		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
September 2022 | Vol. 100 No.18

Title:	MACHINE LEARNING PREDICTION OF HEPATIC FIBROSIS IN HEPATITIS B EGYPTIAN PATIENTS BASED ON CLINICAL LABORATORY PARAMETERS
Author:	ESLAM TAHER SHARSHAR, HUDA AMIN MAGHAWRY, EMAN ABDELSAMEEA, NAGWA BADR
Abstract:	Liver fibrosis stage prediction in chronic hepatitis B virus (HBV) infected patients is vital. Liver biopsy is the reference style and gold standard to evaluate fibrosis stage but with many drawbacks. Therefore, using noninvasive methods are better alternatives. In this study, seven clinical laboratory parameters of 235 chronic HBV Egyptian patients with Hepatitis B virus were collected from HBV clinic at National Liver Institute that belongs to Menoufia University in Egypt. The aim of this study is to experiment multiple machine-learning methods based on clinical parameters to build efficient classification models that predict two liver related issues: the fibrosis stage and cirrhosis of liver in chronic HBV Egyptian patients. Also, attribute selection methods were applied to reduce the dimensionality and find the most relevant parameters. For fibrosis stage prediction, a classification model based on Logistic Regression achieved AUROC of 0.991 and accuracy of 93.61%. Besides, using only four parameters selected as the most relevant, AUROC of 0.971 and accuracy of 95.74% were achieved. For cirrhosis of liver prediction, a classification model based on Logistic Regression and cost sensitive with penalty of 2 achieved AUROC of 0.936 and accuracy of 91.49%. Besides, using only three parameters selected as the most relevant, AUROC of 0.92 and accuracy of 85.11% were achieved. The classification models outperformed noninvasive index-based method, FIB-4 that depends on four clinical parameters, in both fibrosis stage and liver cirrhosis prediction in chronic HBV Egyptian patients.
Keywords:	Machine-Learning; Attribute Selection; Chronic HBV; Fibrosis; Cirrhosis; FIB-4.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	DEVELOPMENT OF EXPERT UNSTRUCTURED DECISION-MAKING SUPPORT SYSTEM
Author:	TATIANA KRAVCHENKO, TIMOFEY SHEVGUNOV
Abstract:	With the advent of data warehouses and OLAP-technology, and subsequently many other systems that output information for decision-making, all such systems began to be referred to as decision support system (DSS). Thus, the original purpose of DSS has been forgotten: the selection of an effective solution from the set of possible alternatives for poorly structured or unstructured management decision-making tasks based on mathematical methods and information technology. Therefore, it would be more correct to call systems of this class Unstructured decision-making support systems (UDMSS), and other support systems, DSS. Currently, new terms are appearing, the purpose of which is to combine DSS into certain classes; for example, System DSS, Business DSS and Intelligent DSS. Research objective is the following: to develop a new UDMSS that combines elements of expert systems, data warehouses, group DMSS, author's UDMSS, and can be called Expert UDMSS (EUDMSS). The following main results are presented in the article: features of an expert unstructured decision making support system; system architecture; decision-making method selection module (expert system shell); decision-making module, including 50 mathematical methods (decision-making methods using the majority principle, Pareto and Bayes principle, in partial and full uncertainty, in dynamic formulation, vector optimization, methods combining various principles of matching evaluations of alternatives and other methods); system functionality.
Keywords:	Decision Support System, Decision Table, System Knowledge Base, Methods Of Decision Theory, Unstructured Decision Making Support Systems.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	A NOVEL METHOD TO AUTO CONFIGURE CONVOLUTION NEURAL NETWORK MODEL USING SOFT COMPUTING TECHNIQUE TO RECOGNIZE TELUGU HAND-WRITTEN CHARACTER FOR BETTER ACCURACY
Author:	B.MEENA, PROF.K.VENKATA RAO, PROF.SURESH CHITTINENI
Abstract:	The paper presents the performance optimization using Genetic Algorithm with Convolutional Neural Networks (CNN) architecture to recognize hand written digits written in Telugu Language. CNN is tested with multiple configurations for various numbers of convolutional layers, filter size in each convolution layer, number of convolution filters in each layer, and pool size (for down sampling). the images in order to get optimal performance. Researchers have been using the trial-and-error approach of picking configurations for a CNN Model. This may not always guarantee the optimal performance and it needs, the user to monitor the performance trend on a regular basis with the improvement in prediction accuracy for changes in number of layers, filter size and number of filters. The Genetic Algorithm is used in this research to change the configuration of CNN to achieve the best results (accuracy of image recognition). Various architectures have been proposed by researchers for producing better results in Image recognition and classification areas. Our paper has proposed a method by changing CNN configurations with Genetic Algorithm and evaluated the overall test accuracy to 99% for hand written telugu characters.
Keywords:	Genetic Algorithm , Convolution Neural Network , Telugu Character Recognition , Soft Computing
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	X-RAY IMAGE PROCESSING OF BONE CAVITY FILLED WITH BIOMATERIALS BASED ON PHOSPHATE CALCIUM
Author:	SALMA HAKIM1, , ABDELAZIZ ESSAKHI, , MANAL EZZAHMOULY, ABDELKADER BOULEZHAR, ABDELMAJID ELMOUTAOUAKKIL, ZINEB HATIM
Abstract:	Certain traumatic situations, congenital diseases or cancers can cause bone loss and require bone grafts or implants. Bone substitutes prepared from calcium phosphates such as hydroxyapatite (Ca10(PO4)6(OH)2) or Beta-tricalcium phosphate (β-Ca3(PO4)2) are used in orthopedic and dental surgery and they present good biocompatibility and bioactivity. These biomaterials in different forms: paste, granule or screw and their biological integration is influenced by structure and microstructure as well as the architecture, porosity, location and bone / implant connectivity. The aim of this study is segmenting and analyzing nano- biocomposite granules with low crystalline structure from bone. The simple thresholding is not sufficient, for that we have developed a novel method that combine different segmentation methods and then determine the volume of the defect, segmented the granules in the defect, calculate their size distribution.
Keywords:	Image Processing, X-Ray Tomography, Segmentation, Bio-Materials, Calcium Phosphate Granules, Bone Filling
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	CNN PERFORMANCE IMPROVEMENT USING WAVELET PACKET TRANSFORM FOR SCA PREDICTION
Author:	YOSAFAT VINCENT SARAGIH, SANI MUHAMAD ISA
Abstract:	Sudden cardiac arrest (SCA) is a medical emergency that poses the risk of death to the patient. For prevention, a robust system is intensively on ongoing research to predict whether a person may predict sudden cardiac arrest in the future, long before the incident. The current system development method is learning from the patient's ECG recordings. A combination method between the Wavelet Packet Transform and the Convolutional Neural Network classification model was proposed to obtain hidden patterns from the patient's ECG recordings. The SCA dataset was obtained from the MIT-BIH SCA Holter DB with 2 ECG machines and the Normal Dataset from the MIT-BIH Normal Sinus Rhyme. With cross-validation evaluation with k-fold=10, by comparing one segment 1 minute from 30 minutes before onset, Convolutional Neural Network (CNN) performed with an accuracy of 95.89%, precision of 96.75%, recall 95.83%, and F1-Score 95.75%, with two-level Meyer Wavelet Packet Transformation.
Keywords:	Sudden Cardiac Arrest, Electrocardiogram, Wavelet Packet Transform, Convolutional Neural Network
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	DESIGN AND IMPLEMENTATION OF A COLOR QR CODE GENERATOR AND READER FOR SHOPPING MALL NAVIGATION
Author:	BAKRI BADAWI, TEH NORANIS MOHD ARIS, NORAINI CHE PA
Abstract:	In this paper, we proposed an indoor navigation system for navigation inside shopping malls or hypermarkets. the indoor navigation system provides an easy way to navigate to a product or store. The system consists of two parts. The first part is the encoder or the QR code generator which will be used by the shopping mall manager to generate QR codes. The generated QR code needs to be installed in the mall. The second part is the decoder which needs a mobile phone. The decoder will take the required destination from the shopper and then using the information stored inside the QR code will build the virtual map and provide the navigation instruction. The experiment was done by testing the encoder to generate QR codes for two different virtual buildings. While the decoder tested to get the location for multiple destinations.
Keywords:	Indoor Navigation, Virtual Map, Color QR Code.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	TOWARDS CONCEPTUAL MODEL OF SOCIAL MEDIA USE FOR FLASH FLOOD PREPAREDNESS IN KLANG VALLEY
Author:	NUR NAZIRA MUSTAKENG, NURAZEAN MAAROP, NUR HASNIZA ILLIAS, GANTHAN NARAYANA SAMY, PRITHEEGA MAGALINGAM, NORSHALIZA KAMARUDDIN
Abstract:	Flash flood seems to be one of the natural disasters prompting considerable worry throughout the globe. Malaysia, which is situated in Southeast Asia, is not immune to flash floods; in fact, it has lately suffered a rise in the frequency of flood incidents, each of which has been more severe than the previous. This flash flooding event can cause disruptions towards the economic, environmental, property and the livelihood of the people in Klang Valley, Malaysia. Nowadays, the importance of social media such as Facebook, Twitter, and Instagram as a platform for connecting individuals from all over the world is gaining prominence. Therefore, this research aims to develop a conceptual model on the factors influencing social media use towards flood disaster preparedness in the case of Klang Valley. This research has applied quantitative-deductive approach and employed PLS-SEM analysis involving a total of 98 respondents, statistically seems to be sufficient for analyzing the model. The initial factors have been reviewed and identified according to the empirical results of related studies and these are Knowledge Self-Efficacy, Subjective Norms, Attitude, Trust, Community Participation and Openness. Overall, the model can explain 44.9% of the variance in the intention to prepare using social media for flood preparedness. The evaluation of the proposed model yielded that three of the six factors which are Knowledge Self-Efficacy, Attitude, and Trust, have significant positive influence on social media use for flash flood disaster preparation in the context of Klang Valley, Malaysia.
Keywords:	Social Media, Flood Preparedness, Knowledge Self-Efficacy, Attitude, Trust
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	MULTICRITERIA DECISION-MAKING MODEL FOR LEGACY SYSTEM MODERNISATION: A SYSTEMATIC LITERATURE REVIEW
Author:	AWS A. MAGABLEH, Z. M. KASIRUN, ADI ASLAH
Abstract:	Rapid development of information technology and communication (ICT) has increased the use of information systems in companies. At the same time, many organizations are still using old systems to support their business (legacy systems). Even though these systems cause technical problems, but they are still used to support service delivery to the customer. These systems are also essential to organizations as they have been operated for many years and possess high business value Legacy system modernization (LSM) decision is very challenging and problematic issues in many organisations. In this Systematic Literature Review (SLR) paper, we describe the problem from a theoretical perspective, followed by models and approaches for its effectiveness. We present trends in decision-models and approaches and the resulting implications on practicality strategies. We then review the multicriteria decision-making (MCDM) application in LSM. Additionally, we present all relevant works classified by the year of publication, MCDM techniques, journals, and conferences in which they appeared. We discuss significant criteria identified to support researchers and industry practitioners by adopting the MCDM techniques to their LSM and providing insights into the state-of-the-art approaches or models, respectively. The study successfully managed to answer the three presented research questions.
Keywords:	SLR, Legacy System Modernisation, MCDM, Approaches, Models, Software Engineering.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	THE DEVELOPMENT OF AUTOMATED ESSAY SCORING BASED ON CLASSIFICATION MODELS
Author:	MARDHANI RIASETIAWAN, YUNITA SARI, GUNTUR BUDI HERWANTO, BAMBANG NURCAHYO PRASTOWO, ISNA ALFI BUSTHONI, ROCHANA4, RIAN ADAM RAJAGEDE, INDRA HIDAYATULLAH, MARVINA PRAMULARSIH, WILIA SATRIA
Abstract:	In previous research, machine learning methods have been carried out in implementing automatic essay assessment. Automated essay scoring (AES) is used in evaluating and assessing student essays written based on the questions given. However, there are difficulties in carrying out an automatic assessment carried out by the system, the difficulty occurs because of typing errors, use of regional languages, and incorrect punctuation. These errors make the assessment less consistent and accurate. One of the problems in essay answers is the proofing process which is more complicated than multiple-choice questions. The Automated Essay Scoring established to manage the process of essay scoring assessment and evaluation using computation approach which is machine learning with classification capabilities. The problem occurs when we have unbalanced dataset and a few labeled data in especially for the model training process. The evaluation conducted with comparing the classification model with several combinations. This study proposes to analyze and comprehensive evaluation of the Word Embedding with GRU and RNN, TFIDF with AdaBoost, back of word with AdaBoost, and FastText with MLP which are expected to solve these two problems. The optimal model and architecture for sequential feature-based scoring (RNN) with a fairly stable performance
Keywords:	Automated Essay Scoring, Machine Learning, Classification Model, Evaluation.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	ELLIOTT WAVE PRINCIPLE WITH RECURRENT NEURAL NETWORK FOR STOCK MARKET PREDICTION
Author:	KV MANJUNATH, MALEPATI CHANDRA SEKHAR
Abstract:	Nowadays, academics and finance industries are being discussed highly in the domain of stock market trading due to which the improvement in economic globalization. Connections of stock markets are seen among various countries that develop risk factors associated with the market. Everyday rise and fall in the stock market make it a challenging area yet an important one. The increasing dynamic features and complexity of stock markets show difficulty in the industry of finance. The existing methods of inflexible trading were developed by researchers who had utilized larger features of the stock market and failed to establish effective outcomes during different scenarios of markets. Further, the existing data mining methods were inefficient and incomplete in predicting the stock market. To overcome such an issue, a stock market recommendation method based on the Elliott Wave Principle (EWP) with Recurrent Neural Network (RNN) was proposed. The proposed EWP-RNN identifies the impulse waves that sets the pattern and opposes the larger trend using EWP. The RNN assists the traders regarding the future stock trends to enhance the investment profit of a lesser period of time. The proposed EWP-RNN method utilizes the Fibonacci Series (FS) with EWP and RNN to analyze the future trends in the finance market. The proposed method achieved accuracy of 98.67% for the stock market prediction, whereas the existing BPNN showed accuracy of 92.55%.
Keywords:	Elliott Wave Theory, Data Mining method, Recurrent Neural Network, Fibonacci Series, Stock Market.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	ANALYSIS OF FACTORS AFFECTING INTEREST OF THE MILLENNIAL GENERATION IN ROBOT TRADING FOREX
Author:	YOHANNES KURNIAWAN, TANJUNG KUSUMONINGTYAS, NORIZAN ANWAR
Abstract:	Today, transactions can be done automatically so that sellers and buyers feel more convenient and don't waste a lot of time. Technological advances enable companies to keep up with the times. Robots are useful for the current 4.0 era, especially for traders so that they don't have to watch the moves every time. This study aims to analyze the impact of knowledge, ease of use, investment risk, investment return, and trust on millennial interest in forex trading robots. The data collected in this study was disseminated via Google form and snowballed through social media and group chats. The researchers used partial least-squares structural equation models to analyze data and results obtained by variables such as knowledge, investment risk, and trust, which influenced millennial interest in forex trading robots. Meanwhile, ease of use and return on investment do not affect millennials' interest in forex trading robots. This research shows that traders are influenced by their thinking and adapt to their wishes when making the decision to invest in Forex using robots.
Keywords:	Robot Forex, Ease of Use, Trust, Millennial Generation, Trading.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	REAL TIME INFORMATION SYSTEM OF RAW WATER SALT LEVELS PDAM TIRTA KHATULISTIWA PONTIANAK BASED ON LORA GATEWAY TECHNOLOGY
Author:	FITRI IMANSYAH, JANNUS MARPAUNG, REDI RATIANDI YACOUB, LEONARDUS SANDY ADE PUTRA, EKA KUSUMAWARDHANI, AYONG HIENDRO, VINCENTIUS ABDI GUNAWAN
Abstract:	Quality clean water is essential for humans to meet their daily needs. In Pontianak City, one way to obtain clean water is by subscribing to the Perusahaan Daerah Air Minum (PDAM). PDAM obtains raw water in large volumes during the rainy and dry seasons from the Kapuas River. Water taken from rivers without going through treatment is commonly referred to as raw water. Previously raw water was still in poor condition, such as cloudy, high salt content, and smelled. It raises concerns in maintaining water quality which will later be distributed to customers after going through the sterilization process by the PDAM. The quality of raw water from the Pontianak Kapuas River is very vulnerable to saltwater intrusion from the high seas, especially in the dry season. Based on information from the media which contained an expert statement from the University of Tanjungpura Pontianak, seawater intrusion into the Kapuas River could reach 2000 ppm (salt content in water), which means it is the same as saltwater and goes as far as 50 km. Information about seawater intrusion into the Kapuas River that is conveyed occurs periodically or only when it occurs during the dry season. A breakthrough (innovation) is needed so that information about the water quality of the Kapuas River can be carried out continuously and in real-time and can be accessed by related parties and monitored remotely. In addition, variations in early detection of water quality in the Kapuas River can be an alternative in finding alternative locations for raw water sources for PDAMs. They become the right solution in distributing clean water to customers. The results of this study are an information system on the condition of raw water in the Kapuas River, which PDAM Tirta Khatuliswa Pontianak can monitor in real-time. This technology utilizes LoRa as data communication between nodes to the gateway. The monitoring process is carried out using a website that is connected by a microcontroller through the IoT process.
Keywords:	Raw Water Salt Level, Monitoring System, LoRa Gateway, Internet of Things, PDAM Tirta Khatulistiwa
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	THE SECURITY CONCERNS AND SOLUTIONS FOR CLOUD-BASED IOT SYSTEM
Author:	MAHENDRA DEORE, DEEPAK MANE, GOPAL UPADHYE, NILOFER KITTAD
Abstract:	From recent times our day to day life has significantly started to depend on the technological advancements of the Internet of Things. IoT has made it possible to converge the abilities of almost all types of devices ranging from small hand held devices to massive machines. Any system based on IoT infrastructure needs to deal with the issues of collection, storage and analysis of humongous data. Using external cloud servers is more convenient than the other alternative of being responsible for onsite storage but the issue of security and privacy need to be addressed in this case. This paper primarily focuses on the analysis of possible security threats for cloud based IoT systems. The authors have classified the security challenges for such a system and have presented a detailed survey of the techniques of cryptographic solutions to address the identified challenges. The authors have also suggested the security techniques and tools that can be used at each layer of the cloud service provider.
Keywords:	Internet of Things, Cloud, Cryptography, Encryption, Security and Privacy.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	MONITORING LAND USE AND LAND COVER CHANGE USING ENSEMBLE MACHINE LEARNING CLASSIFIERS
Author:	SUBHRA SWETANISHA, AMIYA RANJAN PANDA, DAYAL KUMAR BEHERA, SHREELA DASH
Abstract:	Land Use and Land Cover (LULC) classification is a better tool for change detection and other remote sensing applications. Changes in LULC have become a vital aspect of conventional strategies for land cover monitoring. The aim of this work is to monitor the changes using classified images of the machine learning models. A change detection exercise was conducted in the research region, namely Kendrapara District, Odisha. Landsat7/8 imagery was used in 1999 and 2020 to track potential changes, particularly in agricultural land and urban or built-up land, to detect urban growth. This work uses three machine learning models to determine the best classifier from SVM, XGBoost and Ensemble Model of SVM and XGBoost. The ensemble classifier outperforms the other two machine learning models. Then the best model is used to analyze the change. This change detection may enable the government to implement legal measures & norms and develop the city.
Keywords:	Land Use and Land Cover, Change Detection, SVM, XGBoost, East Odisha
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	IMPLEMENTING A SECURED OFFLINE BLOCKCHAIN-BASED ELECTRONIC VOTING SYSTEM
Author:	APEH JONATHAN APEH, CHARLES K. AYO, AYODELE ADEBIYI
Abstract:	Internet penetration is a critical factor in determining the adoption of an internet-based electronic voting system. In Nigeria for instance, the electoral bill which is to provide the legal backing for the transmission of voting data from polling units across the federation had witnessed huge setbacks hinged on lack of internet infrastructure in Nigeria’s remote places. Arguments have been made for and against the possibility of disenfrenching citizens if electronic transmission was allowed in the electoral laws. In this article, we propose an electronic voting system model that allows the secured continuation of voting exercise in offline mode and the transmission of cast votes upon the restoration of internet connectivity using the infrastructures permissible with the blockchain technology. The model is adaptable in any national election, specifically, Nigeria’s national elections.
Keywords:	Blockchain, Election, Electronic Voting System, Internet penetration, Suffrage
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	UTILIZATION DOCKER SWARMS IN A CONTAINER TECHNOLOGY SYSTEM TO PROBLEM SOLVING LOAD BALANCE
Author:	NURUL KHAIRINA, SUSILAWATI, RAHMAD SYAH
Abstract:	Container technology is a type of virtualization technology that is used at the operating system level. This is more in line with the need for long-term data storage for day-to-day operations. Data mining is becoming increasingly important for everyone in order to gather relevant information. Large-scale data processing slows down several operations, including data collection, processing, organization, modeling, analysis, and storage. The most significant difference for most users is the use of a high-quality data-collection system and its distribution, as well as the use of a complex data-analysis system. Docker Swarm is used for the development of various types of distributed systems, which can aid in the resolution of all issues as well as the optimization of results. Machine Learning was used to perform horizontal.
Keywords:	Optimasi, Docker Swarm, Machine Learning, Raspberry pi, Support Vector Regression.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	EFFECTIVE COST ESTIMATION USING AGILE PROCESS
Author:	UDIT KUMAR NATH, ALOK KUMAR JAGADEV, PRASANT KUMAR PATTNAIK, SANTOSH KUMAR SWAIN
Abstract:	Cost estimation of any product or project is the key factors to determine the overall budget and successful completion of project deliverables. There are many traditional methods available to estimate the efforts. But understanding the project features or requirements and apply correct methods in effective way is the key for any successful project. The above modern way of cost estimation techniques can reduce the overall development cost and improve the quality deliverables. This research paper elaborate more on available cost models, analyzes, and compare their results and proposed the effective models.
Keywords:	Cost Estimation, Budget, Traditional Methods, Cost Estimation
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	COMPARATIVE ANALYSIS ON THE RELIABILITY ATTRIBUTES OF FINITE FAILURE NHPP SOFTWARE RELIABILITY MODEL WITH EXPONENTIAL DISTRIBUTION CHARACTERISTICS
Author:	SEUNG KYU PARK
Abstract:	In this study, the reliability attributes of the finite failure NHPP software reliability model with exponential distribution (Exponential Basic, Inverse Exponential, Lindley, Rayleigh) characteristics were comparatively analyzed, and based on this, the optimal reliability model was also presented. To analyze the software failure phenomenon, the failure time data collected during system operation was used, and the parameter estimation was solved by applying the maximum likelihood estimation method (MLE). As a result, first, in the analysis of mean square error (MSE), the Lindley model was effective because it had the smallest error value. Second, in the analysis of the true value estimation power of the mean value function, all of the proposed models showed an overestimated pattern, but it was found that the Lindley model was excellent because the width of the error was the smallest. Third, in the evaluation of the strength function, the Lindley model and the Rayleigh model were effective in terms of fit as the failure rate increased and then decreased significantly as the failure time passed. Fourth, as a result of evaluating the reliability by applying the mission time, the Rayleigh model appeared to be the highest and most stable, but the Exponential Basic model showed the largest decreasing trend and was found to be inefficient. In conclusion, it was found that the Lindley model is an efficient model with the best performance. Through this study, the reliability attributes of the distribution with the characteristic of the exponential form, which has no existing research case, were newly identified, and through this, basic design data that software developers could use in the initial stage could be presented.
Keywords:	Exponential Basic, Inverse Exponential, Lindley, NHPP, Rayleigh, Reliability Performance
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	SIMILARITY-BASED GENE DUPLICATION PREDICTION IN PROTEIN-PROTEIN INTERACTION USING DEEP ARTIFICIAL ECOSYSTEM NETWORK
Author:	SRINATH DOSS, JOTHI PARANTHAMAN, VINSTON RAJA R, JOHN ANAND G
Abstract:	In the living organism, almost entire cell functions are performed by protein-protein interactions. As experimental and computing technology advances, yet more Protein-Protein Interaction (PPI) data becomes processed, and PPI networks become denser. The traditional methods utilize the network structure to examine the protein structure. Still, it consumes more time and cost and creates computing complexity when the system has gene duplications and a complementary interface. This research uses gene expression patterns to introduce a deep artificial ecosystem for gene duplication counting and cancer cell prediction. The main objective of this research is to predict the MYC proteins influence level, which is in charge of controlling cell growth and death in gene expression of lung cancer. Small body parts are responsible for these protein interactions, which are crucial for understanding life's activities. To achieve the research objective, a similarity-based clustering approach is employed for gene duplication counting, and Artificial Ecosystem Optimizer based Minimal Gated Recurrent Unit network (AEOMGRU) network-based approach is introduced to predict the cancer gene patterns. The proposed models' efficiency is compared to recently develop bio-inspired optimizer deep neural network techniques such as GAANN, PSOANN, and classic GRU. The efficiency of the proposed classifier shows the highest concerning the performance metrics weight average accuracy ratio of 99.08%, average precision rate of 99.2%, least root mean square error of 0.2%, and least mean absolute error of 0.5%.
Keywords:	Protein-Protein interaction, MYC Protein structure, Clustering, Gene duplication counting, Lung cancer, Minimal GRU network
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	IMPROVE MANUFACTURING QUALITY CONTROL WITH ARTIFITIAL INTELLIGENCE
Author:	SOUMIA TABIT , AZIZ SOULHI
Abstract:	Stagnation has no place in the modern industrial world, especially when it comes to quality. To remain successful in a competitive environment, any company must improve on all levels, including quality, which is a key index to measure its performance. The sources of waste, failure and non-quality are the real obstacles to production and its quality, so it is necessary to identify and remedy them. Improving production quality (quality approach) requires a particular attention to processes and operational organization, in particular by redefining technical support (thanks to new technologies) and by implementing adapted quality tools. The control at the end of the production line is essential to ensure the manufacturing quality of each product. Quality control can be fully automated but human verification is also very often undertaken by qualified operators. Rising production and raw material costs are creating a growing need for automated quality control throughout the production chain. It is an essential tool to reduce manufacturing errors and therefore waste at the end of the chain. The research work presented in this article aims to establish a model allowing the company to enter the industry 4.0 (or industry of the future) through the automation of quality control to improve their reliability by freeing themselves from human errors related to the repetitive nature of these tasks. to measure the quality index of production within the industrial chains. Indeed, the conformity of products cannot yet be guaranteed directly without measurement. This last one (conformity measurement) allows to locate and follow the evolution of a parameter in time, to analyze it on a given period, to correlate it with other related values and to act to improve it in order to control and adjust the production process in real time; This decision support model is based on the fuzzy logic theory, it consists in modeling the relevant decision criteria which influence the quality of the production, which are: the rate of conformity, the rate of reworked product and the rate of non-conforming product but accepted under exemption. Thus, determine the most predominant factor. For the validation of this proposed model, an experimental study was conducted to control the production quality in an automotive parts manufacturing line. The proposed model meets the desired objective and is therefore retained as a model to ensure the quality of a manufactured product.
Keywords:	Quality Control, Artificial Intelligence, Product Line, Industry 4.0 ,
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	ELECTRONIC GOVERNMENT RESEARCH IN JORDAN A BIRDS EYE VIEW USING META ANALYSIS
Author:	ALAA ALZYADAT , AYMAN ALARABIAT
Abstract:	This research presents a quantitative analysis of 121 published papers specific to Jordan's e-government researches (EGR) throughout the years 2009- January 2021 through a meta-analysis systematic process. The focus EGR specific to Jordan is due to the fact that the e-government studies conducted in Jordan context are among the highest publications in developing countries. Study results reveal that the majority of EGR in Jordan have adopted a quantitative approach rather than qualitative or multi-method evaluation approaches and none of EGR adopted a design research approach or action research approach involved researcher(s) and practitioner(s). While a fair number of EGR take a theory-based approach, the majority of them rely on common and traditional theories (e.g., TAM and UTAUT), neglecting many other potential theories to use e.g., expectation confirmation and technology-organization-environment theories. EGR in Jordan has overwhelmingly focused on specific e-government topics (e.g., citizens’ acceptance and adoption besides evaluating e-government websites or portals) and thus more research orientation should go further toward other recent topics e.g., continuous-use intention and /or post-adoption, citizens resistance, privacy and security issues as well as to capture new trends and priorities in the e-government domain such as anticipatory e-government, smart government, participatory governance, smart city, and data-centric governance that all are critically required to advance EGR in Jordan. The study findings provide opportunities for future areas of research, which contribute to more diversity of EGR in Jordan. The study helps to develop reliable knowledge and leads to ideas for new studies that are anticipated to be of significant value for both academics and practitioners. While the findings might be restricted to Jordan's context, nevertheless, it would encourage other e-government scholars to conduct similar studies for their own countries.
Keywords:	E-Government, Digital Government, Meta-Analysis, Literature Review, Jordan
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	ADOPTION OF TECHNOLOGICAL SOLUTION ON FINTECHS USING TRAINING ENGINEERING: CASE OF HEALTH SECTOR
Author:	HANANE NIYA, AMINA EL BOUSAADANI, MOHAMED RADID
Abstract:	Artificial intelligence and blockchain are game changers for healthcare, but they come with challenges that companies and governments need to design innovative approaches to address. Digitization of all processes that once took days is now just a click away. In recent years, with the rapid development of information and communication technologies (ICT), the integration of financial information systems with new information technologies has led to changes in business operations. Technology adoption is not new to the financial industry, but digital innovation has brought major improvements in system connectivity, customer experience, and newly created and usable data. Financial and technological innovations are multiplying: crowd funding services, mutual loan sites, online banking, mobile wallets, e-commerce. All this is only the beginning of the path that Moroccan banks and financial companies must travel to obtain the main advantages and opportunities that initiate the development of the fintech segment. However, the rapid development of new financial technologies corresponds to the rapid growth of the risks that accompany them. Therefore, an important step in the development of fintech is the identification of the risks caused by their appearance. Recently, digital finance encompasses a multitude of new financial products, financial activities, finance-related software and new forms of communication and interaction with customers, provided by innovative financial companies and financial service providers. Digital innovation in financial services is changing the way financial resources can be accessed, distributed and managed. This study analyzes the approaches of the emerging field of FinTech, InsurTech and Blockchain by specifying the concrete example of the M-wallet technology, applying it in the health sector, knowing that its solution will mainly be based on training engineering.
Keywords:	Fintech , Digital, Information technology, M-wallet, Engineering, Health sector.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	MODELS AND ALGORITHMS FOR OPTIMIZING THE RESERVE OF EQUIPMENT TO ENSURE THE CYBERSECURITY OF THE INFORMATION EDUCATIONAL ENVIRONMENT OF THE UNIVERSITY
Author:	AKHMETOV B.S., ABUOVA A.K., IZBASOVA N.B., ZHILKISHBAYEV A.A., GERASYMCHUK N, MATOVKA T., RIZAK V.
Abstract:	The article proposes to apply a system of sufficiency indicators in the process of solving the optimization problem of assessing the effectiveness of choosing the composition of the backup equipment (CBE) for the information and educational environment of the university (IEEU), including information security systems (ISS). Also, a model, algorithms and corresponding software (SW) have been developed for solving the optimization problem of choosing CBE for IEEU. The proposed solutions will help to ensure the smooth operation of the IEEU. This is true both in terms of technological failures and in terms of destructive interference in the work of IEEU by hackers. The proposed solutions help to reduce the cost of creating a CBE for IEEU by 14–18%. For the practical implementation of the developed algorithms, a neural network analyzer (NNA) was developed and tested as part of a decision support system (DSS) for the selection of CBE for IEEU.
Keywords:	Information And Educational System Of The University, Information Security System, Equipment Reserve, Algorithm, Optimization
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	AN IMPROVED APPROACH FOR SCHEDULING IN CLOUD USING GA AND PSO
Author:	SHYAM SUNDER PABBOJU, DR. T. ADILAKSHMI
Abstract:	In order to improve the efficiency of cloud com- puting task scheduling, the Improved Genetic Algorithm (IGA) and the Improved Particle Swarm Optimization (PSO) are integrated into the IGA-IPSO algorithm for cloud computing task scheduling. The fitness function is constructed by integrating the three objectives of task completion time, task execution cost and virtual machine load balancing to find the optimal solution of task scheduling. The particle swarm algorithm is improved and the dynamic inertia weight strategy is used to improve the adaptive search of the algorithm. In the early stage of task scheduling, the IGA algorithm is used to reduce the solution space, and the Improved PSO is used in the later stage of task scheduling to quickly converge to the optimal solution. Simulation experiments show that compared with the other algorithms, this algorithm has faster convergence speed and stronger optimization ability. In cloud computing task scheduling, it can not only reduce task completion time and execution cost, but also optimize virtual machines load.
Keywords:	Cloud, Scheduling, Genetic Algorithm, PSO, Completion Time, Makespan.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	SOFTWARE EFFORT ESTIMATION USING HIERARCHICAL ATTENTION NEURAL NETWORK
Author:	HAITHEM KASSEM, KHALED MAHAR, AMANI SAAD
Abstract:	In every software project, a software effort estimation process is not only vital but also extremely critical. Project success or failure depends massively on, the concise knowledge of effort and schedule estimates. The development of agile techniques in the field of software development has presented researchers and practitioners with many opportunities and challenges. An estimated effort for agile software development is one of the main challenges. Although traditional estimates of effort are used to estimate effort for agile software projects, most of them lead to inaccurate estimates. This paper focuses on the development of the agile effort estimation model. A machine learning classifier that uses information contained within an issue report is proposed to classify the difficulty or the weight of a given task according to a range of story point scales. The model has two levels of attention mechanisms implemented at the word and sentence levels, allowing it to pay distinguished attention to more and less relevant semantic features when constructing the document representation. The proposed model has achieved 87% classification accuracy. An empirical evaluation demonstrates that our approach has a greater or at least equivalent F score, Precision, and Recall when compared to classical classifiers.
Keywords:	Software Effort Estimation, Story Points, Deep Learning, GloVe, Hierarchical Attention Networks, Agile
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	FUZZY LOGIC-BASED INTELLIGENT IRRIGATION SYSTEM WITH MOBILE APPLICATION
Author:	ANIS S AZRY, MD N DERAHMAN, ZARINA MOHAMAD, AMIR R A RAHIMAN, BASHIR A MUZAKKARI, MOHAMAD A MOHAMED
Abstract:	Current irrigation scheduling is inefficient and inaccurate as it still relies heavily on human labour which can lead to over- or under-irrigation, affecting crop quality and workers productivity. This study proposes an implementation of an Internet-of-Things (IoT)-based irrigation system with fuzzy logic to improve the efficiency of the irrigation process. That includes the development of a mobile application called Chill-I, which acts as a remote reporter for the agricultural contractor. In addition, this system was developed specifically for the bird's eye chilli crop, which is grown on a large scale. With three inputs, soil moisture, humidity and temperature collected by the sensors, the system uses fuzzy logic processing capability to generate the output of water pumping at different rate. The results showed that fuzzy logic-based system increases the efficiency of automatic irrigation, rather than setting a fixed water pumping rate for the plant or only the ON/OFF option. Moreover, the mobile application allows remote monitoring of plants reducing unnecessary resources and improve intervention efficiency when needed.
Keywords:	Automated irrigation system, Fuzzy Logic, IoT, mobile application, Raspberry Pi.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	COMPARISON OF ARTIFICIAL NEURAL NETWORK CLASSIFICATION METHODS FOR DISEASES THAT ARE DOMINATELY SUFFERED BY COASTAL COMMUNITIES
Author:	T.H.F HARUMY, FUZY YUZTIKA MANIK, ALTAHA
Abstract:	The problem that often occurs in Neural Networks is how to determine the right model, see effectiveness, accuracy, based on parameters, and datasets. Furthermore, various training and testing are needed to determine the best model. In-depth Artificial Neural Network Analysis is required to be analysed and compared with various other classical methods. This study tries to offer the best analytical method, namely Artificial Neural Networks that can be used, especially in the data category. Solution The analytical approach used is to add additional layers to the model until the accuracy is >= 90%. The subject of this research is the health problem of the coastal community, namely the classification of the dominant disease that most suffers from the coastal community. The purpose of this study is to classify using the Protis Neural Network Method approach and compare it with other methods to classify the dominant disease suffered, then measure the level of accuracy of each method and find the best method to classify the dominant disease suffered by coastal communities. The parameters used are region, profession, education, environment, access to health, weather, and dominant disease. The research locations include the regencies of Belawan, Serdang Bedagai, and Central Tapanuli in the Province of North Sumatra, Indonesia. The data used is 100 data. The results showed that the Protis Method approach is known to be able to classify and predict well that the dominant disease suffered by coastal communities is diarrheal disease. From the several methods tested, it is known that the Neural Network Protis is the best method in classifying the dominant disease suffered by the community with an AUC value of 0.9967, a CA value of 0.9504, an F1 value of 0.9505, a Precision value of 0.9523 and a Recall value of 0.9504.
Keywords:	Neural Network, Coastal, Disease, Artificial Intelligence
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	DNA CRYPTOGRAPHIC APPROACHES: STATE OF ART, OPPORTUNITIES, AND CUTTING EDGE PERSPECTIVES
Author:	MWAFFAQ ABU ALHIJA, NIDAL TURAB, ALA ABUTHAWABEH, HAMZA ABUOWIDA, JAMAL AL NABULSI
Abstract:	DNA cryptography approaches are attracting considerable interest widespread attention due to its unbreakable algorithms. They have enriched designing and implementation of more sophisticated and withstands to differential attack crypto algorithms. These DNA approaches have been influential in the field because of several properties such as higher speed computing, reduced amount of storage, and reduced amount of power consumption. DNA cryptography involves popular cryptographic techniques and the characteristics of DNA. The main objective of study is to provide a state of art of DNA cryptographic techniques, algorithms, and approaches recently proposed in the literature, it seeks to categorize which approaches fulfil most of the evaluation parameters, and which is a lightweight cryptography where few prior review studies investigated the related literature from this perspective. In this study, a preliminary explorative analysis was performed. Accordingly, prior work on DNA cryptographic approaches were investigated in timeframe from 2018 to 2022; using a keyword such as “DNA LWC”, “DNA Encryption” DNA cryptography; DNA-based Cryptographic system; Lightweight Cryptography (LWC); DNA computing; steganography among different scientific databases. The study of the literature undertaken indicates that most articles on DNA cryptography techniques lacks providing complete security analysis and few ones were constructed on mathematical basis. The researchers proven the presented system model and examined the approaches mainly using computer simulations. However, no real DNA implementation of the examined techniques were revealed. This study will support researchers in the assessment of current state of research on DNA cryptographic approaches and providing a reference for research trends.
Keywords:	DNA Cryptography, DNA-Based Cryptographic System, Lightweight Cryptography (LWC), DNA Computing, Steganography
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	AN IMPROVED POWER SUPPLY BASED ON A NEW MAGNETIC FLUX LEAKAGE TRANSFORMER FOR MICROWAVE OVENS
Author:	RAJAA OUMGHAR, MOHAMED CHRAYGANE, MOUHCINE LAHAME, HAMID OUTZGUINRIMT
Abstract:	This work presents a new contribution to improve the stable power supply systems, which are intended to supply magnetrons in microwave ovens. The conventional system is based on a single-phase power supply that can feed one magnetron at a time. The new system proposes a three-phase magnetic flux leakage transformer, which can supply simultaneously three magnetrons per phase. Accordingly, this work is based on a different design of the core-type five-limb transformer. The system can reduce the installation space, volume, and cabling size. This paper presents a detailed design, sizing, and implementation procedures of the new power supply, including the feasibility study of manufacturing. The modeling performed is based on the nonlinear inductances related to transformer dimensions taking into account its complex magnetic field. At last, a newly developed method describes an approach for modeling the nonlinear inductances by an analytic expression, using the Neuro-Fuzzy Network under the MATLAB-SIMULINK® code. As a result, the simulation curves are consistent with the experiments in the case of the conventional power supply used in a microwave oven. Also, the stabilization of magnetron current is insured.
Keywords:	Stable power supply, Magnetic flux leakage Transformer, Magnetron, Modelling, ANFIS-MATLAB
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	ANALYSIS OF KINECT FALL DETECTION SYSTEM AND REHABILITATION GAMING EXERCISES USING AUGMENTED REALITY (AR) USER INTERFACE AND MULTI - PATH CONVOLUTIONAL NEURAL NETWORK (MP – CNN)
Author:	V MURALIDHARAN, DR V VIJAYALAKSHMI
Abstract:	Among practically all nations, the occurrence of falls in the elderly is currently a big concern. Severe injuries occur as a result of the fall and sometimes even to mortality. Physiotherapy is an analysis of human joints and bodies, which gives remedy for any pains or injuries. Kinect Xbox One is a low – cost 3D camera which can be used for human motion tracking. The human movements are tracked in real time by using Kinect Xbox One and use the human exercises to calculate certain values in parameters. This paper contains, a Multi - Path convolutional Neural Network (MP – CNN) is recommended for doing rehabilitation exercises recognition using Kinect Xbox One sensor data. It contains two important components. They are a Dynamic - convolutional Neural Network (D – CNN) and a State transition probability convolutional Neural Network (S – CNN). Gaussian Mixture Regression (GMR) is used in D – CNN to record the sensor data’s regarding the way the body moves at the time exercising for rehabilitation. The input signal and the GMR are appeared in various segments. In S – CNN we use Lossless Information Compression Encoder Algorithm (LICE) to take use of the hidden states of distinct motions’ the transition probabilities. The combination of D – CNN and S – CNN creates the MP – CNN. We use Augmented Reality (AR) technique in this method. When comparing the results obtained from MP – CNN, KNN and Logistic Regression it is found that MP – CNN is better than Logistic Regression and KNN.
Keywords:	Healthcare, Kinect Xbox One, Rehabilitation Exercises, Recognition, Convolutional Neural Network.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	NATIVE JSON MODEL FOR DATA INTEGRATION IN BUSINESS INTELLIGENT APPLICATIONS
Author:	MOHD KAMIR YUSOF, MUSTAFA MAN, WAN AMIR FAZAMIN WAN HAMZAH, SUHAILAN SAFEI, ISMAHAFEZI ISMAIL
Abstract:	Collection of data is important component for most business intelligent (BI) application to make a best decision regarding to company. Successful of BI application is consist how much this application can provide useful data for decision maker to achieve the company critical goals such as achieving or exceeding revenue, opportunity to reduce cost, etc. However, 80 percent of BI application has a problem to produce useful data because of data integration issue. This issue is occurred because of increasing amount of data., integration difficulties, and high complexity. Universal data integration model is required to provide useful data for BI application. Native XML (NXD) and JSON are two approaches have been implemented in data integration. These approaches are proven efficient for data integration in term of data insertion response time and query processing response time. Based on NXD and JSON, this paper proposed Native JSON (N-JSON) as a new alternative data integration for BI application. Three experiments such as data insertion response time, query processing response time and CPU usage has been done by using two different datasets; SigmodRecord and DBLP. The results indicate N-JSON produces a better performance compared NXD. As a result, N-JSON can be used as an alternative data integration for BI application in order to provide useful data to decision maker.
Keywords:	Data Integration, Business Intelligent, Native XML, JSON, Native JSON
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	AN INNOVATIVE APPROACH CONGESTION MANAGEMENT IN POWER TRANSMISSION LINES WITH ADVANCED CONTROL
Author:	KUMAR CHERUKUPALLI, BADDU NAIK BHUKYA
Abstract:	Due to power line overloading, it is sometimes difficult to allocate all of the necessary power to a supply in a modern power system. The traditional power framework inside seeing Flexible AC Transmission Framework (FACTS) regulators is a choice to deal with this issue and can extend the electrical power framework's ability to manage quick variations in the framework's working conditions. This paper proposes an optimal power flow control strategy for transmission line executives by combining an advanced model of interline power flow controller (AIPFC) calculation with constriction factor-based particle swarm optimization (CFBPSO). When all factors are considered, multi-line FACTS regulators outperform single-line FACTS regulators. The complete exact displaying of an advanced level Interline Power Flow Controller (AIPFC) is presented in this paper and the effect of an ideal area is investigated. To address OPF issues in the context of the advanced model IPFC, an imaginative calculation, such as CFBPSO, is proposed. The proposed method is validated using a standard IEEE 30 bus test framework. The exploration paper revealed the accuracy of the projected calculation through a reduction in the value of the goal work.
Keywords:	Flexible AC Transmission System (FACTS), Advanced Interline Power Flow Controller (AIPFC), Optimal Power Flow (OPF), Constriction Factor Based Particle Swarm Optimization (CFBPSO).
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text

Title:	E-WASTE AWARENESS AND PRACTICES OF ZIMBABWEAN UNIVERSITY STUDENTS: A DESCRIPTIVE STUDY
Author:	VUSUMUZI MAPHOSA, MARGARET MACHERERA, DAVID ZEZAI, JASPER MANGWANA
Abstract:	Africas cyberspace is experiencing unprecedented growth as the continent joins the global village to spur socio-economic development. Information and communication technologies (ICT) have become part of everyday life, and when they reach their end of working life, they become electronic waste (e-waste) and should be appropriately discarded. However, the continent is streaming towards a major crisis as obsolete ICT equipment is indiscriminately disposed of to the detriment of the environment and public health. This study aimed to assess university students’ e-waste awareness and practices. This cross-sectional study was conducted amongst university students in Zimbabwe. After obtaining institutional ethical clearance, a predesigned pretested questionnaire was administered to university students with informed consent. The sample size calculated was 223 from four purposely selected state universities. Part two and four students were randomly selected. Chi-square Test was applied to get the Chi-square value and p-value. Multiple regression analysis was used to determine the significance of the independent variables in explaining the variability of the dependent variable. Our results show that the four independent variables (lack of knowledge, policies, poor practices and handling) positively influenced e-waste management by university students in Zimbabwe. Of the four independent variables, poor handling had the strongest effect on e-waste management with a regression coefficient of 0.420 and the lowest significance of 0.000. Although the knowledge of e-waste was high, students lacked knowledge of policies/laws that regulate environmental and health management. Advanced knowledge of e-waste did not translate into responsible management as e-waste was kept at home, transported and stored with municipal waste, and there were no designated bins for collecting it. Most respondents were unsure of what was happening regarding the generation, handling, storage, transportation and final disposal of e-waste. By analyzing students’ knowledge and practices, universities should intensify e-waste management advocacy by incorporating e-waste matters into their learning curriculum. The government should enact policies that govern the management of e-waste, and this will provide a framework for institutions to set up local-level policies that promote green initiatives.
Keywords:	Health Information, University Students, E-Waste Management, Awareness, Practices
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2022 -- Vol. 100. No. 18-- 2022
Full Text