		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
August 2022 | Vol. 100 No.16

Title:	HYBRID NUMERICAL ASSIGNMENT AND ANALYTICAL HIERARCHICAL PROCESS
Author:	AHMAD BANY DOUMI, AMJAD HUDAIB, MAHMOUD ASASSFEH
Abstract:	Nowadays, the whole world based on software to manage the huge jobs, as results of this, the software became very complex and need systematic way to build them. Therefore, choosing the right requirements from candidate requirements is one of the important steps in software engineering and provide project planning phase with good decisions this is requirement Prioritization. In this paper, we propose hybrid technique of numerical assignment and analytical hierarchical Process to solve requirement prioritization problem at which numerical assignment collect the requirements into different groups as first step, then reciprocal matrix of requirements is developed by analytical hierarchical process and used to compare every pair of requirement of each group with respect to number of criteria. We compare and analyze proposed technique with numerical assignment and analytical hierarchical Process in term of time, number of comparison, number of requirements, scalability, granularity, accuracy, speed and complexity in prioritization process. The results show that proposed technique outperformed on AHP technique by number of requirements, complexity, number of comparison, scalability and speed whereas outperformed on numerical assignment by accuracy and granularity.
Keywords:	Numerical Assignment, Analytical Hierarchical Process, Requirement Prioritization
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	AGILE TEST AUTOMATION FOR WEB APPLICATION USING TESTNG FRAMEWORK WITH RANDOM INTEGRATION ALGORITHM IN MACHINE LEARNING TO PREDICT ACCURACY AND RESPONSE TIME ON AUTOMATED TEST RESULTS
Author:	V.VAMSI KRISHNA, G. GOPINATH
Abstract:	Testing must be a part of any software engineering approach that intends to build high-quality apps. By executing it with input values, testing seeks to find faults in the tested-object and develop confidence in its proper functioning. Web apps take first place in development and testing, according to everyday usage. By automating the entire software development testing process, testing automation saves time and money for developers and testers. Our proposed solution would use the "TestNG framework," an automated testing framework, to test a public website and save the test results in the format of a ".csv" or ".xls" file to a given directory. The Support-Vector-Machine Algorithm (SVM), Random-Forest Algorithm & other machine-learning algorithmshave been used to analyses the output file. The outcomes of all of the different ways will be compared and displayed on a graph. By Automating The Testing Framework Manual Testing Task Will Become Easy.
Keywords:	Test Automation, Web Applications, TestNGFramework, SVM, Random Forest Algorithm, Random Integration Algorithm.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	SYSTEM OF A SELF-ORGANIZING VIRTUAL SECURE COMMUNICATION CHANNEL BASED ON STOCHASTIC MULTI-LAYER ENCRYPTION AND OVERLAY TECHNOLOGIES
Author:	E.A.BASINYA, ZH.B.AKHAYEVA, A.B.ZAKIROVA, D.ZH. OMARKHANOVA, G.B.TOLEGENOVA, В.K.ABDURAIMOVA, L.ALDASHEVA, ZH.A.ZHANAYEVA
Abstract:	The paper considers the problem of ensuring information security of information flows in computer networks operating on the basis of the TCP/IP protocol stack (Transmission Control Protocol/Internet Protocol). one of possible solutions for providing the data transfer protection, proposed in this paper is to use a combination approach to dynamically build encapsulated virtual network tunnels using onion and garlic routing, and additional encryption layers. The algorithm of tunnel self-organization based on the author's modification of the port knocking technology, taking into account metadata about the previous connection (route tracing, duration of interaction, the sequence of port enumeration, protocols and other control information, including the client's computing device) is described. An analysis of the conceptual vulnerabilities of TOR (The Onion Router) and I2P (invisible internet project) overlay networks is made, and possible approaches to their elimination are reviewed. The experiment in identification of unauthorized access to transit traffic on the output nodes of the TOR network is described. Under the experiment “ traps” were used in the form of sending authentication data of own test servers through all active outgoing nodes in an open form , the redirection from top 100 _ foreign sites to other information resources ( including falsification of DNS <Domain Name System> replies ) was tracked . The duration of the experiment was two years. An analysis of the dynamics of the development of TOR network is further described, and the conclusions about the credibility of these networks are outlined. The results of the developed and software - implemented solution are described, as well as the results of testing. In conclusion, findings and recommendations on the use of the proposed system with various parameters are presented.
Keywords:	Traffic Management, Network Attacks, Virtual Secure Communication Channels, Overlay Networks, Onion Traffic Routing, Garlic Traffic Routing, Traffic Analysers, Multilayer Encryption, Encapsulation Of Virtual Tunnels, DPI, TOR, I2P.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	STUDIES OF TRANSMISSION OF INFORMATION AND CONTROL SIGNALS OF TREATMENT PLANTS
Author:	DINARA KOZHAKHMETOVA, DMITRIY MYASSOYEDOV, RASHID NAZAROV, DANAR BEKKASSIMOVA, DINARA KURUSHBAYEVA
Abstract:	This article is devoted to the development of an automated control system for process parameters, which allows transmitting controlled parameters to the computer of the central dispatch control room in order to increase the efficiency of the sewage treatment facilities in Semey due to the possibility of making operational decisions on the control of the process of wastewater treatment based on the monitoring of equipment. The article is aimed at substantiation and development of centralized automated system of control of technological parameters (ASC TP) of treatment facilities of g. Semey, including a microcontroller information system for the main sewer pumping station and blower pumping station and designed for continuous monitoring of operating and limit (emergency) parameters of equipment operation, They are presented in the form of discrete potential and continuous current signals, with the possibility of graphical and sound display of the current information on the panel of controllers and computer monitor with the possibility of saving.
Keywords:	Wastewater Treatment, Sewage Treatment Facilities, Mechanical Treatment, Biological Treatment, Control Systems, Dispatch Control, Sewage Pumping Station, Signal Frequency.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	GRADIENT BOOSTED DECISION TREE (GBDT) AND GREY WOLF OPTIMIZATION (GWO)BASED INTRUSION DETECTION MODEL
Author:	MADURI MADHAVI, DR. NETHRAVATHI
Abstract:	Intrusion Detection Systems (IDS) have become increasingly important as computer networks have grown in size and complexity over the last several years, and they have become an essential component of the system's infrastructure. Increases in the number of breaches into computer networks have been attributed to a thriving underground cybercrime market and advanced technologies that make it simpler to hack into computer networks over the past decade. Researchers in both industry and academia have been working on strategies to detect and prevent these types of security breaches for more than 40 years, and the results have been promising. They have also put in place systems to assist them in this endeavour. It is critical for an intrusion detection system (IDS) to be able to deal with situations such as a low detection rate and a large amount of work. One of the most pressing concerns facing the globe today is that of data security. The hacking of data can occur in a variety of ways, which can render any network or system less effective. Interceptor denial of service (IDS) systems that are still in use are incapable of keeping up with the continually changing and complex nature of incursion activities on computer networks. Discovering and preventing these types of attacks is one of the most difficult tasks we face today. Machine Learning has risen to become one of the most successful methods of learning about things in recent years, thanks to advances in artificial intelligence. Machine Learning approaches have the ability to generalise from known attacks to variations, or even discover new sorts of breaches, which is a beneficial thing for security professionals. In recent years, there has been a lot of research on how to combine multiple strategies in order to increase the detection rates of Machine Learning classifiers. Since the development process for intrusion detection systems has included the use of Artificial Neural Networks and Decision Trees, the technology has risen in popularity. In order to determine how well different machine learning classifiers performed with the KDD99 incursion dataset, a number of tests and evaluations were conducted. The study's main focus was on Grey Wolf optimization (GWO) models based on Gradient Boosted Decision Trees (GBDT). They were used to identify and categorise intrusions, among other things. Furthermore, this research looked into how to create attack rules by using a KDD99 dataset to look for anomalies in network audit data, which was then used to create attack rules. Performance indicators such as the false negative and false positive detection rates are important in order to increase the rate at which an intrusion detection system detects objects that have been broken into by an intruder. In the experiments, different algorithms are compared. There is evidence to suggest that the GBDT is the best since it is the most accurate and does not produce many false positives.
Keywords:	Gradient Boost, Decision Tree, Intrusion Detection System, Grey Wolf Optimization, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	ASSESSMENT OF CYBERSECURITY AWARENESS AMONG E-BANKING IN PALESTINE - EMPIRICAL STUDY FROM CUSTOMER’S PERSPECTIVE
Author:	DERAR ELEYAN, RASHEED YOUSEF , AMNA ELEYAN
Abstract:	The internet services are available and widely expanded in Palestine. This expansion and availability contributed positively in enhancing the quality of services especially in E-banking. The internet services are enhanced and developed after the development and adoption of 3G/4G technology and infrastructure. This development widens the existing services and creates more opportunities for cybercrimes and security threats. These threats mainly attract the financial services. More and more users and beneficiaries become victims; therefore, more awareness is required amongst users and those involved in the e-banking services. In this study performed in depth analysis to measure the level of security and threats awareness related to E-banking service in Palestine and what are the main difficulties which faced the E-banking users in Palestine. Results showed that the average age of e-banking users and customers are from 30-40 years old are 42.4%, 65.3% of them are males and 55.4% holding BA degree as a level of education and 70% of the customers are using the e-banking services for more than a year. Recommendations have been suggested to raise the customers awareness to avoid victims and minimize the loss of data and money.
Keywords:	Cybersecurity, E-Banking, Cybercrime, Security Awareness.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	AN IMPROVED SARDINE FEAST METAHEURISTIC OPTIMIZATION BASED ON LÉVY FLIGHT
Author:	MOHAMMAD FAIDZUL NASRUDIN, DWI YANUAR PANJI TRESNA
Abstract:	The recently proposed Sardine Feast Metaheuristic Optimization (SFMO) is a population-based meta-heuristic optimization algorithm inspired by the commensal behavior of various predators while preying on sardines at sea, which is commonly known as a sardine feast. This algorithm is a behavior imitation of dolphins and sea birds (blue-footed boobies and brown pelican) preying on schools of sardines. SFMO suffers from premature convergence since it relies on the normal random function to calculate predators' movement or step size during exploration and exploitation. The proposed improved SFMO (SFMO-Lévy) aims to enhance the ability of predators to explore divergent areas using Lévy flight in the step size calculation. The performance of the SFMO-Lévy is investigated using several predefined benchmark functions for global optimization problems. The outcomes of the tests are then compared with those generated by the standard SFMO algorithm. The SFMO-Lévy outperforms the SFMO by providing an average of 23.44% fewer function evaluations. The results reveal that the proposed algorithm can solve the benchmark functions better than the standard SFMO algorithm.
Keywords:	Sardine Feast Metaheuristic Optimization, Lévy Flight, Metaheuristics, Global Optimization
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	BIG DATA-BASED SW EDUCATION CURRICULUM RECOMMENDATION PLATFORM DEDIGN FOR LEARNERS
Author:	JI HOON SEO
Abstract:	The current educational infrastructure environment is trying to change in line with the 21st century. As the importance of computational thinking, software, and artificial intelligence education gradually increases in the trend of using subject-centered curriculum, experience-oriented curriculum for learners is spreading. Since a general curriculum do not consider basic knowledge and difficulty of individuals but run the education by following the setup, it has limitations in realizing high satisfaction of learners and providing an effective education. Accordingly, this study uses online self-diagnostic data for learners based on AI education, which is the core of the future curriculum, to diagnose individual competency and difficulty, and develops a curriculum recommendation system that recommends personalized learning contents according to personal level of the learner.
Keywords:	Education System, Opinion mining, Recommendation system, Learning care platform.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	A FRAMEWORK FOR REDUCE CO2 EMISSIONS AND ENHANCING ENVIRONMENTAL SUSTAINABILITY PROTECTION USING IOT AND ARTIFICIAL INTELLIGENCE
Author:	YASSINE CHAHID, ISMAIL CHAHID, MOHAMMED BENABDELLAH
Abstract:	In recent years, our environment is constantly changing and faces multiple problems, it is for this reason that is necessary to become increasingly aware of all problems that surround it. The parts per million of CO2 in 2022 is 418 and the global temperature rise now 1.1 Celsius [1]. The whole world knew several disasters due to the increase in greenhouse gas emissions, these disasters are multiple like eat waves and flooding to be more intense and frequent than seen before. According to this study [2], even if all greenhouse gas emissions were halted in 2020, global warming would only be halted by around 2033. The IoT market, and specially M2M (Industrial IoT) sector, has been growing very rapidly for several years, at the same time, a crucial issue for urban planning has emerged: the need for a green economy that would make it possible to reconcile cities with the environment. The AI also makes it possible to rationalize agricultural operations, optimize yield and contribute to the reduction or elimination of insecticides and chemical products by detecting the proliferation of diseases or insects as early as possible. The purpose of this article is to give a state of the art on the use of IoT and AI to enhance environmental sustainability, propose a secure solution based on IoT and AI to reduce and optimize the time of waste collection in smart cities and the CO2 emissions.
Keywords:	CO2, Internet of Things, Artificial Intelligence, Environmental Sustainability, Architecture
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	KOREA GRAMMER-BASED SENTIMENT DICTIONARY DESIGN TO IMPROVE THE RELIABILITY OF OPINION MINING TECHNIQUES
Author:	JI HOON SEO
Abstract:	The contemporary society is shifting to a paradigm that creates valuable data by utilizing various types of data. The value of such data is highly appreciated, and the vast asset serves as useful analysis materials in information warfare. Entering the 21st century, the amount of data is increasing geometrically. The more data collected from such big data, the higher accuracy of its analysis, and the more efficient data extracted. Big data analysis consists of structured and unstructured data analysis. One of the analysis methods of text-type unstructured data is opinion mining. The analytical method is advanced text mining, which determines the status of the given sentence as either positive or negative based on sentiment words to analyze reputation. This study draws out an integrated Korean-based sentiment dictionary algorithm to enhance the accuracy of reputation analysis when using Korean as sentiment words in opinion mining analysis. Since Korean grammar shows different characteristics in vocabulary formation compared to English, SWN used in English grammar analysis has limitations in its application to Korean. Thus this study aims to build up a Korean-style sentiment dictionary, thereby proposing a methodology to increase the precision of opinion mining analysis.
Keywords:	Big data, Opinion mining, Sentiment analysis, Sentiment data dictionary
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	ARTIFICIAL INTELLIGENCE IN PROJECT MANAGEMENT RESEARCH: A BIBLIOMETRIC ANALYSIS
Author:	VUSUMUZI MAPHOSA, MFOWABO MAPHOSA
Abstract:	Projects are critical to organizations' success; hence improving project management (PM) is imperative. Artificial intelligence (AI) has revolutionized many disciplines, including PM. Applying AI techniques in PM can lead to more control for the project manager and better management of projects. One of the inherent problems faced in PM is related to human error by the project managers leading to project failure. Project managers use PM software and tools to improve their tasks. In this paper, we demonstrate the application of AI in project management through a bibliometric analysis and keyword analysis to show the state of the art of research on AI in PM in the past decade. We extracted 106 articles from the Web of Science database published between 2012 and 2021 and analyzed the data. VOSviewer provided visual maps revealing research hotspots in the field of AI in the HE knowledge base. Our analysis focuses on publication and citation trends, the geographic distribution of articles, analysis of papers by source in which they were published, h-index analysis, and keyword analysis. Results show that research in AI-based PM is widely distributed geographically, by the publisher, and by discipline or field. Furthermore, research in the corpus in the past decade has centered around four themes. The first theme relates to applying AI techniques to improve accuracy, precision, and prediction in software projects, project management, and development estimation. The second theme focuses on the application and development of AI for decision-making in PM. The third theme highlights the benefits of applying AI in PM, such as dealing with uncertainty, improving efficiency, scheduling, and stakeholder management. The last theme shows how AI manages risks and improves cost management in engineering, procurement, and construction (EPC) projects. This research makes valuable contributions to the corpus by highlighting opportunities, challenges, and future research directions in AI in education. The study highlights its limitations and future research areas.
Keywords:	Project Management, Artificial Intelligence, Bibliometric Analysis, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	FEDERATED LEARNING DISTRIBUTED CONSENSUS ALGORITHM FOR TELEMEDICINE
Author:	YOUNGBOK CHO
Abstract:	Recently, as the importance of telemedicine increases due to the COVID-19 pandemic, interest in the safe use of medical data is increasing. The need for safe and effective management of personal information is emerging as the number of hacking cases related to personal information is increasing due to the activation of big data utilization and the activation of telemedicine due to the 4th industrial revolution. In addition, since personal information used in the medical field is classified as sensitive information, it is necessary to focus more on security. However, in order to access one's own medical information in telemedicine and big data environments, it must be provided anytime, anywhere. In Korea, medical information is currently managed in the form of centralization where local hospitals store and manage each patient's data. Therefore, the problem of centralized data management was solved by applying block-chain technology. It provides more free information exchange in cooperative telemedicine and ensures the privacy of patient information while safely reaching mutual agreements
Keywords:	Telemedicine, Federated Learning, Distributed Consensus Algorithm, Privacy, Black-chain
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	PERCEPTIVE GENETIC ALGORITHM-BASED WOLF INSPIRED CLASSIFIER FOR BIG SENTIMENT DATA ANALYSIS
Author:	Ms. D. J. ANITHA MERLIN, Dr. D. VIMAL KUMAR
Abstract:	Big data analytics has a significant impact on real-time purchasing and e-commerce, and it’s being used to boost sales and enhance consumer interactions. Customers increasingly rely on online marketing to find the best deals on high-quality goods. Social media activity on both sides of the transaction might reveal information about the customer’s purchase experience and opinions about the business. Using Sentimental Analysis (SA), one can figure out how something makes you feel. SA examines people’s ideas and feelings about a product. The importance of acquiring insight into customers’ sentiments when purchasing things is reduced when SA is weak. Also, the influence of understanding the consumers’ impression of a product is reduced. For sentiment analysis in big data, this research proposes a Perceptive Genetic Algorithm-based Wolf Inspired Classifier (PGAWIC). For sentiment analysis in large product review datasets, PGAWIC draws inspiration from wolf foraging behavior. Better optimization for classifying the sentiments is achieved using genetic algorithms. The proposed classifier is evaluated using MATLAB with the metrics namely precision accuracy and f-measure performance measures on a four-product review dataset. According to the results, the proposed classifier PGAWIC is more accurate than the current classifiers in classifying the sentiments.
Keywords:	Sentiment, Classification, Amazon, Wolf, Genetic
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	A SYSTEMATIC REVIEW ON MOTORCYCLISTS’ AGGRESSIVE BEHAVIOR ANALYSIS USING COMPUTATIONAL MODELS: CURRENT STATE, CHALLENGES, AND RECOMMENDATIONS
Author:	SARAH NAJM ABDULWAHID, MOAMIN A. MAHMOUD, HASSAN MUWAFAQ GHENI, SALAMA A. MOSTAFA, ALI MOHAMMED
Abstract:	There is an increase in motorcycles traffic accidents, while the cause for such accidents has always been associated with aggressive driving behaviors. There has been considerable research attention on how to deal with such driving behavior that causes severe and fatal accidents from the academic perspective; these research works addressed technical, scientific, and social issues. This study systematically searches, reviews, and analyzes the literature associated with motorcycle accidents and driving behaviors. Between the years 2014 and 2021, the next four databases have been searched: ScienceDirect, Scopus, Web of Science, and IEEE Xplore. A total of 108 people were picked depending on certain inclusion and exclusion criteria. Approximately 68% (n=79/108) of the researchers looked at the challenges from a social science perspective, whereas 25% (n=26/108) concentrated on experimental research variables. Only 7% (n=3/108) explored the development of Apps & systems. Finally, our contribution comprehensively analyses most of the articles by highlighting challenges associated with motorcycle behavior, motivations, and recommendations. In addition, provide potential research gaps in current studies that require further investigation.
Keywords:	Accident Causation, Driving Behavior, Traffic Violation, Motorcyclists, Computational Models
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	FAKE-NEWS DETECTION SYSTEM USING MACHINE-LEARNING ALGORITHMS FOR ARABIC-LANGUAGE CONTENT
Author:	MOUTAZ ALAZAB, ALBARA AWAJAN, AMMAR ALAZAB, ANSAM KHREISAT,‪ ABEER ALHYARI, REEM SAADEH‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬
Abstract:	Over the past decade, social media has become a dominant source of news and information. This has led to an increase in the number of groups and individuals spreading news through social media with no direct quality control or censorship of the content being distributed. A fake breaking-news headline can spread rapidly to millions of people and cause tremendous local and global problems. Because checking all information posted on social media is almost impossible, researchers are now concentrating on combating fake news on the Internet and social media to mitigate the enormous damage the spread of such news can cause to individuals, communities, and nations. To detect whether news is fake and stop it before it can spread, a reliable, rapid, and automated system using artificial intelligence should be applied. Hence, in this study, an Arabic fake-news detection system that uses machine-learning algorithms is proposed. An in-house Arabic dataset containing 206,080 tweets was collected using an API search on Twitter. The algorithm uses term frequency-inverse document frequency to extract features from the dataset and analysis of variance to select subsets from them. Nine machine-learning classifiers were used to train the model (naïve Bayes, K-nearest-neighbours, support vector machine, random forest (RF), J48, logistic regression, random committee (RC), J-Rip, and simple logistics). The experimental results indicated that the highest accuracy (97.3%) was obtained using the random forest and random committee, with training times of 4403s and 0.367s, respectively.
Keywords:	Cybersecurity, Artificial intelligence, Social Media, Fake News, Machine Learning, API Search, Twitter.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	A NOVEL SEQUENCE-BASED NEGATIVE SAMPLING APPROACH FOR IMPROVING PROTEIN-PROTEIN INTERACTIONS PREDICTION USING MACHINE LEARNING TECHNIQUES
Author:	M. SAYED BARKAT, SHERIN M. MOUSSA, NAGWA L. BADR
Abstract:	Protein–protein interactions (PPIs) have been involved in numerous diseases’ progression in drug discovery. Although PPIs prediction is a crucial and well-studied task in bioinformatics, they still lack thorough investigations for several proteins. The cost of understanding PPIs and identifying protein–protein non-interactions (PPNIs) using sequence alignment make the current computational methods inefficient, so identifying PPNIs without applying sequence alignment has become a necessity. In this research, a machine learning approach is proposed for PPIs prediction based on protein sequence information, in which we introduced “Features-based Negative Generation” which is a novel approach for identifying PPNIs samples. This method measures sequence features' similarity without alignment for an affordable computational feasibility. After PPNIs identification the Conjoint Triad (COT) and Epitopes are used for features extraction and results of both are compared to achieve higher accuracy with less time consumption. Five machine learning techniques were investigated to learn from the interacting pairs sequence, obtaining PPI features. Support vector machine (SVM) with polynomial and RBF kernel functions, Linear SVM, Tree Model (TM) and Linear Model, and the (TM) achieved the best result with an accuracy of 97.8%. The experimentation of PPIs prediction using generated negative dataset and COT using 343 features achieved an accuracy of 97.8%, versus 93% using random negative dataset using COT also. Applying Epitopes with our PPNIs dataset using 21 features achieved an accuracy of 94.5% versus 92.5% with random negative dataset, which indicates that identified PPNIs datasets are clearer, less noise and prediction of PPI using identified PPNIs is more accurate. We compared PPI prediction accuracy using identified PPNIs which extracted using our method with that obtained by other methods in the literature, and we found improvement in our favor of between 2 and 7%. Considering Epitopes for features extraction is faster than COT by an average of 83%.
Keywords:	Protein-Protein Interaction, Protein–Protein Negative Interactions, Machine Learning, Biological Pathways, Drug Discovery, Ppnis Sampling, Epitopes, Conjoint Triad Method.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	MACHINE LEARNING-BASED SENTIMENT ANALYSIS FOR TWEETS SAUDI TOURISM
Author:	SARAH M ALRASHIDI, FATMH N ALANAZI, HANAN A ALBALAWI, OHOOD M ALBALAWI, AWAD M AWADELKARIM
Abstract:	The growth of tourism in Saudi Arabia is a superior aspect of the recent economic success and realization of the Kingdom of Saudi Arabia's Vision 2030. This places a premium on research in such field and elevates it to national priority research, thus, this research project contributes to such context and places a premium on sentiment analysis in the tourism industry, namely concentrating on tweets about Saudi tourism. Therefore, this paper intends to demonstrate machine learning-based sentiment analysis models for tweets on Saudi tourism. The research studies and analyzes tweets related to tourism collected about six touristic places in Saudi Arabia from twenty accounts and nineteen touristic places from 144 hashtags. Following the preprocessing and feature extraction stage, such tweets are labeled as positive or negative using various machine learning algorithms. Two base classifier models of Support Vector Machine (SVM) and Naïve Bayes (NB) are applied. Over and above, a vital and important contribution of this project is creating the First Dataset for Tweets Saudi Tourism (FDTST) in both Arabic and English languages collected from Twitter libraries. Utterly, numerous classification models are developed and evaluated based on their performance computation, and the experimental results show that the developed models have achieved righteous and reliable upshots. Finally, the developed predictive models aid to appoint and specify several valuable recommendations and insights for continuous improvements and sustainable growth in the Saudi tourism industry.
Keywords:	Sentiment Analysis, Machine Learning, Saudi Tourism, Tweets Saudi Tourism, Classification Models.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	FAKE NEWS CONSUMPTION AMONG INDONESIAN GENERATION Z ON TWITTER DURING PANDEMIC COVID-19
Author:	ANDARI KARINA ANOM, DIAN AYURIA SARWONO , YOSEPHINE CLAUDIA CHANDRA
Abstract:	This research aims to analyze how Indonesian Gen Z identifies and responds to fake news on Twitter and what types of sources produce fake news on Twitter. The research findings showed that Indonesian Gen Z identifies fake news through five metrics: Content, Context, Semantics, Structure, and User. The most used metric they used, which marked as the novelty findings of this research, was Context and Structure. Furthermore, Indonesian Gen Z tends to respond to fake news through Passive Engagement more, such as ignoring, cross-checking, passively reading, and showing skepticism, compared to Active Engagement, such as replying, sharing, and reporting.
Keywords:	Hoax, Fact Check, Twitter, Covid-19 Hoaxes, Indonesian Youth
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	AUTONOMOUS ROBOT SYSTEM FOR PAVEMENT CRACK INSPECTION BASED CNN MODEL
Author:	ALAA SHETA, SAHAR A. MOKHTAR
Abstract:	Maintaining the excellent state of the road is critical to secure driving and is an obligation of both transportation and regulatory maintenance authorities. For a safe driving environment, it is essential to inspect road surfaces for defects or degradation frequently. This process is found to be labor-intensive and necessitates primary expertise. Therefore, it is challenging to examine road cracks visually; thus, we must effectively employ computer visualization and robotics tools to support this mission. This research provides our initial idea of simulating an Autonomous Robot System (ARS) to perform pavement assessments. The ARS for crack inspection is a camera-equipped mobile robot (i.e., an Android phone) to collect images on the road. The proposed system is simulated using an mBot robot armed with an Android phone that gathers video streams to be processed on a server that has a pre-training Convolutional Neural Networks (CNN) that can recognize crack existence. The proposed CNN model attained 99.0% accuracy in the training case and 97.5% in the testing case. The results of this research are suitable for application with a commercial mobile robot as an autonomous platform for pavement inspections.
Keywords:	Autonomous Robot System, Deep Neural Network, Road Maintenance, Crack Detection, Pavement Crack, Automatic Detection.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	IMPROVE GAMIFICATION DESIGN WITH UX DESIGN ELEMENTS: A SURVEY WITH PRACTITIONERS
Author:	OMAR AZOUZ, NOUAMANE KARIOH, YOUSSEF LEFDAOUI
Abstract:	Since the emergence of Gamification, many design frameworks have been proposed. However, the implementation of this concept is still subject to risk due to the lack of tools, best practices and complete processes that cover the end-to-end product cycle. This article proposes an online questionnaire addressed to UX and Gamification practitioners to explore the UX design elements that can enhance Gamification design. Therefore, the aim of this paper is to investigate the relevance of adapting and adopting UX design elements in order to enhance the design of gamified products from the practitioners' perspective. To achieve this goal, this study proposes and analyzes the results of a survey to which 123 practitioners responded. We sampled the participants by inviting over 1200 practitioners extracted from the LinkedIn network. The purpose of the survey is (i) to collect feedback from Gamification and/or UX practitioners on the design of gamified products, (ii) to identify the UX design elements that need to be adapted to the specificities of Gamification, and (iii) to conclude guidelines to help unify a design process for a meaningful user experience. The survey results show that, in general, UX and Gamification practitioners share the relevance of strengthening Gamification design via UX design elements. Several recommendations have been highlighted in order to adapt UX processes to deal with the specificities of Gamification such as the adaptation of the tracks of the MAP journey to better analyze the motivation and engagement of users. The Persona is also concerned by adaptation proposals to include player profiling in the current model. Finally, we conclude by suggesting starting points for the unification of a UX process specific to gamified products.
Keywords:	Gamification, User experience Design, UX Design Element, Process, Survey.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	WILL FINANCIAL BEHAVIOR BE ABLE TO MODERATE THE RELATIONSHIP BETWEEN LOCUS OF CONTROL AND FINANCIAL KNOWLEDGE ON YOUNG GENERATION'S DECISION MAKING IN CRYPTO INVESTMENT?
Author:	MEIRYANI , DEBBY , MONICA
Abstract:	The development of information technology encourages the growth of technology in the financial sector (financial technology). Financial technology is an innovative business model and new technology that has the potential to transform the financial services industry. In this study, the author will discuss cryptocurrency which is the result of the development of financial technology. Although cryptocurrency technology is considered as one of the secure online integrated payment systems in financial transactions, cryptocurrencies are considered to be still not ready to face uncertain economic movements and do not yet have an adequate legal basis. Therefore, this study aims to find out what factors influence the young generation in making decisions to invest in cryptocurrencies and how prepared Indonesia's young generation is to face the advancement of financial technology (cryptocurrency). In this study, financial knowledge and locus of control will be used as independent variables, financial behavior as a moderating variable and financial decision as a dependent variable in examining factors that influence the young generation in making decisions. We use a questionnaire survey that provides input on the response of the young generation on this matter. We took a sample of the young generation with an age range of 18-20 years as many as 75 respondents who were chosen randomly. The results of this study indicate that the factors that influence the young generation in making decisions to invest in cryptocurrencies are locus of control which has been moderated by financial behavior and the majority of respondents invest in cryptocurrencies because they follow trends or just for Fomo, more mature preparation is needed in the face of advances in financial technology.
Keywords:	Cryptocurrency, Locus of Control, Financial Knowledge, Financial Decisions, Financial Behaviour
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	GAMIFICATION IMPLEMENTATION ON XYZ DIGITAL PAYMENT SERVICE PROVIDER APPLICATION
Author:	WILDIYANTO YAWIN, GUNAWAN WANG
Abstract:	Nowadays, the importance of gamification is increasingly conscious by many organizations to increase the motivation of their users to spend more on their applications. Many merchants are still unaware of the importance of data in decision-making. The results of interviews with XYZ application users conducted during the previous research show that many users still keep their transaction data in notes, and mistakes like missed transactions, occur frequently. Data that is neatly organized might give them additional insight into how to improve their business. Gamification has become one of the things that keep the users retain to the application services. Through mechanics, dynamics and emotions (MDE) Framework and Self-Determination Theory, result have show that the solution from the framework that the researchers do have prove that gamification can become one of the part that reduce the number of churn rate and increase the motivation to keep using services provided. The objective of this study is to explore how gamification can increase the usage of digital payment service provider and boost their motivation to spend more on the services.
Keywords:	Gamification, MDE Framework, Self-Determination Theory, Fintech, Boost Motivation
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	SECURE XML VIA APPLICATION OF SOAP-BASED TEXTUAL STEGANOGRAPHY ALGORITHM
Author:	MUBARAK AL-MARRI, LOKMAN MOHD FADZIL
Abstract:	This paper briefly reviews the emerging use of and the application of steganographic techniques for exchanging secret messages in a digital medium. In the era of ever-increasing cyberattacks, there is an extreme need for reliable and secure communication. In this respect, cryptography approach has been used to encrypt or encode a textual message with a protective key to prevent unauthorized access. However, encrypted information can conspicuously challenge the hackers and instigate them to crack the code. In contrast, stenographic methods are surreptitiously employed on what appears as a perfectly normal text is actually hiding certain secretive message contents. In a two-part communication structure comprising the message and the message transport, the message is hidden by applying steganographic techniques to be delivered by Simple Object Access Protocol (SOAP). The author’s contribution is a proposed algorithm that resolved current algorithm limitations by increasing message size, maintaining the stego file size equivalency to the real file, and minimizing the real message and the stego message differences. This is accomplished by developing encoding and decoding functions in the algorithm. The encoder extracts the equivalent sequence number from a predefined file representing a null value to generate an arbitrary record to be written to an XML file. The decoder read and select the block to extract the equivalent number that equals the null tags, and search in the database to select the equivalent character to the extracted number to be added to the string. Optional SOAP fields which are normally empty or unfilled are also being used with other tags to hide one character, so one block will be equal to one character based on null values. The XML file, embedded with the SOAP tags, which provides competitive performance in benchmark tests, can be used to securely transact information over the Web.
Keywords:	Algorithm, Cryptography, SOAP, Steganography, XML
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	ENHANCING EFFICIENCY OF THE RULA BY INTERFERING WITH FUZZY LOGIC
Author:	MALEK KHALAF ALBZEIRAT, OSAMA M. ALKHAWALDEH, KADHIM H. SUFFER
Abstract:	Rapid upper limb assessment (RULA) is a survey method developed for assessing the exposure to risk factors associated with musculoskeletal disorders (MSDs). Based on the results of the data collection and the process using the RULA method the work tools or workstations are redesigned in order to avoid musculoskeletal problems. However, users of this tool may be uncertain about his/her risk assessment. A new model based on Fuzzy logic is presented to eliminate the uncertainty that occurs through the risk calculation. The proposed model was verified by a real case study in a solar power plant cleaning process and showed more flexibility in the decision-making.
Keywords:	RULA, Fuzzy Logic, Efficiency, Risk Assessment
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	KNOWLEDGE GRAPH AND SEMANTIC WEB MODEL FOR CROSS DOMAIN
Author:	SHITAL KAKAD , SUDHIR DHAGE
Abstract:	The industry and institutes systems are designed to develop a smart world. The heterogeneous data is available on the web. It is difficult to retrieve precise information from the current web. Semantic web is a solution for semantic interoperability. There are different existing ontology in the education domain. Nowadays, the Industry-Institute gap is increasing due to various reasons. These gaps can be bridged after finding gaps by planning and conducting different activities for students. It will automatically reduce the unemployment rate. Industry and Institute both are equally responsible to develop quality students. In this paper, cross domain (Industry domain and Institute domain) ontology based semantic models are developed to bridge the institute-industry gap using Protégé 5.5.0 editor. The classes and sub classes of Industry-Institute ontology are designed with the help of domain experts. Then, object property and data property are defined to enhance ontology. Next, the result of ontology is validated using HermiT reasoner, DL query and SPARQL query. The graphical representation of ontology is shown by using OntoGraf, OWLViz and VOWL plugin.
Keywords:	Ontology, Semantic Web, protégé 5.5.0, Cross Domain, Data Annotation, Data Filtering
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	NETWORK TRAFFIC RESEARCH BETWEEN LAN AND ISP BASED ON OPNET MODELER AND WIRESHARK APPLICATION PROGRAMS
Author:	NAUBETOV D., YAKUBOVA M.Z., MIRZAKULOVA S.A., YAKUBOV D.M., SERIKOV T.G.
Abstract:	Today, a person and a data processing system need quick access to any information on the Internet. To satisfy these needs, more and more Internet Service Providers are appearing on the market. Accordingly, any LAN should receive stable network traffic with minimal delays. The article is devoted to the study of traffic in the network between the LAN and the provider. The network under study was developed on OPNET Modeler with a complete step-by-step description. The logical parameters of the communication line are calculated: throughput and quality of service (QoS) depending on the codec used for voice transmission. The calculation of the information flow to the Internet was made, which allows identifying the shortcomings associated with the bandwidth and congestion of the channel. The congestion of the channel at the slightest increase in load can cause users large delays and packet loss, which will not allow users to work efficiently and use all the possibilities of accessing the Internet. To check the reliability of the network structure, a passive attack was carried out on the developed model using the WireShark program and the network security parameters between the LAN and the ISP were determined using the Net Doctor Module of the OPNET Modeler program. Link analysis between LAN and ISP solves the issues of optimal functional connectivity and productive user experience by analyzing passing traffic, analyzing and investigating the physical connection of the network to the ISP and further blocking unwanted load.
Keywords:	LAN, ISP (Internet service provider), OPNET Modeler, Wireshark.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	AN OPTIMIZED EXTREMELY RANDOMIZED TREE MODEL FOR BREAST CANCER CLASSIFICATION
Author:	TINA ELIZABETH MATHEW
Abstract:	Breast Cancer is a non-communicable disease seen primarily in women population. As per the statistics published by the World Health Organization, it is presently ranked, globally, as number one in incidence. It can principally affect women of any age, and can be diagnosed in any of the five stages of the disease, but chances of cancer survival become more difficult when diagnosis is made in advanced stages of the disease. Mortality rate of cancer is seen to be high in developing countries than in developed countries. Owing to this fact breast cancer prediction, diagnostic and therapeutic facilities need to be urgently improved in this extent. Henceforth, development of clinical decision support systems for early and precise detection of the disease gains significance and is the need of the hour. The study aims in building a model for precise classification of breast tumors with minimum misclassification of labels. In this paper the potential of extra tree classifiers for breast cancer classification into malignant or benign tumors is examined. A model for breast cancer classification is proposed using extremely randomized tree classifier. Hyperparameter optimization is applied. Identification of important features aids in model performance. Features relevant to disease detection are identified and ranked by importance using 3 techniques- impurity based, permutation based and Shap values. The most important four features identified are Size Uniformity, Shape Uniformity, Bare Nucleoli and Normal Nucleoli. Performance of the optimized model is analyzed using training-testing partitions and k fold stratified cross validation with k as 5 and it was observed that they produced an accuracy of 99.27% on the test set and 97.3 % on the cross validated model respectively. The study reveals the suitability of the extra tree classifier for breast cancer classification. The model is compared with other state of art models and it was seen to be superior in performance. Furthermore, extremely randomized tree classifiers are perceived to be suitable in developing models for breast cancer classification with minimal misclassification of instances.
Keywords:	Breast Cancer, Classification, Extremely Randomized Tree Classifier, Feature Importance, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	IFAA ANALYSIS: AN INTELLIGENT FRAMEWORK AWARE ALGORITHM TO DETERMINE SHORTEST ROUTE TO BOUNDARY OF AREA UNDER ATTACK IN MILITARY SURVEILLANCE AND RECONNAISSANCE WSN AND ANALYSIS
Author:	S. DEEPAK RAJ, Dr. RAMESH BABU. H. S
Abstract:	Wireless sensor networks (WSNs) have proven effective in military applications of surveillance and reconnaissance. Sensors capable of detecting pressure, temperature, movement and presence of specific chemicals are deployed in such applications. Traditionally, sensor data is collected and transferred to a centralized high-capacity node or control station. Analysis of data is carried out at such centralized facilities. Information or intelligence gathered from sensor data after analysis is later used to generate control and management commands that are relayed back to sensor nodes. The situation is analogous to an actual wartime scenario where soldiers who are on the field are equivalent to the sensors. Soldiers observe and sense the situation and communicate their observations to the decision maker who is stationed in the control tent. On gathering field information, the decision maker analyses the data and arrives at his decision which is again communicated to the soldiers on the field. Soldiers as well as sensors are not placed illogically or randomly but intentionally and strategically. Observations made on the field ultimately affect how the soldiers or sensors continue to function. Intelligence gained on the field ultimately gets used on the field itself. Our attempt is to observe, analyze and apply intelligence on the field itself. This work proposes an intelligent algorithm that is aware of the sensor network topology, analyses sensor data within the network and uses the network framework to arrive at usable intelligence. Locally generated intelligence avoids communication to and from the command/control and adds value to military surveillance and reconnaissance applications of WSN. Intelligent sensor management allows us to use just the necessary number of sensors while saving resources on otherwise redundant expenditure. In the present work we have designed and applied a dynamic shortest route to the boundary of the area under attack. We have compared the results of simulation experiments incorporating the proposed algorithm against a control experiment without the algorithm.
Keywords:	WSN, Surveillance, Shortest route, Intelligent framework, Framework awareness
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	DEVELOPMENT OF AN ALGORITHM AND CONSTRUCTION OF A MODEL FOR SOLVING A WAVE PROBLEM WHEN AN ELASTIC STRIP IS BENT, PARTIALLY SOLDERED INTO A HALF-PLANE
Author:	ZHUZBAYEV SERIK, KHABDOLDA BOLAT, 1TANIRBERGENOV ADILBEK, SEITZHAN NARTAY, ISSABEKOVA LYAZZAT, SADYKOVA ANAR, ABENOVA ASSEM, BAIDAULETOVA AIZHAN
Abstract:	The article considers the numerical solutions of some spatial non-stationary problems for elastic and elastic-plastic bodies of finite dimensions in the form of a parallelepiped, and for them the regularities of the propagation of three-dimensional waves are studied. An explicit difference scheme based on a combination of the methods of bicharacteristics and splitting in spatial variables is presented. Based on the described method, the elastic problem of longitudinal and transverse impact on a parallelepiped with one rigidly fixed end is solved. The features of the propagation of three-dimensional waves and the influence of a change in the speed of an external load on the pattern of wave propagation are studied, and some features of the propagation of dynamic stresses in the vicinity of a rigidly fixed end are revealed. Based on the method, an algorithm for calculating the relationship between stress and seismic environment was developed, which made it possible to generate a code and design an information system for calculating the wave process
Keywords:	Information Systems, Wave Process, Explosive Technologies, Bicharacteristics Method, Stress Tensor.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	EFFICIENT CYBER INTRUSION DETECTION TECHNIQUE BASED ON AN ENSEMBLE CLASSIFIER
Author:	MD HARIS UDDIN SHARIF, SHAMIM UDDING AHMED
Abstract:	In the digital world, online base network communication increased significantly. Cause of this, numerous cyberattacks occur every day and create a challenge for the network system to identify that intrusion on time. In addition, within the network, we cannot ignore the existence of intruders as they can launch many harmful cyberattacks. An intrusion detection system is the most valuable technique to help prevent network systems by investigating the network traffic. There are many intrusions detection research has been conducted. However, intrusion detection system still has some research gap and challenges that need to be improved to detect the accuracy of new intrusions. For this purpose, current artificial intelligence-based approaches, especially machine learning (ML) and deep learning (DL), are highly capable of intrusion detection in a network system. Both methods provide accurate outcomes. We proposed a novel, fast, efficient intrusion detection technique based on an ensemble classifier. The suggested classifier integrates all votes of the classifiers from the various instances that operate hard voting to reach the absolute voted class identity label. However, it has been shown on standard datasets of Network Security Laboratory and Knowledge Discovery in Databases (KDD). The suggested method acquired the most heightened precision of 98.19%.
Keywords:	Machine Learning; Deep Learning; Artificial Neural Network; Cyber Security; Intrusion Detection; Ensemble Method
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	AGE CLASSIFICATION USING ISOMETRIC AND ANISOMETRIC CROSS DIAGONAL -LOCAL DIRECTION TERNARY MATRIX
Author:	AKARAPU SWARNA, V.VENKATA KRISHNA, SUPREETHI K.P
Abstract:	Aging has a massive effect on the features and appearance of the human face. Even though various traits are utilized to estimate human age, this article focuses on age classification using prominent texture and edge-based feature vectors. Most of the local-based methods derive features on a circular window. The applications related to facial skin require the computation of elliptical or anisotropic features since the lips, eyes, and other prominent facial skin features primarily represent elliptical shapes. Further, the locally-based approaches are prevalent in estimating human age; however, most of these methods are intensity-based and sensitive to noise illumination changes, thus may not provide better results. To address this, the local directional patterns (LDP) are proposed, which derives features based on the top edge responses in all eight directions in the form of binary patterns of a 3x3 window. The disadvantage of LDP is finding the threshold for top edge responses. This paper derived an automatic process for deriving thresholds and explored the derivation of the ternary pattern instead of binary patterns. To reduce the complexity, the 3x3 window is divided into cross diagonal -local direction Ternary matrix (CD-LDTM) on both isometric (ICD-LDTM) and anisometric (ACD-LDTM) local structures. The facial features derived by the proposed ICD-LDTM and ACD-LDTM descriptors are fed to machine learning classifiers for age classification purposes. The experimental results demonstrate that the proposed strategy is effective.
Keywords:	Edge Responses; Intensity; Elliptical Features; Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	VARIABILITY ANALYSIS USING PHASE-SPACE DIAGRAMS IN AUTOMATED TEST EQUIPMENT
Author:	LOKMAN MOHD FADZIL, WAN MANSOR WAN MUHAMAD
Abstract:	Integral to authors own PhD research is the investigation on the enhancements to variability in semiconductor industry Automatic Test Equipment’s (ATE’s) equipment maintenance time. Based on industry’s case studies on product yields, ATE downtime, and ATE throughput time, ATE process variability is perceived as a real problem in semiconductor manufacturing industry. However, effective methods for addressing process variability is not available in the literature. The author proposed a relationship-based research where Independent variables (IV) designated as Production Time (PT), Idling Time (IT), Repair Time (RT), and Engineering Time (ET) with Production Yield (PY) as dependent variable (DV) are being used. A chaos theory four-quadrant phase space was plotted with coordinates in a chronological order. X-axis represents “PT changes”, “IT changes”, “RT changes” and “ET changes” signifying differences in factory shift ATE’s time, while “PY changes” illustrated differences in output on y-axis in separate charts. Quadrant in the upper-right section embodies increase in factory output with increase in ATE’s IV and DV. Quadrant in the lower-right section denotes ATE’s increase in IV but decrease in DV where ATE participates in unproductive work. Quadrant in the upper-left section symbolizes decrease in IV but increase in DV in consequence of factory improvement activities. Quadrant in the lower-left section illustrates both decrease in IV and DV proving that ATE is shut down. Analysis shows positive linear PT-PY, negative linear ET-PY, while both IT-PY and RT-PY graphs as extremely erratic. Judging on the results, cumulative ATE time characteristics can be comprehended, which provide some clarity in predictable equipment performance for support maintenance prioritization and task management, and for future research directions on prediction capability for equipment capacity improvement. In conclusion, the chaos theory’s phase space diagrams were successfully applied to simulate the chaotic characteristics and unpredictability in equipment performance in guiding maintenance teams to better prioritize maintenance tasks management, and for future research directions, to enable better prediction on equipment capacity improvement.
Keywords:	Chaos Theory, Manufacturing, Modeling Techniques, Phase-Space Diagrams
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text

Title:	AN EFFICIENT LINK STRENGTH CLASSIFICATION SYSTEM FOR SOFTWARE DEFINED NETWORKING USING DEEP LEARNING APPROACH
Author:	THANGARAJ ETHILU, ABIRAMI SATHAPPAN, PAUL RODRIGUES
Abstract:	In this paper, the link strength of each network switch in Software Defined Networking (SDN) environment system is analyzed into either good or bad using the proposed deep learning approach. This proposed method is designed with two modules as feature computation and Convolutional Neural Network (CNN) architecture. The feature computation module computes the intrinsic feature values of each network switch in SDN, and these intrinsic features are trained and classified into either good or bad using the proposed CNN architecture. The performance of the proposed SDN system is analyzed using the parameters precision, recall, accuracy, average detection rate, Packet Delivery Ratio (PDR) and latency.
Keywords:	SDN, Deep Learning, Network, Switch, Precision.
Source:	Journal of Theoretical and Applied Information Technology 31^st August 2022 -- Vol. 100. No. 16 -- 2022
Full Text