		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
January 2021 | Vol. 99 No.02

Title:	DESIGNING AND IMPLEMENTING A SECURED SMART NETWORK THAT CAN RESIST NEXT-GENERATION STATE SURVEILLANCE
Author:	HAITHAM AMEEN NOMAN, SALMAN IMAD SALMAN AL SATARY, OMAR SAMI WASEF AL-QURAINI, MOHAMED ABDULKADER YOUSFI, QUSAY AL-MAATOUK
Abstract:	The vast number of internet services have already become an essential entity in people's lives. Although these increasingly growing services have made communication between people easier, yet they deemed to be a double-edged sword, that might expose people privacy to serious threats like intercepting private messages by hackers and governments. This paper aims to develop and implement a specific encrypted end-to-end encrypted network tunnel that protects the user’s privacy from being violated by any prying eyes. The designed network comprises Nine VPS (Virtual Private Servers), in which each client and server within this network would implement OpenVPN technology. The route through this Network will be determined by a random algorithm. One of these selected OpenVPN servers receives a particular message from the client, it would only recognize the preceding OpenVPN node that sent this message, so that it will disguise the identity of the original sender. The network has shown a high level of anonymity that can protect the identity of its users along with their data from being monitored by third parties. Moreover, the traffic speed will not be affected significantly.
Keywords:	OPENVPN, VPN, Anonymity, Privacy, Internet surveillance.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	ANALYSIS OF SWARM INTELLIGENCE ROUTING PROTOCOLS IN LARGE-SCALE MOBILE AD HOC NETWORKS (MANETS)
Author:	MUHAMMAD AHSAN, SAMMER ZAI, DILEEP KUMAR, ASAD ABBAS, FAWAD ALI
Abstract:	Mobile Ad-hoc Network (MANET) is a network of mobile devices which are connected wirelessly. This network is a self-configuring network as it rebuilds its topology and information in the routing table for exchanging the data packets every time whenever a node either joins or leave the ad-hoc network. Due to the distinct characteristics of this network including dynamic topology, hop-by-hop communication and speedy set-up, MANETs face various issues primarily including routing, security, and clustering. As the use of wireless devices and the wireless networks is going to be increased day by day, so it is required to improve the working of such networks. It is assumed that the framework of mobile networks may be improved by taking inspirations from the biological structures of high-spirited. This study aims to compare Swarm Intelligence based routing protocols specifically Ant-Net and Honeybee-based routing algorithms in MANET that may help the researchers in selection of a routing protocol when working with MANETs. These algorithms work adaptively towards the intelligence behavior of ants and bees which these insects use for searching food from their colonies or hives. Extensive experiments have been performed using Network Simulator 2 (NS2) for a comprehensive analysis and examination of the selected protocols by considering performance metrics including end-to-end delay and throughput.
Keywords:	MANET, AntNet, BeeIP, Swarm Intelligence, wireless network.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	TRANSFER LEARNING WITH VGG16 AND INCEPTIONV3 MODEL FOR CLASSIFICATION OF POTATO LEAF DISEASE
Author:	DEWI ROSMALA, MOCHAMMAD REVALDI PRAKHA ANGGARA, JUNIARTI P. SAHAT
Abstract:	Early diagnosis of plant diseases carried out by experts in laboratory tests is often not applicable for fast and inexpensive implementation. Using deep learning, leaf images are used as data input. Training deep learning models require large, hard-to-come datasets to perform the task to achieve optimal results. In this study, the PlantVillage dataset was used totaling 2700 training data and 300 validation data. Data were trained using 100 epoch iterations using the transfer learning method with the VGG16 and InceptionV3 models. At the top layer of both models, the same MLP is applied to several parameters, namely the size of FC and the dropout rate to compare the model's performance. Based on testing using 150 IVEGRI data, the VGG16 model can generalize data better than InceptionV3. VGG16 by tuning block-3 using parameters 4096x2 and Dropout 0.4 shows the best performance with an average score of 1 precision, an average recall of 1, an average f1-score of 1, and 100% accuracy. Then, with the same parameters, the Inception-v3 model with tuning in the mixed6 inception module shows the best performance with an average score of 0.93 precision, an average recall of 0.92, an average f1-score of 0.92, and an average accuracy of 92%.
Keywords:	Deep Learning, Transfer Learning, VGG16, InceptionV3, Potato Leaf Diseases Classification
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	EVALUATING THE IMPACT OF MULTIPLE LEADING INDICATOR IN FORECASTING NEXT DAY STOCK PRICE WITH LSTM
Author:	ADITYO HIDAYAT, AGUS SIHABUDDIN
Abstract:	LSTM was the preferred choice for financial time series forecasting, whereas fundamental analysis and technical analysis were among the most favorable feature sets. Earlier studies had several suggestions to improve forecasting performance, by using features known to carry information about the future price movement, and features associated with substantial price movements: the foreign investors' trading volume. Overall trading volume and those volumes from foreign investors have been introduced as a leading indicator. However, empirical literatures which examines price-volume relationship using LSTM had not used foreign investors’ trading volume. This study evaluates the use of multiple leading indicators as input, and optimum hyperparameters configurations using LSTM to next day prediction performance. Experiments are evaluated based on 88 stocks in Indonesia stock market, ranging from Jan. 2, 2015 to Dec. 30, 2019. Financial time series forecasting using simple LSTM architecture performs as good as baseline performance with the advantage of fewer computing requirements. Optimum hyperparameters are a single hidden layer, 50 nodes, and ten days of the input window. The highest winning stocks are achieved using feature sets consisting of a lagging indicator (price) and multiple leading indicators (overall trading volume and foreign investors' trading volume). The findings indicate that multiple leading indicators contain predictability factors which can be further explored to improve financial time series forecasting. This study contributes the use of foreign investors’ which improves financial time series forecasting with LSTM.
Keywords:	Financial Time Series Forecasting, Foreign Trading Volume, Stock Market, LSTM
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	ROBUST OPTIMIZATION APPROACH FOR AGRICULTURAL COMMODITY SUPPLY CHAIN PLANNINGG
Author:	NURDIN, BUSTAMI, MARYANA
Abstract:	North Aceh is one of the districts that has great potential in agriculture and plantations. Many agricultural resources have become superior commodities, because most of North Aceh is a commodity producer from the agricultural sector. However, there are several subdistricts in Aceh Utara district that experience a shortage of agricultural commodity supplies, due to the location of their areas along the coast. Therefore, it is necessary to plan management and supply chain management of agricultural resources. The purpose of this study is to create a robust optimization model that is integrated based on artificial intelligence for the distribution network of agricultural commodity supply chains. The stages carried out in this study started from literature review, data collection and analysis, determining parameters and model decision variables, formulating objective functions and model constraints functions, algorithms and model design, implementation and model testing. The results of this study are a mathematical method or model that can be used for the distribution network of agricultural commodity supply chains, so as to minimize supply chain operating costs from suppliers to consumers. This research is expected to assist decision makers and stakeholders in planning and managing agricultural commodities.
Keywords:	Optimization, Supply chain, Agricultural commodities, Decisions, Robust.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	INTERVAL TYPE-2 FUZZY LOGIC USING GENETIC ALGORITHM TO REDUCE REDUNDANT ASSOCIATION RULES
Author:	MAGDA M. MADBOULY, EMAN ABD EL REHEEM, SHAWKAT K. GUIRGUIS
Abstract:	Data mining (DM) is an analysis extensive data in order to gain the novel and hidden information. DM becomes vital to a lot of research domain like soft computing, artificial intelligence, statistics and machine learning. One of the important topics of DM is Association Rule Mining (ARM) in mega databases where it is used to discover frequent itemsets using statistical metrics such as support (Sup) and confidence (Conf) which is an essential process in ARM. Also ARM is practiced to produce association rules (ARs) from frequent itemsets. Such ARs reveal a link between items in the real world. Several algorithms have been submitted to achieve these ARs. However, these algorithms suffer from redundancy problems and a large number of derived ARs, which makes the algorithms ineffective and complicated them for the end users to understand the rules that were created. Because of these motives, this paper uses the type-2 fuzzy association rules mining technique (T2FARM) to achieve frequent itemsets and identify all relationships between items and ARs that achieve minimum support (min sup) and minimum confidence (min conf) in addition to pruning redundant rules. And also adapts genetic algorithm (GA) to improve non-redundant rules derived. Empirical evaluations display that the proposed technique improves redundant rules pruning of DM compared to traditional fuzzy association rules (FARs) and able to improve non-redundant rules by GA.
Keywords:	Association Rule, Apriori Algorithm, Type-2 Fuzzy linguistic, Redundancy of Fuzzy Association Rules, Genetic Algorithm.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	THE REALITY OF INTERNET OF THINGS (IOT) IN CREATING A DATA-DRIVEN MARKETING OPPORTUNITY: MEDIATING ROLE OF CUSTOMER RELATIONSHIP MANAGEMENT (CRM)
Author:	DR. TAREQ N. HASHEM
Abstract:	Internet of things is a word used in many industries and it refers to the spread of devices and programs that have the ability to capture information, record it or send it automatically. Current study aimed at examining the ability of Internet of Things (IoT) in creating a data-driven environment that supports marketing approaches through the mediating role of customer relationship management (CRM). Achieving aim was done depending on quantitative approach, and utilizing a questionnaire which was distributed on (94) marketing managers within e-marketing and advertising organizations in Jordan. Results of study indicated that IoT facilitates the data gathering, classification, and identification for marketers in order for them to be able to target their customers and present better oriented marketing strategies. The fact that CRM highly depends on data appeared to help IoT in presenting marketing opportunities for marketers around the world. Study recommended increasing investments in developing smart applications that are able to tackle the massive amount of data generated by IoT applications and developing personal and relevant customer experiences without being intrusive. Implications of study can be summarized in the fact that Internet of things can be considered as a powerful tool in the marketing industry, but it has just begun to use its potential in order to reach high-quality modeling. The current study can be a source for organizations to make a difference in the marketing industry by realizing the real value that will come from the Internet Things related to machine decision-making and decision-making
Keywords:	IoT, Data-Driven, Marketing Channel, Pop-up Ads, FRID, CRM, Marketing
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	AFCM MODEL TO PREDICT THE LEARNER STYLE BASED ON QUESTIONNAIRE AND FUZZY C MEAN ALGORITHM
Author:	ALBER S. AZIZ, REDA A. El-KHORIBI, SHEREEN A. TAIE
Abstract:	Every learner follows a special Learning Style (LS), which enables him to learn and understand efficiently; it is necessary to discover every learner's behavior and LS to offer him his specialized materials. The success of the E-learning systems comes from the ability to select and recommend the suitable subject contents to the learner. This paper suggested a new adapted technique for the Fuzzy C Mean (FCM) Algorithm named Adaptive Fuzzy C Mean (AFCM). Moreover, this paper proposed a new adapted E-learning model to predict the Learning Style through the process of learning, depending on the suggested AFCM. The suggested model can store the access data of the learner's navigation, finds out the behavior pattern that personalizes every learner, and then offers individualization due to the LS. The analysis of AFCM performance can be performed by the calculation of the two test accuracy; the performance of using the AFCM algorithm in the second test is much better with an overall performance of 88.7%. The AFCM introduced a preprocessing step before the FCM Algorithm to reduce the time and reduced the number of iterations taken by FCM. The proposed model assists the learners for an English course in the Faculty of Computer Science, October 6University, to maximize the E-learning advantage with high performance, in COVID 19 circumference.
Keywords:	Learning Style, Fuzzy C Mean Algorithm, Questionnaire, Adaptive E-Learning, Log File
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	E-GOVERNMENT SYSTEM FRAMEWORK SUCCESSFUL FACTORS
Author:	ALMAHDY ALHAJ SALEH, AHMED RASHID ALKHUWAYLIDEE, MURUGAN THANGIAH
Abstract:	Each government is looking to provide the best services to establish efficiency and quality of performance. This goal could be accomplished by improving the service performance of entire sectors in society. The government of Syria has realized the importance of moving in the direction of information technology. Therefore, E-government initiatives were launched in Syria as part of the country’s overall information technology in the 20th century. Each government sector has since upgraded service performance by having its own websites and E-services application. However, there exist gaps and loose connections among the sectors, which has accordingly tarnished the image of Syrian E-government. This has led to significant questions about the requirement of modification and enhancement of such service. Hence, the purpose of this research is to investiga te and explore the factors that drive the E-government implementation and affect the government performance as well as the government-citizen relationship in Syria.
Keywords:	E-government, Government-Citizen, Syrian E-government.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	CLUSTER ANALYSIS AND SEISMICITY PARTIONING FOR NORTHERN SUMATERA USING MACHINE LEARNING APPROACH
Author:	EVA DARNILA, KERISTA TARIGAN, SUNARDI, FATI GRANTIANUS NAFIRI LAROSA, MARZUKI SINAMBELA
Abstract:	Tectonic activity in the past one year in North Sumatra is quite active as it’s located in seismic region on the fault zone accommodates most of the strike-slip movements associated with the sloping convergence between the Indo-Australian and Eurasian plates. In this case, we used clustering approach to see the potential for earthquakes originating from fault activities in Northern Sumatra recorded by seismic network sensors that have been installed either Broadband type or the new mini region. Northern Sumatra based on the source of earthquake activity can be divided into several segments. The main goal of this study to identify the distribution of the Northern Sumatra inland earthquake based on segment activity using the clustering approach. The result shown that the dominance of onshore earthquakes in North Sumatra varies greatly based on magnitude. The magnitude frequency distribution for the period 2019 and January to June 2020 was dominated by earthquakes with magnitudes below 4. The clustering approach in this study illustrates the classification of magnitude of terrestrial earthquakes in North Sumatra in the categories of minor, light and moderate. In 2019 and January-June 2020 period the dominance of the most sources of earthquake was due to the Aceh Central segment.
Keywords:	Cluster, Machine Learning Approach, Earthquakes
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	A NEW APPROACH FOR SYNTHESIS OF THE CONTROL SYSTEM BY GRADIENT-VELOCITY METHOD OF LYAPUNOV VECTOR FUNCTIONS
Author:	MAMYRBEK BEISENBI, SAMAL KALIYEVA, AIGUL SAGYMBAY, ZHANAT ABDUGULOVA, AIYMKHAN OSTAYEVA
Abstract:	We suggest technique for the synthesis of control systems with the state vector by means of gradient-velocity method of Lyapunov vector functions. Gradient-velocity method of Lyapunov vector functions is based on the presence of a gradient in a control system with a potential function in the form of Lyapunov function. Total derivative of the Lyapunov vector function with respect to time always exists as a negative definite function representing scalar product of the gradient vector and components of the velocity vector expansion in coordinates. In this paper, the synthesis of control systems is provided with the state vector directly from the matrix components of the closed loop system. Meanwhile, the controller synthesis is considered as a method for determining the allowed range of controller parameters to provide desired performance in a closed loop system.
Keywords:	Control system, controller synthesis, system with m inputs and n outputs, gradient-velocity method, Lyapunov vector function
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	SPELLING CHECKER FOR DYSLEXIC SECOND LANGUAGE ARAB LEARNERS
Author:	SAFAA. M. EL ATAWY, HOSNIA.M.M.AHMED
Abstract:	People with dyslexia have a lifetime of a poor spelling problem. Several researchers have tried to solve this problem through spell checkers. However, most of these spell checkers are provided to native language owners and do not take into account second-language learners with dyslexia, especially since most of the mistakes they make real mistakes lead to unintended but correct words. So far, there is no root solution to this problem. This research is proposed a spelling checker (DYS-EnSC) based on n-gram technique, look up dictionary, and Damerau-Levenshtein, To create a list of candidates and choose the most suitable candidate for each misspelled word, to detect and correct misspellings of Arab second language learners with dyslexia. The results of this study are included two parts. In the first part, we focus on comparing the performance of GSC (Microsoft Word (MW), A spell, and Language Tool) with the performance of the proposed spelling checker DYS-EnSC. Standard measures (Recall, Precision, and Accuracy) were used. Results suggest that the proposed DYS-EnSC spelling checker was useful in correcting misspellings of second language learners with dyslexia, achieving an accuracy of 93% in detecting misspellings and corrected about 86% outperforming to MW, A spell and Language Tool. In Section 2 of the results of this study, we focus on how successful students with dyslexia were in correcting their misspellings with and without the proposed DYS-EnSC system. Findings suggest that students could correct 9.3% of their misspellings without DYS-EnSC and 86% with it.
Keywords:	Spell-checker, computer assisted language learning, L2 spelling acquisition, Text processing, Dyslexia, N-gram, Damerau-Levenshtein distance, Spelling detection and correction, Spelling Errors.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	DISCOVERY OF MAXIMAL FREQUENT ITEMSET USING PRIME ALGORITHM
Author:	R.SMEETA MARY, DR.K.PERUMAL
Abstract:	Data mining is the technique of discovering the new patterns in large data sets with reference to various methods at the intersection of statistics, machine learning and database systems. Computer science and statistics are the interdisciplinary subfield of data mining. The overall goal of data mining is to extort information from a data set and renew or reframe the information into a structure. Association rule is a research area in the field of data searching for frequent and using the criteria support to find frequently the items appear in the data and confidence to identify the most important relationships. In focus of this paper is to find maximal frequent itemset using a new algorithm called maximal Frequent Itemset using Prime algorithm. Most of the association rule algorithms are used to find the minimal frequent item set, and then with the help minimal frequent item set derive the maximal frequent item set. But it consumes lot of time. So to overcome this problem a new approach Maximal Frequent Itemset using Prime algorithm is proposed to find the maximal frequent item set directly. The proposed method is efficient in finding the maximal frequent item set
Keywords:	Data Mining (DM), Association Rules (AR), Frequent Itemset (FIS), Maximal Frequent Itemset using Prime algorithm (MFIPA)
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	SPECIFIC FEATURES, REQUIREMENTS, ATTRIBUTES AND METRICS OF SAFETY OF SOFTWARE FOR SPACE PURPOSES
Author:	E.E. ISMAIL, N.K. UTELIEVA, R.Z. MULAEV, T.S. AUELBEKOV
Abstract:	The purpose of the work is to analyze the security features of software for space purposes (SWSP), justify security requirements, determine the main attributes, indicators and metrics of security characteristics. An analysis of the features and requirements for SWSP safety is made. The main objects and threats to SWSP safety have been identified. An attribute model of SWSP safety is proposed, the main attributes are identified and a set of metrics is proposed for a quantitative assessment of the safety level. The results obtained create the prerequisites for the formalization and objective solution of the problem of quantitative assessment of the safety level of SWSP.
Keywords:	Software For Space Purposes Safety, Features, Requirements, Model, Attributes, Metrics
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	THE IMPACT OF VIRAL MARKETING STRATEGY VIA SOCIAL NETWORK SITES ON STUDENTS IMAGE: A CASE STUDY AT PALESTINE TECHNICAL UNIVERSITY-KADOORIE
Author:	KHALID MOHAMMAD OMAR, FADI AHMAD HERZALLAH, MOHANNAD MOUFEED AYYASH
Abstract:	The aim of this study was to investigate the relationship between viral marketing strategies via social network sites and student image at the Palestine Technical University - Kadoorie. This research adopted the perspective of students who had daily use of the university’s portal and official website as well as social network sites, and developed and examined a model that could contribute to scholarly research on information systems and viral marketing. The quantitative method of data collection using a questionnaire survey was used in the current study. Structural equation modelling (SEM) through a partial least square (PLS) software was used for the data analysis. The results revealed that perceived supporting elements, perceived added value, and perceived cost reduction had a significant and positive effect on the student’s image about universities. The most remarkable recommendation was to snowball the use of social network sites in viral marketing. The theoretical and practical implications of this were discussed.
Keywords:	Viral Marketing, Student Image, Social Network Sites, Perceived Added Value, Perceived Supporting Elements, Perceived Cost Reduction, Palestine
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	FOG COMPUTING ARCHITECTURE, BENEFITS, SECURITY, AND PRIVACY, FOR THE INTERNET OF THING APPLICATIONS: AN OVERVIEW
Author:	YEHIA IBRAHIM ALZOUBI, AHMAD AL-AHMAD , ASHRAF JARADAT, AND VALMIRA H. OSMANAJ
Abstract:	To overcome the problem related to cloud computing such as high latency and to increase the efficiency of data processing, Fog computing was proposed and implemented close to IoT devices. This structure helps these devices to meet the requirements of location awareness and low latency, which can not be met by cloud computing. Many benefits, applications, and security and privacy issues were discussed in the literature for Fog computing. This paper provides an overview of all these aspects to provide the reader with a holistic understanding of Fog computing. More focus is given to the security and privacy issues in our discussion since these issues may hinder organizations from implementing Fog computing. The findings of this paper show that a few studies that discussed empirical findings of using Fog computing and many questions related to security and privacy issues are ye to be answered in future research.
Keywords:	Fog computing, IoT, Benefit, Application, Security
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	QCM: QURANIC CITATIONS MANAGER BASED ON NATURAL LANGUAGE PROCESSING TECHNIQUES
Author:	KHALID M.O. NAHAR
Abstract:	Quran is the holy book for all Muslims. It is containing only truths, no suppositions, or uncertain information. In a variety of scientific areas, writers introduce witnesses for their claims or explain their dialogs by citing verses of the Holy Quran. A novel Quranic Citation Manager (QCM) is introduced in this research paper for automatically managing citations from the Holy Quran. The adopted scientific approach is based on Natural Language Processing techniques. The adopted QCM is based on a sliding window technique, and for more accurate Quranic search a context-sensitive error detection and correction are utilized. The citation manager for searching and error correction techniques were employed for referencing unreferenced in-text quotations from the Holy Quran and for preserving the style of a Quranic citation. QCM checks if the text current text is a Holy Quran text, then checks if it is correct or not, and finally if not correct, it will correct it. Experiments reveal that our adopted approach or QCM achieves a 93.95% accuracy rate.
Keywords:	Quranic Citations Manager; Context-Sensitive Error; Quran Searching; Lexically Neighboring Words.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	A DEEP LEARNING CNN MODEL FOR DRIVER FATIGUE DETECTION USING SINGLE EEG CHANNEL
Author:	WAFAA MOHIB SHALASH
Abstract:	Driver fatigue and losing wariness during long driving hours is considered as one of the main road accidents causes. It affects road safety directly. Road safety is a major disquieting problem, since traffic accidents endanger divers, travelers, and everyone in their scope, in addition to the road and vehicle damages. The EEG signal becomes one of the most dependable biological signals utilized to estimate the drivers' drowsiness state, although a multichannel acquiring system must be used to transmit the EEG signal. Wearing a multi-channel headset is not readily accepted by drivers. Many attempts have been done by researchers to reduce number of EEG channels used to detect drivers’ fatigue. The present study proposed utilizing only one of EEG channels signal to estimate driver fatigue state to raise the acceptance of the system and its flexibility. The system starts with receiving the EEG signals, then pre-processing them using filtering and transformed them to color image using spectrogram. After that, the EEGs spectrogram passed to the proposed CNN deep network model to identify them either fatigue or normal fatigue. The present study measured up many EEG channels to identify the most accurate and dependable one to classify driver fatigue. The results indicate that the FP1, T3, and Oz channels considered as the most efficient channels to identify the drive’s state either fatigue or not. They achieved an accuracy of 94.33%, 92.57 and 93% respectively. Therefore, using a single one of these channels and the proposed CNN model will lead to a more robust driver drowsiness/fatigue detection system using EEG signals.
Keywords:	Adam Optimizer, Convolutional Neural Network, Driver Fatigue, Deep Learning, EEG Spectrogram, EEG Signal
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	ASSESSING HUMAN AND ORGANIZATIONAL FACTORS MATURITY EMPLOYING FUZZY ANALYTIC NETWORK PROCESS METHOD
Author:	YOUSRA KARIM, ABDELGHANI CHERKAOUI
Abstract:	The Human and Organizational Factors (HOF) approach consists in identifying and implementing the conditions that favor a positive contribution of operators and groups to safety. But when implementing this approach, companies find it difficult to define their current HOF maturity level and identify the areas that need improvement first. The HOF maturity model suggested in this article aims to support companies during the accomplishment of a successful and safe human performance. It is composed of six factors and their related HOF characteristics described with key questions to facilitate its implementation. The model is applied in a Moroccan cement plant employing the Fuzzy Analytic Network Process (ANP) technique because of the imprecision of human judgements and the consideration of interactions between the factors.
Keywords:	Human and Organizational Factors, Maturity Model, Safety, Fuzzy Analytic Network Process, Improvement.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	COMPUTING PLATFORM ARCHITECTURE FOR MANAGEMENT OF RENEWABLE RESOURCES USING MULTI-AGENTS SYSTEM BASED ON THE CASE BASED REASONING APPROACH
Author:	MOHAMED KOUISSI, EL MOKHTAR EN-NAIMI, NIHAD EL GHOUCH, ABDELHAMID ZOUHAIR
Abstract:	Nowadays, the use of renewable resources has seen a remarkable increase due to economic growth, urbanization, technological developments and the difficulties related to energy availability such as gas, coal, oil, etc. This leads to high energy consumption and overexploitation of these resources. Several studies and research have been carried out to find solutions for the management of these resources, most of these studies do not propose intelligent and dynamic management in real-time of renewable resource consumption. In this article, we propose an architecture of a multi-agent system combined with Case Based Reasoning approach. This system aims to implement a cloud platform to create and simulate renewable resource management models, through a reasoning cycle gathering a set of agents collaborating with each other, to help decision makers anticipate and predict an environmental risk based on models already resolved. We present a first implementation of the architecture of our Multi-Agent System using Jade platform (Java Agent DEvelopment) and the web service integration gateway (WSIG) for a remote invocation of our Agents to expose services provided by them as web services.
Keywords:	Case Based Reasoning (CBR), Multi Agents Systems (MAS), Simulation, Renewable Resources, Web Services Integration Gateway (WSIG), Java Agent DEvelopment Framework (JADE)
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	PARALLEL IMPLEMENTATION OF FORCE ALGORITHMS FOR GRAPH VISUALIZATION
Author:	ABENOV ZHANSULTAN , AUBAKIROV SANZHAR , PAULO TRIGO
Abstract:	In this paper we select some graph generate-and-render algorithms and evaluate their performance. The experimental results ground our proposal of a parallelized version of an algorithm (the Force Atlas 2) and the corresponding performance analysis. Our work resorts to graph visualization tools such as D3.js, jgraph, NetworkX, Gephi, and sigma.js. We analyze how to use those tools, their advantages and disadvantages and compare their performance. Since each of those tools use their own algorithms, we also conducted a comparative review of graph visualization algorithms. We reviewed algorithms such as FA (Force Atlas), FA2 (Force Atlas 2), FR (Fruchterman & Reingold), LinLog and Dijkstra (Dijkstra's algorithm). The different algorithms were experimentally compared on the same data. The experiments enabled to build a performance ranked perspective. The fastest algorithm was chosen, and experiments were carried out to optimize the rate of generation of graph coordinates by introducing parallel computations during the generation of graph coordinates. During the experiments, the best visualization algorithm for Force Atlas 2 graphs was identified and selected. This algorithm was parallelized, and we achieved a relevant speedup ratio around 26.7% and parallel efficiency around 30%.
Keywords:	Graphs, Directed, Non-directed, D3.js, FA, FA2, Jgraph, NetworkX, Gephi, Sigma.js, FR, Dijkstra, LinLog
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	LARGE-SCALE IMAGE EDGE DETECTION USING HIGH-PERFORMANCE COMPUTING CLUSTER
Author:	HARRIS SIMAREMARE, ROZA NOVIANTI, RAHMAD ABDILLAH
Abstract:	The limitation of computational resources for processing large-scale images makes researchers unable to work optimally. PC-Cluster is an alternative as a computing machine on limited resources. This study tested Sobel performance as an edge detection technique on large-scale images using a PC-cluster. The experimental results show that the PC-Cluster can shorten the processing time of the single technique.
Keywords:	Edge Detection, PC-Cluster, Sobel
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	A SYSTEMATIC LITERATURE REVIEW OF PERSUASIVE DESIGN FEATURES UTILIZED BY MOBILE-BASED OBESITY INTERVENTIONS
Author:	YAHYA ALNAABI, NAZRITA IBRAHIM, JASPALJEET SINGH DHILLON
Abstract:	Mobile interventions utilizing persuasive technology represent considerable promise in effecting long-term success against obesity. This study conducts a systematic review of the literature on the persuasive technology features utilized by different mobile interventions geared toward obesity, categorized using an amended Persuasive Systems Design model. Published studies were gathered from the following databases for this study: EBSCOHost Computer & Applied Sciences ACM Digital Library, IEEE Xplore, Scopus, and SpringerLink. Nine mobile interventions collected. The results show that persuasive design features related to Primary Task Support and Dialogue Support commonly supported, while persuasive design features related to Social Support that were less supported. This may indicate that current mobile interventions focus more on individuals, rather than on communities. This study will be useful for developers of mobile interventions geared toward obesity, as it reveals the persuasive technologies used by current interventions to motivate their users.
Keywords:	Obesity, Mobile Interventions, Users Behavior, Persuasive Technology
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text

Title:	SINK MOBILITY MODEL FOR WIRELESS SENSOR NETWORKS USING GENETIC ALGORITHM
Author:	ANAS ABU TALEB
Abstract:	Wireless sensor networks have been an interesting subject of research and have various types of applications in different areas of interest. Thus, enhancing the performance of these network using mobile sinks is one of the major issues and concerns that must be taken into account. In this paper, a new sink mobility model based on using genetic algorithm is proposed. Genetic algorithm is used to construct the path to be followed by the mobile sink in order to collect data form static sensor nodes. Consequently, the mobile sink will traverse the calculated path in order to visit static sensor nodes and collect data. After that, NS-2 simulator is used to simulate the proposed mobility model. Furthermore, the performance of the proposed model was studied using different simulation scenarios and performance parameters.
Keywords:	Wireless Sensor Networks, Genetic Algorithm, Mobility Model, Performance, Sink Node
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2021 -- Vol. 99. No. 02 -- 2021
Full Text