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

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

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

Journal of Theoretical and Applied Information Technology
July 2021 | Vol. 99 No.14

Title:	THE MODERATING EFFECT OF INFORMATION TECHNOLOGY ON THE RELATIONSHIP BETWEEN AUDIT QUALITY AND THE QUALITY OF ACCOUNTING INFORMATION JORDANIAN AUDITORS PERCEPTION
Author:	DOAA SHAISH ABABNEH, ALI MAHMOUD ALRABEI
Abstract:	This study aimed to explore the Moderating Effect of Information Technology on the Relationship between Audit Quality and the Quality of Accounting Information. Jordanian Auditors Perception. To achieve that the researcher designed a 47-items questionnaire distributed to 190 questionnaires, out of 190 questionnaires distributed only 161 were returned. Nine of these questionnaires were excluded because they were invalid, the remaining 152 questionnaires yielded 80% responses rate. The data was analysed through the SPSS, to find the Moderating Effect of Information Technology on the Relationship between Audit Quality and the Quality of Accounting Information. “Jordanian Auditors Perception”. Multiple regression analysis has been used. This study found a moderating effect of information technology on the relationship between audit quality (audit firm size, audit fees, contact with international auditing offices, and compliance with international auditing standards) and the quality of accounting information (relevance and faithful representation).
Keywords:	Information Technology, Audit Quality, Quality of Accounting Information, External Auditor
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	ANALYSIS OF SOCIAL MEDIA AS BUSINESS STRATEGY DURING PANDEMIC
Author:	TANTY OKTAVIA , FANNY CLAUDIA , CINTHIA SABRINA YULANTHARI KARUH , BRANDON JULIO THENARO , JAMESON HANDOKO , LUISE ANTHONUA ALKINS, NATALIA
Abstract:	This research was conducted to examine the influence of social media, consumer engagement and consumer purchase intention in order to find out the most effective social media strategies and platforms to established online business. This study uses questionnaire that involved 125 social media users in Indonesia. The method used is a quantitative approach that focus to define descriptive result from the phenomenon. The results showed that social media had a significant influence on the customer purchase intentions and consumer engagement exclusively in the certain brands. According to the results of this study, it can be concluded that to start establishing online business have to pay attention to the social media platform that will be used because it will affect consumer purchase intentions and consumer engagement.
Keywords:	Social Media, Customer Purchase Intention, Business Strategy, Customer Engagement
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	A CLASSIFICATION MODEL TO IDENTIFY PUBLIC OPINION ON THE LOCKDOWN POLICY USING INDONESIAN TWEETS
Author:	ARMINDITYA FAJRI AKBAR, ARIS BUDI SANTOSO, PRABU KRESNA PUTRA, INDRA BUDI
Abstract:	The spread of the Pneumonia Coronavirus Disease 2019 (COVID-19) or Corona virus has affected several industrial sectors in Indonesia, particularly in the tourism and economy sector. Corona virus has been declared by the World Health Organization (WHO) as a pandemic that has spread to various parts of the world including Indonesia. In this regard, the Government of the Republic of Indonesia then declared the Corona virus as a non-natural national disaster. The Case Fatality Rate (CFR) of the Corona virus is 8.37%, placing Indonesia as one of the countries with the highest mortality ratio in the world. Currently, the Government of Indonesia has not implemented a lockdown policy, but there are some people who deplore the government's firmness in imposing the policy and there are also those who support the government for not making the lockdown status decision. Therefore, the lockdown is still a debate in the public. This can be read on social media Twitter, where many people express their opinions about the lockdown policy in Indonesia. Based on this polemic, this research has obtained a classification model that can differentiate between pro and contra tweets on the lockdown policy topics using Indonesian tweets. By using the Bernoulli NB algorithm as a classification model, an optimal value with the highest f-measure score of 88,57% was obtained. This model can be used to assess the effectiveness of communication in implementing lockdown policy to slow the spread of COVID-19 because it can identify public opinion about the trends in supporting or rejecting the lockdown policy.
Keywords:	COVID-19, Lockdown, Sentiment Analysis, Supervised Learning, Text Classification
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	ECG SIGNAL CLASSIFICATION FOR ARRHYTHMIA DETECTION USING DEA AND ELM
Author:	SUMANTA KUILA , NAMRATA DHANDA, SUBHANKAR JOARDAR
Abstract:	The electrical mobility of the human heart is represented by the Electrocardiogram signals. In the modern years the automatic classification of ECG signals has great significance as the cardiologists and the technicians take the decision on heart disease based on automatic classification. The goal of the work is to optimize the total number of hidden neurons by using DEA ( Differential Evolution algorithm ) and ELM (Extreme Learning Machine) algorithm, which makes the classification of the ECG signals with high rate of accuracy. The extreme learning machine is an application of single feed-forward Neural network whose performance depends on weight, activation function and threshold value of the modeled data. The Pan-Tompkins technique were used here to obtain different characteristics of the ECG data, mainly works with the QRS complex of the ECG signals. The ventricular depolarization is maintained by QRS complex where PR period, ST period, QT period are used to analyze the characteristics properties of the ECG signals. A series of filters are applied here to remove the background noise from the ECG signals which makes quick heart depolarization to get adaptive thresholds to identify the peaks of the signal. The ECG samples were simulated with ELM and then the DEA algorithm was used to optimize the problem for better classification of the ECG data. The performance of the classification was measured and it was compared with other related works. In this work the total accuracy was 96.027% where different numbers of hidden neurons were taken (maximum up to 160 ) which was tested with conventional ELM.
Keywords:	Machine Learning , Differential Evolution algorithm, Extreme Learning Machine, Pan Tomkins , Electrocardiogram, Arrhythmia.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	METHODOLOGY FOR ASSESSING THE EFFECTIVENESS OF MEASURES AIMED AT ENSURING INFORMATION SECURITY OF THE OBJECT OF INFORMATIZATION
Author:	LAKHNO V. , AKHMETOV B. , MAZARAKI A. , KRYVORUCHKO O. , CHUBAIEVSKYI V. , DESIATKO A.
Abstract:	The article analyzes publications on the evaluation of investments in information security (IS) of objects of informatization (OBI). The possibility and necessity of obtaining the necessary data have been substantiated, contributing to a reliable assessment of the effectiveness of measures aimed at increasing the company’s IS. In the study process, the modelling methods have been used. A methodology is proposed for calculating indicators from investment activities in the context of increasing IS metrics of OBI. A specific example of such simulation is described. The proposed methodology provides an assessment of the damage prevention from a cyber-attack. The amount of the damage prevention from a cyber-attack is taken as a basic indicator for calculating the economic effect of investing in information security tools (IST). The performed simulation modelling allowed taking into account the relative uncertainty of the real situation with IS of OBI. The conducted study will help practitioners in the field of IS to obtain informed decisions to increase the efficiency of investment projects in the field of IS for OBI, using the approach outlined in the study. Unlike the existing ones, the proposed methodology takes into account both direct and indirect factors of investment projects in the field of IS of OBI. The obtained research results make it possible to expand the tools of information security analysts in the synthesis and analysis of information security contours of objects of informatization of any scale.
Keywords:	Information Security, Information Protection, Uncertainty, Investment Process, Methodology, Damage Prevention
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	THE APPLICATION OF MACHINE LEARNING APPROACH TO ADDRESS THE GPV BIAS ON POS TRANSACTION
Author:	MUJIONO SADIKIN, PURWANTO SK, LUTHFIR RAHMAN BAGASKARA
Abstract:	Each transaction always produces junk data or bias data either due to errors or intentions. The junk data volume is always increase day by day, mainly in the using of public and free to use applications. Junk data is a disruption in every decision making which can cause the material or immaterial losses. This kind of problems are also occurring in the Qasir.id application, a POS application developed by PT. Solusi Teknologi Niaga for MSME entrepreneurs in Indonesia. In the company case, the junk data of POS transaction causes a poor quality of GPV (Gross Payment Value) information. The article presents the results of study in the POS transaction junk data handling. The junk data handling is performed by to validate three machine learning techniques and to deploy the best model in the company's Business Intelligence (BI) system. Based on the result of qualitative and quantitative evaluations, it is shown that the proposed approach provide a significant contribution to the company's decision-making process. The evaluation applied to the operational data sample reveals the accuracy score in the handling of junk data is 0.96 in precision, 0.73 in recall value, and the f1 score is 0.831. Whereas the qualitative evaluation based on users feed back of two-month operation indicates that users were greatly assisted in decision-making regarding the GPV.
Keywords:	Employee Appraisal, Additional Salary, Employee Performance, Decision Support System, FIS, Fuzzy Logic
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	REAL-TIME HUMAN FACE ANONYMIZATION SYSTEM FOR SERVICE ROBOTS
Author:	GERMAN ROJAS, JASON MARTÌNEZ, FREDY MARTINEZ
Abstract:	Like any other computer system, robots are susceptible to security problems that could lead to unauthorized disclosure of private information. While it is true that these systems in critical applications (industrial or medical level for example) can result in great damage to equipment and people, in addition to the costs involved with data leakage, domestic applications, in particular service robots, cannot be left aside. A security breach in a system that stores private information puts the security of all individuals in a family group at risk. The communication capabilities of these systems can make them targets for attacks that can seriously compromise the privacy and security of their users. As a sensor system for human environments, it is normal for these robots to incorporate cameras as an important element of their interaction system, similar to the way human eyes do. This research presents an anonymization strategy for all video signals captured by a home service robot as a way to reduce unnecessary personal information captured by these cameras and to increase the confidence of use by users. We propose the use of an algorithm capable of identifying and distorting faces in real-time from the video input of the robot. This process is performed with the original video signal ensuring that no human face is digitized by the robot. The algorithm was evaluated on the ARMOS TurtleBot platform for different operating conditions, demonstrating more than sufficient performance for general robot applications. This strategy will be combined in the future with other systems under investigation by the research group related to source encryption protocols
Keywords:	Anonymization, Human face, Personal information, Privacy, Real-time, Service robots
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	A MODEL FOR RISK ANALYSIS IN THE INDUSTRIAL INTERNET OF THINGS
Author:	AMIROVA AKZHIBEK , TOKHMETOV AKYLBEK
Abstract:	With the rapid development of the industrial Internet of Things (IIoT) the need to respond quickly, detect and prevent intrusions has arisen. IIoT networks have special functions and face unique challenges in defending against cyber attacks. These problems are especially relevant as the predicted growth of IIoT users. Risk assessment is an important part of the process of information security systems, including industrial complexes. In this document, we present a practical information security risk assessment model. This model is based on simple additive weighting method and fuzzy logic. Fuzzy logic is a suitable model for risk assessment and represents practical results.
Keywords:	Industrial Internet of Things (IIoT), Simple Additive Weighting Method (SAW), Security, Threats.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	WORD LEVEL ENGLISH TO HINDI NEURAL MACHINE TRANSLATION
Author:	NOMI BARUAH, AURANGZEB KHAN, DHANOJIT RAY, SAHID AFRIDI, RANDEEP BORAH, RAKHEE D. PHUKAN, ARJUN GOGOI
Abstract:	In todays world English is considered as important language across the Globe. Many resources are available in English language on the internet, which is not easily understandable , so its necessary that English language need to translate into the local languages of India so that the people of India can easily understand the enormous amount of English resources. As the information is of large amount so its not possible to keep translating things from one language to another manually. Thus its very important to translate the given text or information from one language to another automatically and effectively. This paper discusses about Neural Machine Translation(NMT) for converting English text to Hindi text. Neural machine translation(NMT) is one of the most recent and effective translation technique amongst all existing machine translation systems. In our experiment we have tested using 4 different model on OPUS, IIT-Bombay English-Hindi parallel corpora contains nearly 1084157 sentences and we have been able to get quite good results in terms of BLEU score while comparing to other available English to Hindi Neural Machine Translation model.It has achieved satisfactory score of 21.07,22.08,23.45 and 23.44 (in terms of percentage) for 2-layer, 4 Layer, 2 Layer (Bidir) and 4 layers (Bidir) LSTM respectively. Also,the accuracy of the system is compared with 4 existing machine translation system available in the internet for English to Hindi.Human evaluation of the systems is done based on five parameters and our system outperforms all the others.
Keywords:	BLEU Score,Byte Pair Encoding, English-Hindi, Machine Translation, NLP, NMT.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	PREDICTION OF EPILEPTIC SEIZURE CLASSIFICATION USING THIRD-ORDER CUMULANTS AND SPARSE AUTOENCODER
Author:	G. BUCHANNA, P. PREMCHAND, A. GOVERDHAN
Abstract:	Epilepsy is one of the serious neurological diseases in the world. Indeed, early detection of epileptic seizure will extend the life span of epileptic patients. In this regard, a lot of efforts has been done to predict epileptic seizures based on electroencephalography (EEG) signals. In literature, there are many feature-based seizure classification methods quoted. No method is proved perfectly in capturing a standard set of feature with the dynamics of signals. In this research, a new strategy is proposed based on ant colony organization (ACO) pro-processing and third-order cumulants (ToC) for capturing the perfect feature set. Besides second-order statistical features also derived for pre-processed EEG signals. All these features are inputted for a sparse encoder which selects optimal features to obtain good accuracy. This paper describes an automated seizure classification into a focal and non-focal epileptic seizure. The proposed strategy experiments for different labels and all cases shown stunning performance in seizure classification into focal and non-focal EEG signals, and it will be useful for neurologists for rapid and robust prediction of epileptic seizure surgery.
Keywords:	Electroencephalography, Epilepsy, Focal, Non-Focal, Sparse Encoder, ACO, ToC
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	FACTORS AFFECTING THE ADOPTION OF CLOUD COMPUTATIONS ON COMPANY PERFORMANCE
Author:	ANDERES GUI, KAISAR YUWANA PANGESTU, FRANSISCA HANITA RUGOSWANTO, AHMAD AFIF AHMAROFI, SURYANTO
Abstract:	Industry 4.0, while not fully implemented, has seen many companies starting to strategise their future business process. Companies have started to look at Industry 4.0 technologies that companies can adopt to remain competitive. One of the widely available technologies is cloud computing, which helps companies perform data storage and computation. This study aims to investigate the effect of cloud computing adoption by describing the TAM-TOE model on the factors that affect cloud computing to improve company performance. The variables tested in this study consists of independent variables, namely Technology Context (TC), Organizational Context (OC), Environment Context (EC), Perceived Usefulness (PU), Perceived Ease of Use (PE), Attitude (A), and Behavioral Intention (BI). The sample used in this study was taken using a cross-sectional design method where 127 respondents were selected as samples. The analytical method, in this case, used multiple linear regression analysis using SPSS version 26 statistical software. The results showed that TC, EC, PU, and A affected company performance, but OC and PE did not affect. The result shows that companies agreed that cloud computing is practical and can improve the company's performance. However, the respondents agree that the current cloud computing technology will disrupt the company's business performance and migrating to cloud computing is challenging. This study recommends that the government should introduce policies such as tax incentive and encourage collaboration with other developed nations to foster the adoption of cloud computing and other Industry 4.0 technologies.
Keywords:	TAM, TOE, Organizational Context, Behavioral Intention, Cloud Computing
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	METEOROLOGICAL DATA ANALYTIC SYSTEM: DESCRIPTIVE AND PREDICTIVE ANALYSIS
Author:	DANA SHAHIN, MOHAMMED AWAD, SALAM FRAIHAT
Abstract:	Weather can be described as the status of the atmospheric conditions at a specific time. on the other hand, climate is the weather’s status over a long period. both are very important for people’s life management on multiple levels. Weather prediction is a complicated process that requires input from experts. This paper describes a weather business intelligence solution starting from requirements gathering and analysis all the way to the creation of a dashboard with weather prediction capabilities based on a machine learning technique to fulfill the business needs. In this paper, we used Long Short-Term Memory (LSTM) to predict the weather with high accuracy.
Keywords:	Weather Prediction, Weather Dashboard, Weather OLAP, Temperature Prediction, Climate Change Indicators, LSTM, Data Architecture, Weather Analysis, Power BI, SQL Data Tool.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	P-BBA: A MASTER/SLAVE PARALLEL BINARY-BASED ALGORITHM FOR MINING FREQUENT ITEMSETS IN BIG DATA
Author:	ALIYA NAJIHA AMIR, HITHAM SEDDIG ALHASSAN ALHUSSIAN, SALLAM OSMAN FAGEERI, ROHIZA AHMAD
Abstract:	Frequent itemset mining is a data mining technique to discover the frequent patterns from a collection of databases. However, it becomes a computational expensive task when it is used for mining large volume of data. Hence, there is a necessity for a scalable algorithm that can handle bigger datasets. Binary-based Technique Algorithm (BBT) can simplify the process of generating frequent patterns by using bit wise operations and binary database representation. However, it still suffers with the problem of low performance when dealing with high volume of data and a minimum values of support threshold to generate the list of frequent itemset patterns. This is due to its design which run in a single thread of execution. This research proposed a Parallel Binary-Based Algorithm (P-BBA) to solve the mentioned problem. The proposed algorithm is designed with collaborative threads which simultaneously work together to generate frequent itemsets in a big data environment. A master/slave architecture is used to fit the algorithm with distributed computing platform. The obtained results showed significant reductions in execution time when using the proposed parallel binary-based algorithm.
Keywords:	Big Data mining, Distributed Framework, Frequent Itemsets Mining, Parallel Frequent Item Mining
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	A REVIEW ON IMPACT OF INTERNET OF THINGS (IOT) FOR MODERN ELECTRIC POWER SYSTEMS
Author:	HEMANTH SAI MADUPU, B.BADDU NAIK, B. BALA SAIBABU
Abstract:	Advancement of technologies in electric power systems (EPS) gives a clean energy to maintainable worldwide economic development. Internet of Things (IoT) is at the cutting edge of this change conferring abilities, for example, data monitoring, situational decisions and insight, control, and cyber security to change the current EPS into digital empowered EPS, which is more productive, secure, solid, versatile, and practical. Furthermore, digitizing the electric power environment utilizing IoT improves resource permeability, ideal administration of circulated generation, disposes of energy wastage, and makes reserve funds. IoT essentially affects EPS and offers a few chances for development and improvement. There are a few difficulties with the arrangement of IoT for EPS. Feasible arrangements should be created to overcome these difficulties to guarantee the proceeded with development of IoT for EPS. The progressions in computational knowledge capacities can advance a shrewd IoT framework by imitating neural network system with psychological calculation, streaming, and investigation. This paper gives an assesment of the importance, effect, and difficulties of IoT in changing electric power and energy frameworks.
Keywords:	Internet of Things (IoT), Electric Power Systems (EPS), Smart Home Environment, Networking and Security for IoT, Impact of IoT
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	MATHEMATICAL MODELS AND METHODS FOR SOLVING THE PROBLEM OF EVACUATION
Author:	AINUR KOZBAKOVA, ALIYA KALIZHANOVA, FERUZA MALIKOVA, ZHAZIRA AMIRGALIYEV, TIMUR KARTBAYEV, BYRZHAN SHARIPOVA, ZHALAU AITKULOV, AYGERIM ASTANAYEVA
Abstract:	The problem of evacuation of people from closed premises such as universities, colleges and schools is considered. The peculiarity of this work lies in the formation of an integrated approach for organizing the evacuation process in peacetime as a training for an emergency. A conceptual diagram of an evacuation system is proposed that uses heterogeneous sources for receiving and transmitting information about the onset of an emergency. The input and output sources for receiving and transmitting information about the number of people in the building are determined. The main purpose of the system is to form an operational evacuation plan in real time. The optimal solution to the problem of maximum network flow is implemented using a game-theoretic approach. A mathematical model has been developed for the optimal distribution of the flow along the grindshill network with the analysis of the flow formation and the characteristics of the ways of people moving in closed spaces. A game-theoretic approach and mathematical methods of the theory of hydraulic networks for finding an equilibrium state in flow-distribution networks have been developed. An algorithm for solving the evacuation problem using the graph approach is proposed.
Keywords:	Mathematical modeling, graph, method, algorithm, maximum flow, evacuation.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	ANALYSIS OF THE EFFECT OF USEFULNESS, EASE OF USE, AND SECURITY PERCEPTION ON INTENTIONS TO USE THE PAYLATER APPLICATION
Author:	YOHANNES KURNIAWAN, REGA BHATARA, NORIZAN ANWAR, JOHAN
Abstract:	Online trading transactions have experienced rapid development in recent years, both in terms of users, and the number of transactions continues to increase year after year. Paylater, with various innovative features that offer many conveniences, it is believed to increase financial literacy and inclusion for the Indonesian people. This study aims to analyze the effect of perceived usefulness, ease of use, and security on using paylater applications. The data collection method in this research is a survey by distributing questionnaires via google form for the population in the areas of Jakarta, Bogor, Depok, Tangerang, and Bekasi (Jabodetabek). The sampling technique used was purposive sampling, namely paylater users who live in the Jabodetabek area, and snowball sampling in which data were collected in a chain through group messages. We use SmartPLS software for analysis the data and the results of the path coefficient describe only the perceived usefulness, has a significant effect on the intention to use the paylater application. In contrast, the perception of ease of use and security does not significantly affect the intention to use the paylater application. This research shows the results that a person's decision to use a paylater is strongly influenced by their perception of the benefits that the paylater application can provide. It is very natural for someone to choose things that benefit for him.
Keywords:	Paylater, Usefulness, Ease of Use, Security, Intention to Use
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	FORECASTING MODEL OF PRODUCTION AND PRICE OF GRAINS COMMODITY IN CENTRAL SULAWESI
Author:	EFFENDY, DIZZI EVANSYAH, MADE ANTARA, KRISNAYANTI NOLI, M. FARDHAL PRATAMA
Abstract:	Food derives from biological resources, animals, and water, whether processed or not processed, meant as food or drink for human consumption. Food commodities have often been referred to as staples or basic needs of Indonesian people and others. The availability of staples has played a strategic role in stabilizing food security, economic security, and national political stability, leading to the issue of availability of staples receiving very serious attention from the Indonesia government. This study analyzed the best model of production forecasting and prices of rice and corn in Central Sulawesi, Indonesia. The study used the ARIMA method to predict the production and prices of rice and corn. The results of the analysis showed that the best model was the forecasting model of ARIMA rice production (4,0,0) with decreasing production forecast data trends and corn with the ARIMA model (1,0,0) with increasing production forecast data trends. The forecasting model of ARIMA rice price (2,2,0) with decreasing price forecast data trends and ARIMA corn prices (2,2,0) with increasing price forecast data trends.
Keywords:	Forecasting, Grains, Rice, Corn
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	DISCOVERING UNKNOWN BOTNET ATTACKS ON IOT DEVICES USING SUPERVISED SHALLOW AND DEEP LEARNING CLASSIFIERS
Author:	MALEK AL-ZEWAIRI, SUFYAN ALMAJALI, MOUSSA AYYASH
Abstract:	Computer networks constitute the vital artery of the information and communications technology era, allowing heterogeneous devices to communicate and share data. The immense number of Internet-connected devices with unpatched security vulnerabilities makes them susceptible to massive security attacks. Detecting unknown security attacks continues to be a major challenge, as they have been ranked constantly in the top three attack techniques since 2014. In this paper, the researchers aim to study the ability of supervised shallow and deep learning classifiers in detecting unknown botnet attacks on IoT devices. The performance of shallow and deep supervised learning classifiers was studied and compared using a well-known dataset (i.e., the Aposemat IoT-23 dataset). A thorough and extensive experimentation process was conducted (1000 experiments in total were performed), in which 12 unknown attack types and 38 unknown attack subtypes were studied under binary and multiclass classification problem. The results showed that the overall weighted average classification error rate was considerably high (61.46–86.40%), which dictates the importance of finding novel approaches and techniques to detect unknown attacks.
Keywords:	Botnet, Deep Learning, IDS, IoT, IoT-23 Dataset, Unknown Attacks
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	THRESHOLD IDENTIFICATION FOR P2P BOTNET DETECTION USING LOGISTIC REGRESSION APPROACH
Author:	MOHD FAIZAL ABDOLLAH, WAN AHMAD RAMZI W. YA, WARUSIA YASSIN, RIZUAN BAHARON, MOHD FAHMI ARIF
Abstract:	Nowadays, all matters involving communication network that covers various fields such as banking, business, learning, and social media should be monitored as they are exposed to various cyber crimes and aggression committed by the irresponsible. Identifying an appropriate threshold value is essential to differentiate between normal and abnormal P2P network traffic to detect the abnormalities of the botnet behavior. The suitable value of the threshold can minimize the false positive rate of P2P botnet activity and increase the detection rate. Therefore, in this paper, the appropriate static value of the threshold will be identified for detecting P2P botnet. The likelihood ratio tests and classification table were two tests from a logistic regression that will be used to access the fitness of the model. Based on the result, the selected threshold manages to detect around 98% of overall detection. This result is supported by the validation process which also manages to detect 98% of overall detection. Such value has confirmed that threshold value is acceptable discrimination to be used in detecting P2P botnet activity.
Keywords:	P2P Botnet Protocols, Threshold, Logistic Regression, Detection
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	DETECTING OLFACTORY IMPAIRMENT THROUGH OBJECTIVE DIAGNOSIS : CATBOOST CLASSIFIER ON EEG DATA
Author:	MIN JONG CHEON, OOK LEE
Abstract:	Detecting olfactory impairment using an objective diagnosis kit has been a challenge. Recently, machine learning and deep learning models have been used on EEG data with promising results. The goal of our study was to detect olfactory impairment through a machine learning classifier with EEG data. This was done by identifying the important EEG data factors affecting olfactory impairment. Finally, we compared our model to other machine learning and deep learning algorithms in order to identify possibilities for further research. Downsampling and extracting various waves from EEG data were conducted for data preprocessing. Then, an independent component analysis was performed to remove artifacts. Through this processing, a dataset in CSV format was obtained. Next, we built a CatBoost classifier model because it is recent boost model and has high performance for classification. It identified whether a subject had olfactory impairment or not. After training with the CatBoost algorithm, we compared it to different machine learning and deep learning algorithms. The CatBoost model showed 87.56 % accuracy, while other machine learning algorithms such as the random forest classifier, gradient boosting classifier, XG boosting classifier, k-nearest-neighbor classifier, decision tree classifier, Gaussian NB, and logistic regressor revealed 82.22 %, 78.89 %, 78.22 %, 75.78 %, 74 %, 69.78 %, and 41.11 % accuracy, respectively. With deep learning models, which consisted of bi-directional long short term memory, long short term memory and a deep neural network, the performance was 63.11 %, 51.33 %, and 60 %. The CatBoost model showed feature importance, which revealed that the gamma wave on the Cz channel was about 20, which was the highest among the other variables.
Keywords:	Artificial Intelligence, Machine Learning, Deep Learning, EEG, Olfactory Impairment, Diagnosis
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	DATA MINING IN THE PROFESSIONAL EDUCATIONAL ENVIRONMENT USING MACHINE LEARNING METHODS
Author:	AINAGUL AMANGELDINOVNA KABDIROVA, VALENTINA PETROVNA KULIKOVA, VLADIMIR PAVLOVICH KULIKOV
Abstract:	The article deals with the problems of building an intelligent system for organizing course training using machine learning methods. The main idea of the present study is to solve the problem of optimal layout and the presentation rate of the material for the listener to learn the courses by automating the methods of data mining. Machine learning is used to collect and initially process information about the trainees for its structuring, identification of characteristic features, generalization, and sorting. Proper evaluation of this information helps to build a more correct and adequate model of the learning process for subsequent analysis and planning. The authors propose automated mechanisms for organizing a personalized environment in the context of managing the development of professional self-actualization of a specialist based on training models such as the "static" case, loss of qualifications, lost profits, and a dynamic model. The article describes the possibilities of using multidimensional regression analysis in predicting the behavior of the system under study for making managerial decisions and possible risks. The results of the conducted study will be useful for researchers in the field of software design and mathematical simulation, analysts, as well as vocational education teachers – for integrating information data about listeners.
Keywords:	Advanced training, Management, Automation, Data analysis, Dynamic model.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	ANALYSIS AND RESEARCH OF THE SECURITY OF A WIRELESS TELECOMMUNICATIONS NETWORK BASED ON THE IP PBX ASTERISK IN AN OPNET ENVIRONMENT
Author:	MANANKOVA O.A, YAKUBOV B.M., SERIKOV T.G., YAKUBOVA M.Z., MUKASHEVA A.K.
Abstract:	To date, widespread is the connection to the Internet, which is a global public IP network with a large number of IP users and increased requirements for the capabilities of IP networks, using them not only for data transmission, but also for interactive video conferencing, transmission of voice information streams and for other real-time applications. Growth of network resources’ users entails the emergence of a large volume of transmitted information and the problem of reliable, secure data transmission, that is, to the problem of information security. The solution to this problem is the use of encryption algorithms, as well as the choice of the OS server, configuration and settings of the Asterisk software firewall. In this regard, this publication has developed a simulation model of a wireless telecommunications network based on PBX Asterisk software IP consisting of wireless devices -workstations, border wireless router, Asterisk server, IP cloud, Wireshark traffic analyzer and others. Using the NetDoctor utility of the Opnet environment, the security of the configuration of the built simulation model of the wireless telecommunications network based on the PBX Asterisk IP software was checked. To carry out simulation modeling of the developed network, settings of all network equipment are performed and experiments are carried out on it, as a result of which it is established that when using the G711, G729, G726 and G728 codecs, small delays are obtained in the interval Router 1 - IP Cloud - Router 2 when using the G711. The rest of the codecs have low latency values at other network sites. Also, a passive attack was performed on the network based on the Wireshark traffic analyzer to determine the protocols, connection time, IP addresses of the network to study the security of the wireless network. The obtained results are aimed at using them in the design of new networks or their modernization.
Keywords:	IP PBX Asterisk, NetDoctor, Opnet Environment, Wireshark, Wireless Telecommunications Network, Traffic Analysis, Passive Attack, Codec
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	GREEN CELLULAR DESIGN USING AN ADAPTIVE POWER MANAGEMENT REDISTRIBUTION FOR MOBILE COMMUNICATION
Author:	SAIF E. A. ALNAWAYSEH, AMANI. R. AL-ZAGHIBEH
Abstract:	With the advent of the 5G revolution, the demand for wireless access data rates is growing exponentially at a pace where supply cannot keep up with. Similarly, there is an enormous growth rate of telecommunications data. In addition, user behavior is changing towards using more features and apps on their User Terminal (UT). This leads telecom companies to build new infrastructure to meet the rapid increase of resources. Many previous works tackled this problem, but at the expense of many factors such as the Quality of service (QoS) provided to the user, power consumption and CO2 footprint, and the behavior of user such as the user in the loop (UIL) which leads to annoy the user and to make theses solution inapplicable. This research paper proposed a novel solution based on optimizing distribution for the users in order to maximize the network capacity while keeping the same infrastructure and resources. This paper was performed using real network modeling using Matlab. The model used in this paper is according to (IEEE) 802.15.4 Machine Access Control (MAC). Based on the power equations, the received power was calculated, and the users were redistributed automatically according to the proposed methodology. Accordingly, it is found that the proposed solution (automatically redistribution) allows the cells to accommodate the largest possible number of users and thus reduces the possibility of blocking by 43% for 70 users compared with the current solution before applying our algorithm (random redistribution). Therefore, the system is more efficient while maintaining the same resources. The performance evaluation of many system metrics according to the proposed solution was investigated. Power consumption, CO2 footprint, number of assigned users to each cell in each scenario were investigated in addition to reliability and probability of blocking and failure to the system. The QoS provided to the user does not decrease by enabling the service providers to utilize the allocated channels as efficiently as possible to reduce call blocking probability. Also, CO2 footprint and power consumption noticeably reduced by 27% for the same amount of users in comparison with other solutions.
Keywords:	Green Cellular Network, Redistribution Dynamically, Dynamic Cell Allocation, Cell Maximum Capacity, Power Consumption, CO2 Footprint
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	THE INFORMATION TECHNOLOGIES IN THE TASKS OF PLANNING OF SMART CITY DEVELOPMENT
Author:	LAKHNO V., TOGZHANOVA K., KASATKIN D., KARTBAYEV T., USKENBAYEVA R., ALIMSEITOVA ZH., KASHAGANOVA G., BALGABAYEVA L.
Abstract:	The article defines the main tasks and stages of the planning of Smart City development. There was developed a sequence for solving planning tasks. Presented a mathematical formulation of the task of planning of Smart City development. Formalized the main steps for creating plans of the Smart City development. There was considered an example of decomposition in solving the task of ranking factors into a hierarchy and creating a multilayer model for assessing the Smart City development parameter. The energy efficiency of objects is considered as such a parameter and the process of ranking factors is described. It is shown that the use of the proposed methodology makes it possible to streamline, algorithmize and correct the procedure for expert assessment of dissimilar factors and to improve the quality of the results obtained for the formation of the decision-making process during the planning of Smart City development. The use of the methodology proposed in the article will allow you to streamline, algorithmize and adjust the procedure for expert evaluation of various factors and improve the quality of the results obtained in the decision-making process for the development of Smart City.
Keywords:	Smart City Development, Planning, Energy Efficiency
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text

Title:	NEW APPROACH TO CONSTRUCT A NEW ISLAMIC GEOMETRIC PATTERNS USING THE HASBA METHOD
Author:	YASSINE AIT LAHCEN , ABDELAZIZ JALI , AHMED EL OIRRAK
Abstract:	By its beauty and the symmetry of its patterns, Islamic geometric Pattern (IGP) art has always attracted the interest of scientists. These methods to make geometric patterns were analyzed and proposed by several author scientists. In this paper, we present a new method called the ‘Âark method’ to construct new geometric patterns by using the method called “Hasba” (measurement). That is widely adopted by Moroccan artisans. This proposed method, based on the concept of symmetry, allows building numerous patterns by systematic and dynamic processes. Symmetrical patterns are constructed from an asymmetric element called the ‘fundamental region’ by applying reflections and rotations. Compared to the classical ‘Ribbon method’ which will be explained later on, the proposed method is tolerant to construct more than 200 patterns with different visuals. This demonstrates the ability of the proposed method to construct various motifs and can easily be used in a softwere program, for an automatic generation of a large number of patterns without the intervention of the human being, to overcome the problem of limitation of the patterns posed by the craftsmen of Islamic geometric art.
Keywords:	Islamic patterns, Symmetry, Islamic Art, geometric Art, Âark method.
Source:	Journal of Theoretical and Applied Information Technology 31^st July 2021 -- Vol. 99. No. 14 -- 2021
Full Text