		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 2021 | Vol. 99 No.18

Title:	TREND ANALYSIS OF RAINFALL INVESTIGATION AND ITS IMPACT ON CLIMATE CHANGE IN VELLAR RIVER BASIN AT CUDDALORE DISTRICT OF TAMILNADU, INDIA
Author:	G. NEELAGANDAN , Dr B.KUMARAVEL
Abstract:	Trend analysis is an important process in the determination and analysis of rainfall pattern. In this study, the rainfall and temperature data for daily was obtained from the meteorological department for the years 1986 to 2016. The collected rainfall and temperature data were separated as average monthly, annually and were analysed. The rainfall map of the study area was prepared by the methods of Mann-Kendal (MK) Test and Sen’s method for years 1986-2016 using GIS. To explore spatial patterns of the rainfall and temperature trends over the entire Vellar river basin of Cuddalore district, GIS software easily implemented using GIS environment. Yearly and monthly rainfall trend were analyzed along the Vellar river basin in quantifying aspects as the anomaly of rainfall amounts and the spatial distribution of rainfall data. A monthly average rainfall trend analysis were done for the same period which shows a very high rainfall in the region of Inderavelly and very low rainfall in Chidambaram region. Average rainfall shows a decreasing rainfall trend in the basin during the period 2014-2016, meanwhile the period 2010-2012 result an increasing rainfall trend in the basin. Rainfall trend investigation was carried out seasonally for the period, the trend analysis of seasonal rainfall reveal that the seasonal normal rainfall pattern has been altered from the last two decades. Temperature variations also had an observable effect on seasonal trend which may affect the crop yield. Therefore, the cropping pattern of this region may have chance to change considerably which can lead to poor crop yield. Thus, this trend analysis of rainfall and temperature is essential to investigate the seasonal changes and analyse the cropping pattern to improve crop yield to meet the increasing demands for food.
Keywords:	Rainfall trend analysis, GIS, Seasonal trend, Crop pattern, Vellar River Basin.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	FEATURE EXTRACTION AND CLASSIFICATION OF RAINBOW FISH BASED ON MORPHOMETRIC TRUSS NETWORK BY USING DISCRIMINANT ANALYSIS
Author:	IHSAN JATNIKA, SARIFUDDIN MADENDA, ERI PRASETYO WIBOWO, HUSTINAWATI
Abstract:	Biodiversity is the strength of an ecosystem. Indonesia is a country that has a diversity of ornamental fish species both marine and freshwater ornamental fish. Maintaining its sustainability by identifying its organisms is important. Identification is important because all subsequent work sequences depend on the correct identification results. Identification is looking for and recognizing individual taxonomic characteristics and incorporating them into a taxon. The high diversity becomes its own obstacle in conducting a fast and precise identification. The computer aided of fish’s identification and classification by using image processing technology has been widely carried out. The results of previous studies indicate the identification and classification of the fishes are narrowed only to the stage of distinguishing the characteristics of fish species at the family level. This research tries to identify and classify more deeply to be able to distinguish 3 species in one genus Melanotaenia (Rainbow fish). This study extracts features based on morphometric network truss using distance measurement methods and produces features in the form of the ratio of segment length ratio toward standard length of the Rainbow fish. The learning method used for classification and introduction is the Linear Discriminant Analysis method. The results showed that the distance measurement method can be used to obtain the characteristics of the Rainbow fish based on morphometric network truss, which is independent toward the fish’s size and the magnification of objects in the image. Another result is that the Linear Discriminant Analysis method can produce an accuracy of 70.83% to 75.00% in the classification of Rainbow fish species.
Keywords:	Feature Extraction, Morphometric Truss, Linear Discriminant Analysis, Rainbow Fish
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	COMPARISON OF CLUSTER VALIDITY INDEX USING INTEGRATED CLUSTER ANALYSIS WITH STRUCTURAL EQUATION MODELINGTHE WAR-PLS APPROACH
Author:	ADJI ACHMAD RINALDO FERNANDES, SOLIMUN, FARID UBAIDILLAH, AISYAH ARYANDANI, ABELA CHAIRUNISSA, AISYAH ALIFA, ENDANG KRISNAWATI, ERLINDA CITRA LUCKI EFENDI, NI MADE AYU ASTARI BADUNG, ALIFYA AL ROHIMI, EVA FADILAH RAMADHANI, FATHIYATUL LAILI NUR RASYIDAH
Abstract:	This study wants to compare the Integrated Cluster Analysis and SEM model of the Warp-PLS approach with various cluster validity indices on data on Service Quality, Environment, Fashions, Willingness to Pay, and Compliant Paying Behavior of Bank X Customers. The data used in this study are primary data. The variables used in this study are service quality, environment, fashion, willingness to pay, and compliance with paying behavior at Bank X. The data were obtained through a questionnaire with a Likert scale. Measurement of variables in primary data using the average score of each item. The sampling technique used was purposive sampling. The object of observation is the customer as many as 100 respondents. Data analysis was carried out quantitatively, to explain each of the variables studied, a descriptive analysis was carried out first, then an Integrated Cluster Analysis and SEM analysis of the Warp-PLS approach were carried out with the ward linkage method and the euclidean distance on various cluster validity indices, including: Sillhouette index, Krzanowski-Lai, Dunn, Gap, Davies-Bouldin, Index C, Global Sillhouette, Goodman-Kruskal in this study were used as analysis tools. This research uses R software. Integrated cluster with index C is better for modeling influence between variables than index Silhouette, Krzanowski-Lai, Dunn, GAP, Davies-Bouldin, Global Sillhouette, and Goodman-Kruskal. The novelty in this study is the application of Integrated Cluster Analysis and SEM of the Warp-PLS approach to compare 8 cluster validity indices, namely the Silhouette Index, Krzanowski-Lai, Dunn, Gap, Davies-Bouldin, C Index, Global Sillhouette, Goodman-Kruskal simultaneously
Keywords:	Cluster Analysis, Sem, Warp-Pls, Integration Model, Dummy Variable, Cluster Validity Index
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	PERFORMANCE ANALYSIS OF CHOREOGRAPHY AND ORCHESTRATION IN MICROSERVICES ARCHITECTURE
Author:	HANDI KRISTIANTO, AMALIA ZAHRA
Abstract:	Microservices architecture (MSA) is a system architecture design pattern with an approach that applies applications as a collection of small services. Service composition is combining various services together to provide the solution. There are two methods for the microservice composition i.e., Choreography and Orchestration. Both techniques have pros and cons based on the use case which is being implemented. In the past some researchers have suggested the use cases for which these approaches are suitable, but a quantitative analysis has not been performed thoroughly and did not evaluate the effects of large number of concurrent users and number of service instances on performance of MSA. We perform an extensive quantitative analysis to analyze and quantitatively measure the performance of Choreography and Orchestration in a Saga which consists of several services, with a maximum number of eight services, and to determine the criteria for selecting the Choreography or Orchestration method to be used based on the measured parameters, namely response time, CPU utilization, and throughput. The factors which impact the performance are the number of services, the number of concurrent users, and the number of service instances. Both models are simulated by varying these parameters. It can be concluded that Choreography has a better response time, throughput, and CPU utilization when compared to Orchestration.
Keywords:	Microservices, Database per Service, Saga Pattern. Choreography, Orchestration
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	A PREDICTION OLIVE DISEASES USING MACHINE LEARNING MODELS, DECISION TREE AND NAÏVE BAYES MODELS
Author:	JAFAR DRDSH, DERAR ELEYAN, AMNA ELEYAN
Abstract:	Machine Learning Models as Decision Tree and Naïve Bayes ‘NB’ models are widely used to predict diseases. This paper has used these models to predict olive diseases. It relies on image processing of the olive leaves and predict the type of disease according to the information gathered from different images. Where 2000 images were collected of an olive leaf which is affected by the disease and healthy. The results show that the accuracy of prediction in the decision tree model is 97% and in the NB model it has reached 80%. This idea was inspired by an idea found in disease prediction, such as the Agrobase application, which analyzes and processes images, and then returns to the associated database to analyze and compare the results, and then gives the prediction result. In this research, we focus on the accuracy of prediction and image analysis, where we highlighted the most deadly disease in olives, olive leaf spot disease, so its color was analyzed and open cv was adopted in the Python language.
Keywords:	Olive Diseases, Machine Learning Models, Decision Tree, Naïve Bayes models, Olive Spot Diseases
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	POWER QUALITY ASSESSMENT IN GRID CONNECTED MODE HYBRID MICROGRID WITH VARIOUS LOADS
Author:	M.DEVIKA RANI, P.S.PRAKASH, M.VENU GOPALA RAO
Abstract:	Microgrid plays a vital role to meet reliable and secure energy demands for consumers at various locations. As renewable energy sources are intermittent in nature, the integration of these with power electronic converters leads to various power quality issues. Well-functioning of a microgrid is decided by four key limitation variables voltage, frequency, active and reactive power. Voltage and frequency regulation are the premier control parameters under any operating condition. In Grid connected mode of microgrid, active and reactive power control is required. Various types of loads connected to the power distribution network also affect power quality. In this paper 14-bus, IEEE distribution system is proposed and related power quality issues are analyzed with various loads. The proposed hybrid microgrid is developed using Matlab/Simulink environment.
Keywords:	Power Quality, Renewable energy, energy demand, hybrid Microgrid, and reliability
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	A NOVEL FILTER BASED MULTIVARIATE FEATURE SELECTION TECHNIQUE FOR TEXT CLASSIFICATION
Author:	RAVI KUMAR PALACHARLA, VALLI KUMARI VATSAVAYI
Abstract:	Text classification is a technique of assigning the known class label to the unknown textual documents. This technique assign single label or multiple labels to a specific document based on the content in the document. These techniques are used in various applications such as sentiment analysis, authorship analysis, fake news detection and spam email classification. In the text classification process, the words in the documents are considered as features. The most important words which are having more differentiating power are considered in the representation of a document. Identification of such words or features is a primary step in the classification process. The high dimensionality of data description is a primary issue in text classification. Huge number of features in the analysis not only decreases the performance of classification but also increase the computational time. In this work, a new feature selection technique based on Category specific Feature Distribution without Redundancy Information (CFDRI) is proposed to identify best informative features and eliminating the redundant features. The effectiveness of proposed feature selection technique is compared with existing techniques such as mutual information, information gain, chi square and relative discriminative criterion. The traditional Bag of Words technique is used to designate the documents as vectors. Term frequency and inverse document frequency measure is used to compute the vector value in the document vector representation. Various machine learning algorithms such as Decision Tree, Support Vector Machine, Naïve Bayes, k-Nearest Neighbour, Logistic Regression and Random Forest are used to generate the learned model. Six popular text classification datasets are used in this experiment to train different learning algorithms. The proposed feature selection technique obtained best accuracies for text classification when compared with the popular solutions for text classification.
Keywords:	Text Classification, Feature Selection Techniques, Bag of Words Model, machine Learning Algorithms, Accuracy
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	BUSINESS INTELLIGENCE STRATEGIES IN BUILDING A MODEL THAT INTEGRATES INTELLIGENCE MANAGEMENT, CRISIS MANAGEMENT AND DISASTER
Author:	TAWFIK ZEKI, SABAH TAMIMI
Abstract:	The field of business intelligence and crisis management has now become important issues that the organization must address. The objectives of the research are to define the concepts of business intelligence in crisis management and review and the importance of business intelligence in building important and effective decisions to know the changes of the internal and external environment to find the most important data to reach important and effective decisions. Today we are suffering from a great catastrophe, which is the Coronavirus, which has caused many institutions to fail or significant losses that cannot be overlooked. This paper examines the importance of business intelligence in pre-planning long-term strategies in building a model that integrates intelligence management, crisis management and disaster.
Keywords:	Covid-19, Business Intelligence, Risk Management, Crisis Model
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	ANALYSIS OF FACTORS AFFECTING USE BEHAVIORS OF TOKOPEDIA MOBILE COMMERCE IN DKI JAKARTA
Author:	ALBERT CAHYADI GUNAWAN, SFENRIANTO
Abstract:	Tokopedia, as a large m-commerce platform, is highly targeted by people in DKI Jakarta to fulfill their online shopping needs. This study aims to analyze the factors that influence use behavior in the use of m-commerce with the modification of the UTAUT theory. The variables used are performance expectancy, effort expectancy, social influence, facilitating conditions, and behavioral intention. The number of samples taken was 411 respondents with a domicile of DKI Jakarta. The statistical method used with Smart PLS. The results of empirical analysis show that the variable performance expectancy and effort expectancy does not affect behavioral intention. Tokopedia mobile commerce users are still not satisfied with the use of the application on smartphone users and Tokopedia m-commerce is still difficult to learn because of the use of applications and user interfaces that are still relatively complex which makes it difficult for users to operate Tokopedia m-commerce. In contrast, the variables social influence and facilitation conditions have a significant effect on behavioral intention, and behavioral intention has a significant effect on use behavior.
Keywords:	E-business, E-commerce, M-commerce, UTAUT, Use Behavior, Jakarta.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	CONCEPTUAL DIAGRAM OF AN INTELLIGENT DECISION SUPPORT SYSTEM IN THE PROCESS OF INVESTING IN CYBERSECURITY SYSTEMS
Author:	BERIK AKHMETOV, VALERY LAKHNO, BAGDAT YAGALIYEVA, LAZAT KYDYRALINA, NURZHAMAL OSHANOVA, SALTANAT ADILZHANOVA
Abstract:	The article proposes a structural diagram of the functioning of a DSS in the process of analyzing and choosing a rational (optimal) strategy for investing in cybersecurity systems (CrS) in a dynamic confrontation with the opposing side (hacker). The key functional modules of such a DSS are considered, which contribute to ensuring its continuous and efficient operation. Detailed block diagrams are given for the following key subsystems of this DSS: analysis of the problem, risks and threats associated with insufficient investment in CrS of an informatization object (OBI); the formation of goals and criteria for evaluating the effectiveness of investment in CrS of an OBI; formation of decisions; formation of the decision rule and analysis of alternative strategies for investing in CrS of the OBI. The above scheme provides full-featured decision-making in the process of choosing rational strategies for investing in cybersecurity systems of objects of informatization of any scale, from small companies or enterprises to large OBI. The article describes the results of computational experiments obtained for the online DSS in the process of searching for a rational strategy for investing in CrS of an OBI.
Keywords:	Decision Support System, Investment, Cybersecurity, Object Of Informatization, Subsystem, Block Diagram Of The Algorithm
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	A HAAR CASCADE CLASSIFIER BASED DEEP-DATASET FACE RECOGNITION ALGORITHM FOR LOCATING MISS-ING PERSONS
Author:	ANTHONY U ADOGHE, ETINOSA NOMA-OSAGHAE, KENNEDY OKOKPUJIE, UDUEBHOLO EMMANUEL EDOSE
Abstract:	A countless number of persons, including children, teenagers, adults, and mentally challenged people, go missing every day. Some are victims of kidnap and human trafficking, while others got missing in unfamiliar places. Effectively identifying people has always been a fascinating sub-ject, both in industry and research. The majority of proposed solutions have not considered the possibility of using cameras in public places for detecting the faces of missing persons in real-time. Therefore, this paper presents implementing a Haar Cascade Classifier Based Deep-Dataset Face Recognition Algorithm on cameras to locate missing persons in public and notify law en-forcement of missing persons found. This research study employs the in-depth learning approach using Open Computer Vision to automate searching for missing persons using public cameras, thereby improving security, safety, and reducing the time taken to find missing persons. The im-plemented system is the solution to a closed-set problem where the proposed algorithm assumes a deep dataset gallery of the trained face image of missing persons. The real-time implementation of the trained face recognition algorithm gave an average experimental accuracy of 72.9%.
Keywords:	Face Recognition, Missing People, Haar Cascade Classifier, OpenCV, Deep Da-taset, Rasberry Pi
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	SIGN LANGUAGE RECOGNITION ON VIDEO DATA BASED ON GRAPH CONVOLUTIONAL NETWORK
Author:	AYAS FAIKAR NAFIS, NANIK SUCIATI
Abstract:	Sign language is a very important means of communication for the deaf and the mute. Therefore, it is necessary to automatically recognize sign language by a computer so that non-disabled people can understand the sign language that is used. Many studies on sign language recognition have been carried out, one of which is the sign language alphabet recognition using the Convolutional Neural Network (CNN). However, CNN cannot represent a skeletal data structure that has the graph form. The Graph Convolutional Network (GCN) is a generalization of CNN that can perform feature extraction from graphs in non-Euclidean space. GCN is widely used in action recognition research such as the Shift-GCN method. This study used hand joints position estimated by MediaPipe Hands that shaped like a graph. The graph is processed using the modified Shift-GCN that introduces a shift weighting approach based on the vertices adjacency. The dataset used in this study is hand keypoints extracted from video data of 26 American Sign Language (ASL) alphabets. Based on the experimental results, the proposed method achieved the best accuracy of 99.962%.
Keywords:	Sign Language, Alphabet Recognition, Graph Convolutional Network, Shift-GCN, Skeletal Data
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	PROCESS MINING IN GOVERNANCE, RISK MANAGEMENT, COMPLIANCE (GRC), AND AUDITING: A SYSTEMATIC LITERATURE REVIEW
Author:	JOHAN J.C. TAMBOTOH*, HARJANTO PRABOWO, SANI M. ISA, BONIFASIUS WAHYU PUDJIANTO
Abstract:	Numerous studies increasingly investigate the application of process mining in governance, risk management, compliance, and auditing in response to changing business processes brought about by digital transformation. Audit on business processes is an interesting issue in the process mining literature. This study seeks to specifically map the types, areas, objectives, and frameworks of process mining application in governance, risk management, compliance, and auditing. The mapping process results in the classifications of components and sub-components. We use the systematic literature review (SLR) on the application of process mining in governance, risk management, compliance, and auditing. The SLR approach makes use of 34 papers selected based on the exclusive and inclusive terms and the mapping process related to the research questions. The data extraction results show that the financial domain dominates the research topics. Besides, we identify 6 phases as components and 32 concrete steps or activities sub-components. The SLR findings contributes to future research on the application of process mining to governance, risk management, compliance, and auditing in various research areas.
Keywords:	Process Mining, Governance, Risk Management, Compliance (GRC), Auditing, Systematic Literature Review.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	CONCEPTUAL AND METHODOLOGICAL MODELS FOR DESIGNING WIRELESS NETWORKS
Author:	KISSELEVA OLGA, SAVELYEVA YELENA, DADAEVA IRINA
Abstract:	At the stage of working out design solutions, customers first raise questions regarding the possible volume and speed of information transfer. There is no doubt about the high efficiency of mathematical modeling methods in solving such problems. Unfortunately, the existing tools for modeling wireless networks allow taking into account only certain parameters of traffic and are not able to answer the questions related to its effective management and distribution. This leads to the emergence of the need for new models of control and distribution of traffic in wireless networks, which will be able to provide high quality of service, taking into account the various requirements of applications to the network, which determines the relevance and practical significance of this task. The identified problems and the reasons for their occurrence give reason to consider wireless data transmission as a process where there is a queue and a processing device. Accordingly, to model the control and distribution of traffic in wireless computer networks, the authors propose to use queue management algorithms and cluster reconfiguration methods. The paper presents the results of modeling the traffic of wireless data transmission in computer networks using the queue control algorithm - parametric identification. This algorithm makes it possible to identify the parameters of the mathematical model of a wireless computer network using only the value of the data transmission window. As a result, there was no overload of network buffers, a decrease in the probability of packet loss, an increase in the efficiency of the distribution of the communication channel, and a guaranteed level of quality of service.
Keywords:	Mathematical Model, Traffic Management, Design, Wireless Networks
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	NEURAL NETWORK ASSISTED VIDEO SURVEILLANCE FOR MONITORING HUMAN ACTIVITY
Author:	ADATI ELKANAH CHAHARI, ABDULKADIR IYYAKA AUDU, SAMUEL NDUESO JOHN, ABDULLAHI ZABAIRU, ETINOSA NOMA-OSAGHAE, KENNEDY OKOKPUJIE
Abstract:	A video surveillance system is a useful tool for observing and monitoring human activities in such a way that guarantees protection against risks and danger from within or from the immediate environment. The video surveillance system is already existing technology, which is simply a recording facility. In this study, the surveillance system can record video in real time and transmit it to an existing parameter that then feeds it to an intelligent approach to recognize the human activity in the recorded video. This model consists of a video surveillance system with feature vector of human beings and trained using Artificial Neural Network (ANN) algorithms (Normal and Abnormal). The model was then used to classify human activities such as hand waving, running, jumping, walking, boxing and other environment events. The pre-processing step uses a continuous stream of live AVI video format with a frame rate of 25/30 frame per seconds and a collective total number of frames as 600fps. This work consists of one normal scenario with four activities of dataset with a recognition rate of 98.5%, six abnormal activities from KTH dataset with a recognition rate of 90.8% and five abnormal activities from Weizmann dataset with a recognition rate of 83.2%. selected to evaluate the performance of the model in an indoor environment. The result obtained was 90.8% accurate.
Keywords:	Neural Network; Video Surveillance; Human Activity
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	MODELING AND SIMULATION OF THE EVOLUTION OF THE CORONA VIRUS PANDEMIC IN A CONTEXT OF MIGRATION
Author:	SALMA CHABBAR, MOHAMMED BENMIR, JAAFAR EL KARKRI, KHALID BENSAID, RAJAE ABOULAICH, CHAKIB NEJJARI
Abstract:	The present article deals with a COVID-19 propagation system. A new compartmental model is established. Migration is allowed into the population. We establish the basic reproduction number and proof that it is an increasing function of migration rates. The final size relation has been determined in the case of closed population. Moroccan data are used in order to compute the parameters of the proposed model. Principal epidemiological results have been compared in the presence and absence of migration using a simulation algorithm based on the dynamical systems approach on the one hand, and the multi-agent approach on the other hand. Both approaches have been implemented using NetLogo. The study, under the two approaches, has proven that migration causes a diminution of the timing of the general infection and the symptomatic peaks. It causes also an augmentation in the maximum values of the general infection and the symptomatic prevalences. The model provides a quantitative illustration of migration influence on disease spread in populations and proposes a practical hybrid framework that will be useful in analyzing and controlling many case studies of COVID-19 spread.
Keywords:	COVID-19 spread, Compartmental models, Ordinary differential equations, Multiagents simulation, Migration.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	A SURVEY OF SOCIAL ENGINEERING ATTACKS: DETECTION AND PREVENTION TOOLS
Author:	NOOR AMMAR ODEH, DERAR ELEYAN, AMNA ELEYAN
Abstract:	Rapid, technological advancements have facilitated communication between people and made sensitive information available via networks and social media platforms, which may not be fully protected, facilitating the occurrence of violations and threats via social engineering attacks. The aim of social engineering attacks is to deceive people and corporate workers into revealing their sensitive information such as passwords and usernames, as well as spreading malware. It is easier for criminals to exploit humans' natural tendency to trust rather than using technology and software. Therefore, social engineering attacks are considered one of the most dangerous attacks that violate the privacy and safety of individuals and organizations. The basic principles of social engineering attacks, their stages of implementation, classifications and types, as well as methods and procedures for reducing these attacks, are covered in this study.
Keywords:	Social Engineering Attacks, Phishing, Pretexting, Tailgating, Scareware, Pop-Up Windows, And Quid Pro Quo.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	STUDY OF THE PRINCIPLES OF ERROR CORRECTING CODE IN A MULTIPATH COMMUNICATION CHANNEL WITH INTERSYMBOL INTERFERENCE
Author:	MANARA A. SEKSEMBAYEVA, NURLAN N. TASHATOV, GENNADY V. OVECHKIN, DINA ZH. SATYBALDINA, YERZHAN N. SEITKULOV
Abstract:	The growth of modern wireless communications has increased the demand for high quality and reliable data services. The purpose of this article stands for a review of the principles and techniques of error correcting codes (ECC) and a study of their practical application to combat intersymbol interference (ISI) in multipath channels. A DVB-T system with MIMO technology developed in the Matlab/Simulink environment is introduced and analyzed. The bit error rate (BER) of the additive white Gaussian noise (AWGN) channel and an ISI-influenced multipath Rayleigh attenuation channel is measured and discussed. The method based on a DVB-T receiver-transmitter with MIMO technology provides a higher quality and speed of data transmission in comparison to a DVB-S2 system with MIMO. Other ways to improve the quality of data transmission are offered, including size and type converters, amplifiers, and gain normalization. Images are transmitted through the system that includes a Rayleigh channel and an AWGN with different signal-to-noise ratio values (SNR, dB) and different gain values. The BER graph is obtained; the results are discussed and compared with similar works. The system can be used for transmission of radiological images (such as computed tomography or magnetic resonance imaging) of high quality and high resolution to remote healthcare workers using a wireless network.
Keywords:	Intersymbol Interference, MIMO, BER, PSNR, AWGN, SNR, Rayleigh Channel, LDPC Code, BCH Code, Amplifier, Eye Diagrams
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	AN EFFICIENT QOS MANAGEMENT AND MONITORING FRAMEWORK FOR CLOUD COMPUTING
Author:	S.BEGHIN BOSE, DR.S.S.SUJATHA
Abstract:	Cloud services provide various types of pay-per-use computing services to cloud consumers. However, Cloud Service Providers (CSP) are not always able to offer the service agreed in the Service Level Agreement (SLA). The performance of the cloud services depends not only on the CSP but also on the system performance and network bandwidth of the cloud consumers. As a result, sometimes even a good cloud service may not be able to provide a better service to the cloud consumers. Consequently, client-level system monitoring and QoS management is a significant research problem in cloud computing. In this research, propose a QoS management and QoS monitoring framework for cloud computing. In this innovative architecture, the management framework recommends the SLA guaranteed cloud service to customers, and the monitoring framework monitors cloud consumers' system performance and network bandwidth. Through this proposed system, SLA violation and cloud consumer migration can be effectively prevented. Besides, the performance of cloud computing can be improved multiple times. The experimental study shows that this strategy gives a highly adaptable model of customer satisfaction. Additionally, the results demonstrate significant increases in client-side QoS parameters such as latency, response time, and throughput.
Keywords:	QoS, Cloud QoS Management, Fuzzy Logic, Cloud Computing, Service Level Agreement.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	A STUDY ON ECG SIGNALS FOR EARLY DETECTION OF HEART DISEASES USING MACHINE LEARNING TECHNIQUES
Author:	RAVINDAR MOGILI, Dr.G.NARSIMHA
Abstract:	Early detection and treatment of heart disease can significantly reduce mortality worldwide. Heart disease often leads to malfunctioning of heart, resulting in an abnormal behavior that can be captured in ECG called as arrhythmia. As few types of arrhythmia are life threatening and others are not, it is very important to detect the arrhythmia type correctly from ECG. But it is a complex process because little variation in ECG can change the arrhythmia type and also need human expertise to diagnose it correctly. So, utilization of machine learning techniques is essential. In this paper we discussed about various machine learning classifiers including variants of Artificial Neural Networks (ANN), Support Vector Machines (SVM) and others used in arrhythmia identification process along with their performance. In addition, we also discussed ECG signal preprocessing methods including noise reduction and feature extraction techniques.
Keywords:	Early Prediction, Heart Disease, Arrhythmia, ECG Signal, Machine Learning, Preprocessing, Denoising Technique, Feature Extraction, Support Vector Machine, Neural Networks
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text

Title:	BOND GRAPH MODEL – INTELLIGENT ONLINE DIAGNOSTICS FOR EDUCATION
Author:	MUSTAPHA EZZAKI, YOUSSEF FAKHRI, SAAD ENNIMA, HASSNAE EL MORTAJI, MOHAMED JOURANI, JAAFAR ABOUCHABAKA
Abstract:	Nowadays, the control of physical systems is the result of many steps, from design to implementation, modelling and analysis, Especially in the field of education and innovation. It is often necessary to know in advance the performance of the system under study and in this case a mathematical model is more than useful. For economic and performance reasons, it is often necessary in certain situations to have a precise representation of physical phenomena, which leads to complex models and the mathematical tools are not always adapted to the models obtained. For several decades, the most exploited representation has probably been the state representation, or an extension of this form for non-linear models. For some time now, the algebraic approach has been used to discover other characteristics of the models, or at least a new interpretation of properties well known to automaticians. However, these techniques are difficult to use for the uninitiated, and the representation by a link graph model allows to reconcile all the theoretical concepts, which are necessary in the different design phases. Some analysis techniques for design are proposed by bond graph modelling for linear models, but can be quite easily generalised for more general models. In this paper, the bond graph tool proves its intelligence in the implementation of monitoring systems, and in particular an intelligent design support. The causal properties of the bond graph allow to analyse the necessary monitoring conditions before and after the design to generate diagnostic algorithms in a generic way. The following approach is illustrated on a DC motor.
Keywords:	Diagnosis, Bond graph, Intelligence, Education, Implementation.
Source:	Journal of Theoretical and Applied Information Technology 30^th September 2021 -- Vol. 99. No. 18 -- 2021
PDF Full Text