develop the ideal water usage/loss prediction model to plan the future usage of water. This paper explores and develops AI models that could efficiently predict the water losses and water demands in Palestine, focusing mainly on Beitunia city. Different Artificial Neural Networks (ANNs) with different learning approaches had been used in this paper. The historical and extracted data, representing water supply/consumption in Beitunia are used to propose a nonlinear model. The data is input into the models of ANN and helps predict the water losses/demand in Palestine, to provide a more accurate prediction model. Three models of ANNs were used; Multilayer Perceptron NNs (MLPNNs) MLPNNs-LM, Radial Basis Function NNs (RBFNNs, newrb), and Genetic Algorithms (GAs-MLPNNs). We also used the Autoregressive integrated moving averages (ARIMA) as a linear statistical model to predict water supply using collected data from Beitunia city. The result showed that ANNs models are more efficient than the ARIMA model for the prediction of water movement. Finally, The MLPNNs-LM model results exceeded the other ANNs models in comparison.
Keywords:	Prediction, Water Losses, Water Demand, Non-Revenue water, Multilayer Perceptron NNs, Radial Basis Function NNs, Genetic Algorithms, ARIMA.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	A NOVEL APPROACH FOR AUTOMATIC SPEAKER IDENTIFICATION OF ASSAMESE LANGUAGE USING COSINE SIMILARITY AND ABSOLUTE MFCC FEATURE MATRIX
Author:	ANKUMON SARMAH, RIZWAN REHMAN, PRIYAKSHI MAHANTA, KANKANA DUTTA, KAUSTUVMONI BORDOLOI, KIMASHA BORAH, HARJINDER SINGH
Abstract:	Automatic speaker Identification (ASI) is always challenging work for researchers. ASI is a process where a speaker is recognized automatically from his/her voice sample by comparing it with their previously recorded voices. The machine learning approach has been gaining popularity in recent years for ASI. Different machine learning approaches used in ASI in recent years are Convolutional Neural Network (CNN) [14,15,16], Deep Neural Network (DNN) [10,11,12,13], Artificial Neural Network (ANN) [17,18]. This research aims to build an automatic speaker identification system for the Assamese language, which is spoken in the North-Eastern part of India and is one of the low-resource languages. So far, cosine similarity and parallel processing methods have not been used for speaker identification in the Assamese Language, which is the novelty of the current work. The model developed in this work uses Mel-frequency cepstral coefficient (MFCC) to extract important features of speakers' voices to create a training sample set in the first phase. In the present approach, we have used the Speaker's absolute feature vectors (MFCC) directly, without any averaging, in order to retain and exploit the Speaker's unique characteristics. In the second phase, the features in the training sample set of the first phase are compared with the real-time test voice samples using the cosine similarity method to identify the Speaker automatically. Parallel processing is used to compare all the coefficients in the test voice sample with the training voice sample to make the system faster. The effectiveness of the proposed method has been established in terms of precision, recall, f1 score, and accuracy value. The model demonstrated an accuracy of 91% for speaker identification in the Assamese language.
Keywords:	Mel- Frequency Cepstral Coefficient (MFCC), Speaker Identification, Cosine Similarity, Automatic Speaker Identification (ASI), Assamese
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	MCDM BASED USABILITY EVALUATION OF E-GOVERNANCE SERVICES USING HUMAN PERCEPTION
Author:	BHASWATI SAHOO, PRASANT KUMAR PATTNAIK, RABINDRA NARAYANA BEHERA
Abstract:	E-Governance is the use of information technology (IT) for improving different services provided by the government sector for delivering better and transparent services to the citizens in the trustworthy cyberspace. Information and Communication Technology (ICT) is rapidly changing, and it is almost essential for the government to use IT services effectively in order to provide hassle-free services to citizens. It has the potential to govern with unprecedented transparency and accountability, as well as to significantly reduce the cost of government business operations.Citizens expect their services to be delivered to their door in order to obtain more up-to-date information. Citizens want to access information through government websites as the internet's popularity grows unabated. In order to check the efficiency and reliability of the e-Governance services, various parameters are taken into consideration for decision making. These parameters are taken into account and the decision for the score of usability is verified by use of various Multi Criteria Decision Making (MCDM) Techniques. MCDM technique is applied on the available alternatives for each criterion and are compared also. The focus of the methods is to find out the best alternatives among available features to make the e-Governance Services successful in the upcoming scenarios. This paper is focused on ranking of attributes based on their usability for good e-Governance system using feedback mechanism method in AHP technique.
Keywords:	Analytic Hierarchy Process, E-Governance, Multi Criteria Decision Making, Priority Ranking, Pair-Wise Comparison, Usability.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	DIGITAL MARKETING COMMUNICATION STRATEGY VIRTUAL TOURISM IN 5 SUPER PRIORITY DESTINATIONS ON THE COVID-19 PANDEMIC
Author:	CANDRANING KOES PRIMASTAHTA, LIDYA WATI EVELINA
Abstract:	The tourism sector in Indonesia is feeling a significant hit from the COVID-19 pandemic. As one of the countries that relies on the tourism sector as the largest foreign exchange income besides the non-oil and gas sector, various efforts have been made to restore the glory of national tourism to its former place. Virtual Torism became the initial effort used by Indonesia as a way to overcome the collapse of the national tourism industry. With Virtual Torism, travel activities can be enjoyed anywhere and anytime, because it only requires an internet network, social media platforms and gadgets. With the emergence of this innovation, it is hoped that it can maintain sustainable tourism and reduce cases of the impact of the COVID-19 pandemic because it can be enjoyed at home. This study focuses on answering the reasons for the Ministry of Tourism and Creative Economy of the Republic of Indonesia to develop virtual tourism and marketing communication strategies in Indonesia for virtual tourism during the pandemic in 5 super priority destinations (DSP). With a qualitative-descriptive approach and thematic analysis techniques, this study concludes that the marketing communication strategy is a direct direction of the Government. The formulation of this strategy is supported by the help of sprinkler tools to find out thematic sentiments on social media that are circulating in the community. In addition, to introduce to the public related to virtual tourism using co-partner cooperation with tourism business actors as well as co-branding with actors and influencers. The information provided for 5 DSPs is based on 5 Wonders ((Nature, Culinary & Wellness, Culture, Recreation, Adventure). Then also uses special hashtags such as #WonderfullIndonesia, #InDOnesiaCARE, #diIndonesiaAja, #VirtualTourism, and #5DestinasiSuperPrioritas which is intended to be able to adjusting to social media algorithms.
Keywords:	Communication Marketing, Virtual Tourism, Media Social, 5 Destinasi Super Prioritas, Pandemi Covid-19
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	DEEP LEARNING BASED SOUTH INDIAN SIGN LANGUAGE RECOGNITION BY STACKED AUTOENCODER MODEL AND ENSEMBLE CLASSIFIER ON STILL IMAGES AND VIDEOS
Author:	Ramesh Manohar Badiger, Dharmanna Lamani
Abstract:	Recently, sign or gesture recognition has been challenged by concerns like high computational cost, occlusion of hands, and inaccurate tracking of hand signs and gestures. The existing models face difficulty in managing longer term sequential data, due to poor information learning and processing. To highlight the aforementioned concerns, a novel deep learning based ensemble model is proposed in this article. Firstly, the sign/gesture images are acquired from American Sign Language (ASL)-Modified National Institute of Standard and Technology (MNIST) and real time South Indian Sign Language (SISL) databases. In addition, K-means clustering with the Gaussian blur method is implemented for precisely segmenting the sign/gesture region. Next, the feature extraction is carried-out using Gray-level Co-occurrence Matrix (GLCM) features and AlexNet, and then the dimensionality of the extracted feature vectors are decreased using a deep learning model: stacked autoencoder. The dimensionally decreased feature vectors are fed to the ensemble classifier (Multi-Support Vector Machine (MSVM) and Naive Bayes) to classify 24 alphabets and 30 SISL classes on the ASL-MNIST and real time SISL databases. The extensive experiments demonstrated that the ensemble based stacked autoencoder model achieved 99.96% and 99.08% of accuracy on the ASL-MNIST and real time SISL databases, which are better related to the traditional machine learning classifiers.
Keywords:	Gesture, K-means Clustering, Multi Support Vector Machine, Naïve Bayes, Sign Language Recognition, Stacked Autoencoder
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	EVALUATION OF THE СONTEMPORARY STATE OF SOCIAL NETWORK SECURITY ISSUES: PUBLICATION CONTENT ANALYSIS
Author:	YE.MAKATOV , Al.AKTAYEVA , R.NIYAZOVA , A.KONYRKHANOVA , A.BEISSEKOV 5, M.AITKENOVA , D.PLESKACHEV , M.ZHAMANKARIN
Abstract:	Among various social media platforms, the concept of all users’ openness and accessibility of information is becoming even more lifelike. Social networks afford to receive the freshest news, communicate with various interesting people, regardless of their location and residence, contribute to changing the interaction between people, and so on. This article presents the standard principle of content analysis of the publications indexed in the Scopus and WoS databases and provides the analysis of 67 high-rating publications. The result of the analysis allows for the conclusion that most social network researchers use readily available methods for classifying the threats to information security violations, which cannot be considered specifically suitable for the analysis of social networks since they do not reflect the characteristic features of research in this area. This paper proposes a different approach to the clustering of implemented threats to the information security of social networks. An analysis of the currently existing threats and vulnerabilities in the information security of social networks indicates that the achievement of the goals and objectives of information protection, as well as ensuring the maximum level of security, requires the integrated use of available methods and means of protection.
Keywords:	Social networks, Ontology, Security privacy, Security methods, Content analysis.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	CLASSIFICATION OF ENCRYPTED IMAGES USING DEEP LEARNING –RESNET50
Author:	JAWAD YOUSEF IBRAHIM ALZAMILY, SYAIBA BALQISH ARIFFIN, SAMY S. ABU NASER
Abstract:	Background: With the entry into the world of cloud computing, which has become an essential in our lives, especially after the pandemic of the era of COVID-19, and with the increase of overlapping data over the Internet and networks with an increasing and great speed, the need to protect those data and applications, especially as the usage of cloud computing, increases. Objectives: Searching for the best solutions to provide the necessary protection against data attacks via cloud computing, so the need has become more urgent to access huge storage resources and applications with ease and process them anywhere with flexibility and more security. Methods: In this paper, a large group of images has been encoded using one of the encryption algorithms, then we used the Convolutional Neural Network (CNN) algorithm, which is a widely applied deep learning technique for image recognition. There is no doubt that deep learning has many models that contribute to increasing the speed and accuracy in the appearance of the results, including the ResNet50 model, where we took the model by training many encrypted images. Through this model, it was able to classify and identify the encrypted images without decoding them. Results: It was found that the classification of encoded images using the deep learning technique of the ResNet50 model has the potential to identify the encrypted image without decoding it. The proposed model achieved accuracy (99.75%), Recall (94.12%), Precision (94.23%) and F1-score (94.70%) on the test dataset, which indicates the feasibility of this approach in classifying encoded images.
Keywords:	Deep learning, Cryptographic algorithms, Image Encryption, Encryption, ResNet50 model, Artificial Intelligence
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	MEASURES TO CURB THE CYBER MENACE RELATED TO CRYPTOCURRENCIES
Author:	KIRUTHIKA D, Dr. KESAVAMOORTHY RENGANATHAN
Abstract:	Advancements in technology have affected modern society in numerous areas, including communication, education, commerce, and so on. Cryptocurrencies in general and Bitcoin in particular are the most discussed topics of recent times. Cryptocurrencies are considered to be a subset of virtual currencies which are electronic in nature; protected by cryptography and used for peer to peer transaction payment. The acceptance given to cryptocurrencies across various industries and among various countries is steadily increasing due to the decentralised concept which operates free of central banks. In spite of the use of cryptography providing additional security, like any other business zone, cryptocurrencies are also prone to cyber-attacks. Cryptocurrencies are considered to be the criminal’s heaven. The paper identifies the central features of cryptocurrencies i.e., decentralisation, untraceability, anonymity that forms the main drawback inviting cyber criminals to this zone. The paper further research the various cyber risks and reports the incidence of several record of ransomware attacks, account takeover, phishing, hacking and other security violations of cryptocurrencies. The paper located the diverse measures taken by the Indian Government towards handling of these cyber crimes like framing new Rules under Section 70 B (6) of the Information Technology Act, 2000 in the form of Cyber Security Directions, etc. The authors suggest various cyber security measures to curb the menace and discuss the use of Artificial Intelligence with its scope in combating these identified cyber risks.
Keywords:	Cryptocurrencies, Cyber risk, Cyber security, AI, Safety mechanism.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	IDENTIFICATION OF SCHWANNOMA IN HUMAN BRAIN USING CROSS-CORRELATION-COMMON SPATIAL PATTERN ALGORITHM THROUGH IMAGE-SIGNAL BANDWIDTH ANALYSIS
Author:	Dr. UMA SHANKARI SRINIVASAN, Dr. K. SUTHA, Dr. V. PAVITHRA
Abstract:	Neuroanatomy is a pertinent dimension in neoteric times due to the various dysfunctionalities that is associated with it. The periodical health analysis of the neural connectivity is most commonly effectuated for pregnant women to continuously monitor the structural development of the foetus’ brain. However, in adults this can be comprehended by the symptoms that are evinced on a quotidian basis. The meticulous scrutinization of the neural signals forms to be the quintessential facet of Neuroscience, and thereby delivers a wholistic diagnostical cognizance of the entirety of functions involved. With the increasing competitive realm, rapid lifestyle changes and food habits that contributes to the sundry disorders, Schwannoma can be categorized as a malady that can turn fatal with neglected vigilance. The existing studies have largely pivoted on various domain-relevant algorithmic approaches to agnize the brain disorders in relevance to malignancy and benign characteristics of an observed tumor. While the previous research pivoted on unimodal approaches such as either image processing or signal analysis of detecting brain abnormalities, this paper focuses to render a novel approach of commingling the approaches of image and signal processing to effectuate a bimodal technique of corroborating the detected abnormality through a combined effort of medical imaging and respective brain signal generation. Techniques of pre-processing, filtering and the unrivalled application of Cross-correlation Common Spatial Pattern (CCCSP) algorithm aids to classify the dossier appropriately as normal and abnormal inorder to understand the underlying problem of vagus nerve detriment to their relationship with Schwannoma. This study also focusses on the Fast-Fourier Transform (FFT) and Discrete Wavelet Transform (DWT) to sequester the wave bands, and subsequently accentuate the inconsistencies observed in the specific frequency modules to further corroborate the normalcy of the signal waves. The Delta-Beta frequency bandwidths from the generated Electroencephalogram (EEG) are specifically used in this paper inorder to cognize the abnormalities. The simulative implementation for this study is functioned in MATLAB, and the efficient results to corroborate the motivation of the research is procured.
Keywords:	Cross-Correlation-Based Common Spatial Pattern Algorithm, Delta-Beta Signal wave, Electroencephalogram (EEG), Fast-Fourier Transform, Discrete Time-Direct Form Filter, Schwannoma, MATLAB.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	EMPIRICAL STUDY ON FUNGAL DISEASES IN VARIOUS PLANTS USING DIFFERENT DEEP LEARNING APPROACHES
Author:	G.SRAVANTHI, P.SAI KIRAN
Abstract:	The productivity of the agriculture decreasing day by day due to various factors. The quality of the agriculture is impacted by the pests and diseases infected on the plants. Many researches proposed traditional image processing techniques to identify the diseases and design a recommendation system but all these are expensive and inaccurate systems, which are not affordable by farmers. When a new era known as “Machine Learning” as evolved, researchers extracted necessary features from the plant images and converted them into csv files to classify the diseases in plants using these approaches. Even these approaches are time consuming, so researchers are moved to deep learning approaches in which the intermediate steps takes places automatically in between input and output like pre-processing feature extraction. In this paper, the model studied about different deep learning approaches available on the disease detection system in various plants. Among the deep learning models, the researchers who have implemented transfer learning approaches have obtained high accuracy and few have achieved good kappa cohen values also. In traditional models the system needs to assume random weights for the neurons to produce the dot vectors of every layers. These assumed values some times may give more error rate which results in back propagation. Transfer learning helps the model to get the optimal weights without assumptions of each neuron from the pre-trained model it implements. The major advantage of any pre-trained model lies in faster training of network with millions of different categories images. One of the popular dataset used by most of the researchers for this study is “ImageNet”. Using the concept of transfer using the ImageNet irrespective of any pre-trained model implemented the accuracy lies in between 92% to 96%.
Keywords:	Segmentation, Image Enhancement, Augmented Data, Annotation, Transfer Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	MACHINE LEARNING: STRATEGIES FOR INDUSTRIAL DEFECT DETECTION
Author:	SOUMIA TABIT, AZIZ SOULHI
Abstract:	Maintaining normal operations, without defects or breaks, is the main objective for industrial companies. This is because any anomaly in this sense affects the entire production chain and can disrupt the internal functioning of a factory at various levels... To achieve this goal, control is required throughout the process so that intervention can be made as quickly as possible without slowing down the cycle time or increasing the price of the product. To free themselves from these complicated control processes, industrial companies are turning to the technology of artificial intelligence technology, more specifically machine learning, which is the key to Industry 4.0, to automate the control process. Hence the objective of this article. The objective of our research is to develop an algorithmic solution for the detection of anomalies and nonconformities in production units, through an automatic classification of the data collected by the sensors (which represent the INPUTS of our model) into two categories: defects and without defects, which constitute the set of arrivals of the value of OUTPUT. Establish a model of non-conformity detection in the industrial process (which is the first step in non-conformity management) by integrating Machine Learning to inspect defects in the industrial environment, such as product quality control, predictive maintenance of production equipment, or even monitoring compliance with measures and safety rules. To perform the production. This moderated approach consists in detecting the anomaly as soon as possible through a measurement of the standard deviation between the current state of the object and the ideal state via sensors to classify the result according to the classification criteria pre-established by the experts in our prediction machine. To illustrate this model of machine learning a case study from the automotive industry is presented, through a model that detects the defect of paint in car bodywork
Keywords:	Non-Conformity; Machine Learning; Algorithm; Artificial Intelligence; Industry 4.0; Quality Control; Predictive Maintenance; Prediction Machine.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	LIGHTWEIGHT IOT IMAGE ENCRYPTION
Author:	HANEEN DWEIK, MOHAMMED ABUTAHA, RACHID SAMMOUDA
Abstract:	Nowadays, all smartphones, laptops, and other communication devices connect to the cloud, making data accessible to everyone. The Internet of Things (IoT) network is a group of various devices interconnected over the internet that exchange data between themselves and other services. IoT has a wide application range from smart applications to a variety of industrial applications. Because nodes in an IoT network have limited resources, classical cryptography methods are costly and inefficient, so lightweight block ciphers are one of the most sophisticated ways to overcome security shortcomings in this environment. The result is a low bandwidth, reduced storage space, and shortened computation times due to the compression. Specifically, this paper discusses the performance of lightweight AES algorithms for encrypting and decrypting images in smart IoT devices.
Keywords:	Internet of Things (IoT), Lightweight, Image, AES, Blind people.
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	COMPARISON ARTIFICIAL NEURAL NETWORK METHODS OF BACKPROPAGATION AND LEARNING VECTOR QUANTIZATION FOR FORECASTING STOCK PRICES
Author:	SILVIA FIFI WARDHANI, DIYURMAN GEA
Abstract:	During the COVID-19 pandemic stock trading is a hot topic of discussion and encourages new investors which positive impact on the market modal. Shares of PT. XL Axiata, Tbk. (EXCL) was sluggish despite reporting a surge profit in 2021, this prompted research on how to predict the stock price of EXCL for attract investors and encourage company to be more active in carrying out business strategies. In recent years, Artificial Neural Networks (ANN) are quite used in macroeconomics forecasting, because of their ability to detect and relate linear and non-linear functions. In this study, two ANN methods were used to predict the stock price of EXCL with backpropagation (BP) and Learning Vector Quantization (LVQ). In the prediction results, model evaluation is needed to measure the forecasting model from both methods, resulting in the confusion matrix with the accuracy, sensitivity, and specificity are provided. This research is given some value to stock action suggestions at EXCL.
Keywords:	Stock Price EXCL, Artificial Neural Networks (ANN), Backpropagation (BP), Learning Vector Quantization (LVQ), Confusion Matrix
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text

Title:	A THEMATIC REVIEW ON THE IMPLEMENTATION OF HEUTAGOGY IN UNIVERSITIES
Author:	FAIRUZZA HAIRI, SITI NURUL MAHFUZAH MOHAMAD , SAHRUDIN SAAD, TITO PINANDITA
Abstract:	Smart technology, artificial intelligence and robotics have recently become the focus of the new industrial revolution, which now influences our daily lives. The process of teaching and learning at higher education institutions needs to be updated to meet the challenges of Industry 4.0. Different types of learning spaces and pedagogies, such as heutagogy, are required. Although heutagogy has been practised for a long time, there is a deficiency in studies which review the existing literature about implementing heutagogy. In light of this fact, this article is, therefore, a systematic review of the literature on the application of heutagogical methods in universities worldwide. This study utilized publications from 2016 to 2020 from databases such as Web of Science, Scopus, ACM Library, Science Direct, Emerald Insight, Taylors & Francis Online, as well as from the alternative database Google Scholar. The search efforts resulted in a total of 23 articles that can be systematically analyzed according to the Preferred Reporting Items for the Systematic Reviews and Meta-Analysis (PRISMA). By using ATLAS. ti 8 as a tool, this review has five main themes, namely, i) ICT; ii) Blended Learning; iii) Outside Classroom Activities; iv) Distance Learning and; v) Module or Curriculum Related. The results showed that heutagogy is a suitable approach that can be applied in this era and that it is recommended that this approach be implemented during this COVID-19 season. Finally, at the end of this research, a number of recommendations for future scholars will be discussed.
Keywords:	Heutagogy, Systematic Literature Review, Online Learning, ATLAS.Ti 8, Covid-19, Thematic Analysis
Source:	Journal of Theoretical and Applied Information Technology 15^th November 2022 -- Vol. 100. No. 21-- 2022
Full Text