		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 Informtion Technology
Feburary 2022 | Vol. 100 No.03

Title:	CHOOSING AN INVESTMENT STRATEGY FOR SMART CITY PROJECTS BASED ON A GENETIC ALGORITHM
Author:	LAKHNO VALERII, ABUOVA AKBALA, SAGYNDYKOVA SHOLPAN, ALENOVA RAIGUL, LAKHNO MIROSLAV, KRAVCHUK PETRO, KRAICHAK YEVHENII
Abstract:	This paper presents a genetic algorithm (GA), which is adapted to solve the problem associated with obtaining a predictive assessment of benefit from different areas of investment in Smart City projects. The application of the proposed GA provides potential investors with predictive assessments of the prospects of the selected investment strategies at the stage of assessing the attractiveness of individual projects related to the development of Smart City. This is achieved by identifying significant growth drivers for the benefit from investment in the Smart City, as well as tracking points of growth and structural changes in the urban economy. The application software was developed based on the GA described in the paper. A series of computational experiments on the selection of rational strategies for investors in Smart City projects was conducted. Based on the data of computational experiments, a conclusion about the operability of the proposed GA in the task of forecasting the attractiveness of investment strategies in Smart City development projects was made.
Keywords:	Investment Strategy; Projects; Smart City; Genetic Algorithm; Decision Support
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	THE IMPACT OF EXPOSURE, ENGAGEMENT & IMAGE TOWARD ATTITUDE THROUGH WEB SERIES ON YOUTUBE
Author:	DEVI YOSITA, RICARDO INDRA
Abstract:	This paper presents an investigation of internet user behaviour particularly in YouTube Platform about the impact of web series – a new emerging format of video entertainment in this digital & social media era. A short web series video of JBL Indonesia – an audio device brand in the series #SebuahEpisodeYangTertinggal was picked to be examined by its viewers. The objective was to examine whether JBL Indonesia has achieved its digital marketing objective through this web series about to the introduction of the truly wireless earphone. Does it help raise the audience's state of mind toward the brand and its newly launched product? A modified model based on previous researches about the impact of online video on the shaping attitude of its viewers was proposed in this research. The researcher proposed three main variables which were presumed and based on online observation and previous related literature to be commonly experienced by YouTube users; there were (1) exposure – a representation of viewership & impressions of the video, (2) engagement - a representation of user’s involvement toward the content and (3) brand image a representation of the image of the video owner. Three hypotheses were examined on the samples of the viewers and it resulted in a significant impact. This research contributes based on findings that entertaining content can help the brand shape its audience’s attitude. A good brand name in its category also help amplify the construction of attitude. The brand image of JBL Indonesia itself was perceived to be positive and presenting the brand through web series in a good way. Toward marketing theories, it proves that a combination of good content material, positive engagement, and a good brand reputation can help build positive marketing objectives.
Keywords:	Exposure, Engagement, Image, Image, Attitude, Web Series, YouTube
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	AN INNOVATIVE METHODOLOGY FOR ENHANCEMENT OF POWER TRANSMISSION CAPABILITY OF HVDC SYSTEM
Author:	PRABHAKARA SHARMA. P, P. KANTA RAO, K. VAISAKH
Abstract:	The necessity to deliver cost-effective energy in the power market has become a major concern in this emerging technology era. Therefore, establishing a desired power condition at the given points is best achieved using power controllers such as the well-known High Voltage Direct Current (HVDC) and Flexible Alternating Current Transmission System (FACTS) devices. High Voltage Direct Current (HVDC) is used to transmit large amounts of power over long distances or for interconnections between asynchronous grids. The system planner must consider DC alternatives in transmission expansion. The factors to be considered are cost, technical performance and reliability. Power system operation conditions and topologies are time-varying and the disturbances are unforeseeable. These uncertainties make it very difficult to effectively deal with power system stability problems through a conventional controller that is based on a linearized system model. Therefore the UPFC with the proposed adaptive fuzzy logic controller approach is more effective than the UPFC with the conventional. The proposed work of this paper is to analyze for different types of faults, with the addition of UPFC the magnitude of fault current and oscillations of excitation voltage reduces. However to identify the improved transient stability analysis of UPFC with different controller strategies. By introducing FACTS controller into the HVDC system we can improve the power transmission capability and system stability. The results were analyzed by using MATLAB/SIMULINK.
Keywords:	High-Voltage Dc Transmission (HVDC), Flexible AC Transmission System (FACTS), Unified Power Flow Controller(UPFC), Static Synchronous Compensator (STATCOM), Static Synchronous Series Compensator (SSSC), Fuzzy Logic Controller, Total Harmonic Distortion (THD).
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	A SECURE AND ENERGY-EFFICIENT MODEL FOR CPS USING DEEP LEARNING APPROACH
Author:	DEEPTI JOON, KHYATI CHOPRA
Abstract:	The Cyber-Physical System (CPS) utilizes Learning Enabled Components (LECs) with neural networks for understanding and decision-making tasks. Neural Networks are commonly used for reasoning and making predictions about energy forecasts, but subsequently, the prediction-based application in security basic frameworks is not effective. LECs can work simpler as CPS if their expectations could be supplemented with a proper certainty in resource measurement that evaluates the amount of output. The paper presents a methodology which is Long Short Term Memory (LSTM)-Adam optimizer based Inductive Conformal Prediction (ICP) for proper usage of resources. The Triplet Network is designed to learn the input data information for estimating the comparability among the test models collects the information. The main aim of the research is to perform forecasting certainty to improve the learning of the neural network classifier. The present approach will select a significant level for overcoming the trade-off error and the main aim is to reduce the false alarms. The present research performs multiple predictions for the Triplet with k-Nearest Neighbour (k-NN) for Non-Conformity Measure (NCM) function that shows significant improvement at a higher level as LSTM and showed lesser error values of 5.86 when compared with the existing K-NN based ICP model that obtained error values of 16.5 and Triplet K-NN of 9.2.
Keywords:	Cyber-Physical Systems, Inductive Conformal Prediction, k-Nearest Neighbour, Long Short Term Memory-Adam Optimizer, Triplet.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	EFFECT OF BINAURAL BEATS MUSIC THERAPY ON ANXIETY VIA EEG USING ANN & MACHINE LEARNING – A SURVEY
Author:	DEVIKA RANKHAMBE, BHARATI AINAPURE
Abstract:	Over the past two decades, anxiety has been gradually growing in prevalence, particularly among adolescents and young adults. Antidepressant medications have recently been utilized to treat anxiety related disorders that might lead to addiction. An individual's excessive anxiety level might raise their risk of hypertension, stroke, and other disorders. Binaural auditory beats are perceptual phenomena that happens whenever each ear is confronted with two sounds with significantly different frequencies. Binaural beats can substantially change our brain's frequency to the desired condition. Binaural beats have been demonstrated that impact cognition and mental states, among other aspects. Therefore, the purpose of this survey was to see how binaural beats influences on anxiety levels. In addition to this, the influence of artificial neural network and machine learning technology on the processing of binaural beats have been studied.
Keywords:	Binaural Beats, Anxiety, Artificial Neural Network (ANN), Machine Learning, EEG Signals
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	INDUSTIAL PERFORMANCE CONTROL WITH FUZZY LOGIC AND AHP METHODS
Author:	SOUMIA TABIT , AZIZ SOULHI
Abstract:	Performance monitoring has a crucial role in determining the direction of development and progress of an industrial production unit overtime. For this reason, it is important to establish a system to monitor and synthesize the main parameters that affect performance: Productivity, Quality and Safety. In this study, a multi-criteria methodology of evaluation of the industrial performance in a production unit, it passes by a quantification of the indicators (criteria) chosen and is based on a multi-criteria aggregation. The industrial performance has been evaluated - on a real case - using two approaches: The Analytical Hierarchy Process (AHP) and the Fuzzy Logic System for Multi-Criteria Decision Making (MCDM). The comparison between these two approaches and the limits of use of each approach through the specific results obtained allowed to adopt the most reliable and appropriate weighting method. The important task of the proposed models in this study is to determine the numerical score assigned to each year based on the performance parameters. This study presents a comparative analysis of these two studies, illustrated by a case study of the performance of an industrial plant, in order to choose the most appropriate one.
Keywords:	Fuzzy Logic, AHP, KPI, Industrial Performance, MCDM.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	DEEP LEARNING BASED MODEL FOR PAIN RECOGNITION FROM FACIAL EXPRESSION
Author:	GANGIREDDY PRABHAKAR REDDY, M. KALAISELVI GEETHA
Abstract:	Recognition of pain is allowing a range of diagnosis and care possibilities in patients who cannot articulate themselves. Despite developments in this area there is still a lack of study, particularly under unfavorable conditions, on the identification of pain in live videos. Due to patient self report, pain is normally measured. However, self-reported pain is difficult to understand and may not be affected or even probable in certain cases (i.e. young children and those chronically ill). Conduct scientists have found accurate and valid face markers of pain in order to prevent certain issues. In this essay, we discuss an approach to acute pain without the need for human observators automatically. In particular, in adult patients our research was limited to the automatic diagnosis of pain. This paper introduces a deep learning system for the automated pain detection of RGB images taken by a single camera. It de-identifies the confidential information found in the original photos and preserves the privacy of computers that is highly significant. The experiments with challenging pain datasets in the real world show that our method effectively converts pain detection sensibilities from synthetic to actual data and achieves high data accuracy that demonstrates that pain detection in unknown real world surroundings can be generalized in an extremely accurate way.
Keywords:	Pain Recognition, Deep Convolutional Neural Network, Deep learning.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	A SECURE IDENTITY AND ACCESS MANAGEMENT FRAMEWORK IN CLOUD ENVIRONMENT BASED ON DUAL-FACTOR AUTHENTICATION
Author:	FARIS MUDHHI ALRUWAILI, AYMAN MOHAMED MOSTAFA, OSAMA OUDA
Abstract:	Assuring secure as well as user-convenient access to services and/or resources provided by cloud service providers is a crucial requirement for the widespread acceptance of cloud-based services. As a result, several Identity and Access Management (IAM) mechanisms have been proposed to address security and privacy issues inherent in cloud environments. A typical IAM mechanism mainly depends on a trusted third-party service, typically provided by an identity provider (IdP) server, to authenticate users before granting them access to services and/or resources provided by the cloud servers. These mechanisms, however, suffer from the lack of trust between the identity provider and cloud service provider. A fake identity provider can counterfeit access to cloud resources to disclose services using the user’s identity without his/her consent. This paper presents a dual-factor-based IAM framework that alleviates such security concerns. In the proposed framework, the user’s identity is verified by authenticating his/her credentials of the identity provider and by authenticating his/her iris biometric data by a directory server. The Bio Encoding Iris template protection scheme is employed to protect iris templates stored in the directory server. Experimental results on the typical iris dataset, CASIA-IrisV3-Interval, demonstrate the suitability of the iris biometric for the realization of the proposed IAM framework.
Keywords:	Identity And Access Management; Cloud Environment; Dual-Factor Authentication
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	MALICIOUS ATTACK ALLEVIATION USING IMPROVED TIME-BASED DIMENSIONAL TRAFFIC PATTERN GENERATION IN UWSN
Author:	T. SARAVANAN, S. SARAVANAKUMAR, GOPAL RATHINAM, M. NARAYANAN4, T. POONGOTHAI, P. SANTOSH KUMAR PATRA, SUDHAKAR SENGAN
Abstract:	A group of permanent and movable submarine electromagnetic clusters make up the submarine network components. The architecture may change back and forth through time depending on the methodological perspective and the diverse application demands. The majority of researchers have been using constellation architectural networks in current history. In such a networks, the cluster head gathers and delivers intra-cluster and cross - functional and cross data packets. Clustering leaders are chosen energy is a measure of the remaining node, the ideal quantity of Member Nodes, and electricity usage. The choice of cluster head minimizes power consumption and extends the longevity of the lifespan connection. Any form of show's primary issue is protection. Demand of Service (DoS) attacks can impact underwater wireless sensing (UWSNs) despite if they are implemented using modern techniques. As an outcome of these attacks, collaboration connectivity nodes are disrupted, and the program's capacity is reduced. Destructive attacks, often known as denial-of-service (DoS) operations, can be carried in a variety of methods that are not available in plenty of other communications links. These can be initiated at any point in the transport ward's hierarchy. Even if UWSNs are all well by encryption techniques, Attacks can always be a hazard. In this regard, we propose the primary goal of Improved Time-based Dimensional Malicious Alleviation (ITDMA) to safeguard against DoS attacks when directing at the protocol stack. We used the Deep Insight approach to convert numerical features into standard regarding in this investigation. The input data was then classified as malicious actions using these properties in a proposed bi-level classification system. This research would focus on the gateway node and risk based approach, with a good output in terms of classification accuracies, false positive rate, and capacity.
Keywords:	UWSN, Foraging motion, Alleviation, ITDMA, Network trace and False alarm
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	IMPLEMENTATION OF RELIGIOUS LEARNING FOR STUDENTS WITH SPECIAL EDUCATION NEEDS THROUGH ONLINE APPLICATIONS DURING THE COVID-19 PANDEMIC
Author:	AHMAD HANANY NASEH, HANIF CAHYO ADI KISTORO, EVA LATIPAH, HIMAWAN PUTRANTA
Abstract:	Religious education contains values that are one of the building blocks of student character education. This study will reveal and explain the experience of teachers in carrying out religious learning for children with special education needs through online applications. This qualitative research uses a narrative approach. The sampling technique used purposive sampling. The participants of this study were ten teachers of Islamic religious education from two junior high schools in Yogyakarta. Data was collected through in-depth interviews using the interview protocol instrument. Most of the technical interviews were conducted using a question form via WhatsApp and answered with voice notes. While others can be interviewed directly after getting permission from the school. Data analysis used narrative analysis techniques with data reduction stages, themes determination, description, and data interpretation. The results of the study found that the application of religious learning to children with special education needs was classified on two main themes, namely the form of application of learning through online applications and the obstacles faced by teachers. The application of teacher competency learning in using online learning applications and teacher experience has an important role in its success. Obstacles faced by teachers include students' abilities, infrastructure, and limited learning facilities. Some aspects support the success of religious learning for children with special education needs, namely full support from parents, government support, schools, and good communication.
Keywords:	Implementation, Religious Learning, WhatsApp, Instagram, Support, Facilities
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	EXPERIMENTAL STUDIES OF THE FEATURES OF USING WAF TO PROTECT INTERNAL SERVICES IN THE ZERO TRUST STRUCTURE
Author:	LAKHNO V., BLOZVA A., KASATKIN D., CHUBAIEVSKYI V., SHESTAK Y., TYSHCHENKO D., BRZHANOV R.
Abstract:	With the growth of web applications popularity, the need to protect them from hacking and unauthorized access is growing even faster. More than 75% of hacker attacks are aimed at vulnerabilities in web applications and corporate websites. The consequences of such malicious actions are quite obvious and not very pleasant for companies (especially their customers): the loss of personal data, including payment information, the ability to access trade secrets and confidential documents via enterprise networks. Traditional firewall methods do not prevent attacks on web services. Firewalls target threats at the network and transport layers, while web applications operate at the application layer. A Web Application Firewall (WAF is a type of firewall that is used to protect web applications. While a forward proxy server protects the client computer's identity using an intermediary, WAF deploys in front of web applications (in reverse proxy mode) and analyzes bi-directional HTTP / HTTPS traffic to entice malicious traffic and block it. WAFs are not the ultimate security solution, rather they are intended to be used in conjunction with other network perimeter security solutions such as next-generation firewalls (NGFW) and intrusion prevention systems (IPS).
Keywords:	Security, Firewalls, OWASP, WAF
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	DERMOSCOPIC SKIN LESIONS IMAGES SEGMENTATION USING ENHANCED CLUSTERING TECHNIQUE
Author:	M. KAVITHA, A. SENTHIL ARUMUGAM, V. SARAVANAKUMAR
Abstract:	Cancer is believed as a pathetic reason of mortality around the world. Skin cancer is a foremost health issue concerning a plethora people despite their colors. This pretentiousness may perhaps be identified by means of dermoscopy to find out the visible spots on skin are either benign or malignant tumours. It is able to be categorized either into melanoma - the most treacherous form of skin cancer, or non-melanoma. Computer Systems supporting for the detection of skin cancer process digital images to find out the rate of tumours by understanding clinical parameters, relying, firstly, upon an exact segmentation process to extract appropriate features. Here, we propose a new approach entitled as dermoscopin skin lesion images segmentation using enhanced clustering technique. The unsupervised clustering techniques namely K-Means and Fuzzy C-Means are functioning in JSEG method. This algorithm is segregating the dermoscopic image appropriately exclusive of manual parameter tuning and paraphrase texture and color. Experimental results could be analyzed in various scenarios.
Keywords:	Cluster, K-Means, Fuzzy C-Means, Region Growing, Hit Ratio Region, Class-Map, Quantize, Segmentation.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	ASSESSMENT AND IMPROVEMENT OF HUMAN AND ORGANIZATIONAL FACTORS IN AN AUTO-PARTS MANUFACTURING PLANT USING THE FUZZY ANALYTICAL NETWORK PROCESS COMBINED WITH THE FUZZY COMPREHENSIVE EVALUATION METHOD
Author:	YOUSRA KARIM, ABDELGHANI CHERKAOUI
Abstract:	Nowadays, the highly competitive intensity pushes manufacturing companies to continuously improve the production process, by applying a variety of tools and strategies that can help identify the reduction or elimination of waste, lower the product cost and minimize the product manufacturing time. Taking into account human and organizational factors (HOF) can also lead the factory to significant productivity gains by positively affecting human performance and thus reduce the risk of accidents at work. Maturity models can therefore be used as continuous improvement tools by assessing the maturity of HOF first, then determine the elements to be enhanced to reach a high level of maturity. In this article, a study is conducted in a multinational auto-parts manufacturing plant using an HOF maturity model (HOFMM) and the combination of two methods: Fuzzy Analytical Network Process (FANP) and Fuzzy Comprehensive Evaluation Method (FCEM), which allow to consider the relations between the factors as well as the inaccuracy and fuzziness of the decisions taken by the human being.
Keywords:	Safety, Human and Organizational Factors, Maturity, Fuzzy Analytical Network Process, Fuzzy Comprehensive Evaluation Method.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	MICROSERVICE ARCHITECTURE DESIGN: PROPOSED FOR E-OFFICE APPLICATION
Author:	MOCHAMMAD ISRO ALFAJRI, GUNAWAN WANG, YUDIANTO
Abstract:	Analysis and design of e-office application on ministry health of Republic of Indonesia based on microservice architecture. The system is converting from monolithic architecture into microservice architecture by using domain driven design framework to breaking the domain business of the system. Microservice architecture is an important part to agile, resilience, and high-availability. By improvement the feature and the high intention to use to the system by regulation of e-government of Republic of Indonesia at Ministry bureaucracy. By using the Microservice Architecture will improve the productivity of employee, increase the public services, adaptable in current condition of pandemic covid-19 cases in Indonesia.
Keywords:	Microservice, Domain Driven Design, Monolithic, SOA and Ministry of Health,
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	AN AGENT-BASED DOCUMENT CLASSIFICATION MODEL TO IMPROVE THE EFFICIENCY OF THE AUTOMATED SYSTEMATIC REVIEW PROCESS
Author:	MOUAYAD KHASHFEH, MOAMIN A MAHMOUD, MOHAMMED NAJAH MAHDI
Abstract:	This paper proposes an Agent-based Document Classification (AbDC) model that computerizes the systematic literature review (SLR) process by imitating what a researcher is supposed to perform during the literature review process manually. The AbDC model comprises three main components that perform the SLR. Firstly, the document classification algorithm analyses a full text of research articles and evaluates relevancy. Secondly, the multi-agent architecture accelerates the mining process and handles the performance issues. Finally, the web-based systematic review tool tests and validates the functionality of the proposed AbDC model. The first testing was conducted to assess the performance of the proposed AbDC. Result shows that the required processing time was reduced by 33.5% using four agents to achieve the mining process. Meanwhile, the second testing was performed to validate the mining process results. The text extraction method was run on 200 documents from various studies to conduct the review process. The parsing process yielded valid results with 98.5% accuracy. The testing results showed that the proposed AbDC model is significant in providing researchers and postgraduate students with new means to perform SLR.
Keywords:	Document Classification, Systematic Literature Review, Multi-Agent System.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	ANALYSIS OF FACTORS AFFECTING SOCIETY IN INTENTION TO USE INSTAGRAM AS ONLINE SALES STALLS
Author:	LEVIN IMMANUEL LIMARDI HARYADI, TOGAR ALAM NAPITUPULU
Abstract:	The purpose of this research is to analyze the factors that affecting society in intention to use Instagram as online sales stalls in Indonesia. In this research, quantitative research method is used with 100 business actors who use Instagram as online sales stalls to sell various products as respondents. The structural model of this research includes various variables such as User Experience, Facilitating Condition, Reputation, and Enjoyment, based on related research, to analyze the factors that affecting society in Intention to Use Instagram as online sales stalls. Based on research results, Facilitating Condition and Reputation have significant effect on affecting society in intention to use Instagram as online sales stalls. All variables used in this research explain the variability in Intention to use of 62,6%.
Keywords:	Analysis Factors, Intention to Use, Instagram, Business Actors, Online Sales Stalls
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	DECENTRALIZED APPROACH FOR COLLECTING AND PROCESSING DATA OF THE ENTERPRISE INFORMATION INFRASTRUCTURE
Author:	E.A.BASINYA, G.T.MERZADINOVA, A.B.ZAKIROVA, ZH.B.AKHAYEVA, G.TOLEGENOVA, A.K.ALZHANOV, M.A.KANTUREYEVA, A.ZH.AKHMETOVA
Abstract:	The level of security of the information and communication sector of an enterprise is a consequence of the effectiveness of solving problems of system analysis, management and processing of information in a corporate computer network. The article analyzes the problem of responding to incidents in cyberspace on the basis of existing centralized and distributed systems for collecting and analyzing events. Threats of unauthorized influences from trusted users are considered. An original method of system analysis, management and information processing of a corporate computer network is presented for review. The scientific novelty of the proposed solution lies in the ability to automatically control the traffic of a computer network and local information processes of its hosts based on an objective and informative register of events, protected from various external disturbances (from impersonation attacks to falsification of records) by using a modified decentralized blockchain storage with a trust management system to logged events.
Keywords:	System Analysis, Management, Processing, Logs, Blockchain Storage, Trust Management, Multilayer Encapsulation.
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	RECONFIGURABLE SOC ARCHITECTURE FOR WIRELESS VIDEO SURVEILLANCE
Author:	Dr. P. LATHA, Dr. M. A. BHAGYAVENI, Dr. S. R. PREETHI, S. SIMCY
Abstract:	The advancements in SoC (System on Chip) technology make the design engineers to implement the function of wireless sensor network node in a single chip. Reconfigurable System on Chip (RSoC) plays a vital role in video surveillance applications, where detection of surveillance objects is generally achieved by subtracting estimated background from the raw video. So, this paper proposes a reconfigurable SoC architecture for wireless video sensor network node capable of extracting a moving object in video surveillance system using background subtraction algorithm. The proposed video surveillance node aims in performing real-time moving object detection using FPGA (Field Programmable Gate Array) hardware on high resolution video sequences with a frame size of 4608 × 3456. The proposed system processes 10fps (frames per second) and, therefore, the processing capability is 159.3 Mps (Mega pixels per second) of very high system performance. The background subtraction algorithm is implemented in VIRTEX-5 FPGA kit. The RS232 serial port cable is used for establishing the connection between hardware and PC. The FPGA resource utilization is linearly increased with respect to pixel width of the frame. The area taken and the speed of the algorithm are also evaluated. The proposed hardware implementation is compared with the software implementation running on a 2.10 GHz Intel i3-2310M processor. The hardware implementation is 26.36 % faster than software implementation for complex video inputs.
Keywords:	Reconfigurable SoC, Wireless sensor network (WSN), Surveillance, object detection, Background subtraction, Video processing
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	AN ARTIFICIAL INTELLIGENCE ENABLED FRAMEWORK WITH HYBRID FEATURE SELECTION METHOD FOR EFFICIENT EARLY DETECTION OF STROKE
Author:	ANITHA PATIL, Dr. SURESH KUMAR G
Abstract:	Healthcare is the domain which is indispensable for leveraging human health and also minimize mortality rate caused by different diseases. One such disease is brain stroke. Medically brain stroke is the condition that occurs due to poor blood flow to brain causing cell death and it is causing millions of deaths all over the world. According to WHO in 2019, stroke caused more than 6 million deaths across the globe. There are many machine learning methods used for stroke detection using data driven approach. However, their performance is deteriorated when the training data quality is mediocre. To overcome this problem, some feature selection methods came into existence. Those methods could improve performance of prediction models. Nevertheless, there is still need for leveraging prediction performance. In this paper, we proposed a hybrid feature selection method to enhance accuracy of prediction of stroke from the given benchmark dataset. Different prediction models are used along with the proposed hybrid feature selection method along with other existing feature selection methods. The experimental results revealed many useful insights. First, all brain stroke prediction models could perform well with feature selection methods when compared with the models without feature selection. Second, the stroke prediction models exhibited highest performance with the proposed hybrid feature selection model. Thus the proposed stroke detection framework can be used in Clinical Decision Support Systems (CDSSs).
Keywords:	Stroke Detection, Feature Selection, Machine Learning, Hybrid Feature Selection
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	SWITCHING HYBRID MODEL FOR PERSONALIZED RECOMMENDATIONS BY COMBINING USERS DEMOGRAPHIC INFORMATION
Author:	RAGHAVENDRA C K, SRIKANTAIAH K.C
Abstract:	Recommendation systems are smart tools that are necessary to help users to find relevant items and for E-Commerce platforms to improve their revenues. List of items based on its rating and content are searched using collaborative filtering (CF) and content-based filtering (CBF). The recommendation system mainly depends on quality of item recommended and the rating of items given by the existing users. In this work a switching based hybrid model which is the combination of collaborative, content and demographic based model was built for recommending books. Cold start problem was solved using demographic data of users. Experimental analysis has been made on individual and hybrid models using RMSE and MAE metrics. Results show that hybrid model outperforms all the other traditional models in terms of predictions and quality of recommendations.
Keywords:	Book Recommendation System, Cold Start, Content Based Filtering, Demographic Based Recommender System, Collaborative Filtering Technique, Hybrid Filtering Technique
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	TWO-WHEELED BALANCING ROBOT WITH ANDROID NAVIGATION SYSTEM
Author:	BAKTI DWI WALUYO, DADANG MULYANA, BAHARUDDIN, ARIF RAHMAN, MUHAMMAD AULIA RAHMAN SEMBIRING
Abstract:	The two-wheeled balancing robot is a robot that can move with two wheels on the left and the right. However, in order to maintain balance, the robot needs to use both wheels to move. We, therefore, need control to move the two-wheel robot so that it can stand in balance. This system has two inputs, namely accelerometers, used to measure angular acceleration (m/s2) and gyroscopes for measuring angular velocity (rad/s). The accelerometers and gyroscope values were calculated using the complementary filter method to obtain the angle values. The angle obtained is then compared with the setpoint, which is 0°. The difference between the setpoint and the complementary filter angle is processed using the Proportional Integral Derivative (PID) control method. The PID control process results are used to regulate the rotation of the wheel drive motor in the robot. The direction of the wheel drive motor rotation will go forward if the complementary filter angle is less than zero and reverse if it is more than zero. Based on the tests that have been done, the balancing robot can withstand an angle range of -1.5° to 1.5°. While the PID constant value is Kp = 1.5, Ki = 0.2, and Kd = 0.05 and the coefficient value on the complementary filter algorithm is α = 0.96. The two-wheeled balance robot can be operated with an Android smartphone via Bluetooth properly and can move in balance by lifting a maximum load of 40 Kilograms.
Keywords:	Balancing Robot, Complementary Filter, Android Smartphone, PID
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	AN OVERVIEW OF CLOUD COMPUTING FOR THE ADVANCEMENT OF THE E-LEARNING PROCESS
Author:	ASHRAF ALI
Abstract:	As an aid in the teaching-learning process, online communications systems are used to facilitate e-learning, a form of virtualized computing and distant learning. The rise of E-learning platforms emerged drastically in the past two years. Data mining for education information processing uses facts generated from internet databases to enhance the educational learning paradigm for educational purposes when the learning process is computerized. Cloud computing is a suitable platform for supporting e-learning solutions. It can be automatically altered by providing a scalable solution for transforming computer resource consumption in the long run. It also makes things simpler to use data mining techniques in a distributed environment when interacting with massive e-learning datasets. A summary of the current state of cloud computing is provided in the study and examples of infrastructure explicitly designed for such a system. In addition, it also discusses examples of cloud computing and e-learning methodologies.
Keywords:	E-Learning, Cloud Computing, Virtual Learning, SaaS, PaaS, IaaS
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	FEATURES OF USING MATHEMATICAL MODELS TO CALCULATE THE EFFECTIVENESS OF A DIGITAL PLATFORM FOR ECOLOGICAL MONITORING
Author:	OLGA VALERYEVNA SEDOVA, ALEXEY GRIGORIEVICH ALEKSEEV
Abstract:	The research purpose is to determine the conditions for using mathematical models to calculate the effectiveness of a digital platform for ecological monitoring. The analysis method, parametric method, and simulation were used as research methods. A platform interaction scheme between the participants of relationships in the ecological monitoring market in the field of nuclear energy was proposed. When evaluating the effectiveness of using digital platforms for ecological monitoring with respect to customers, it is proposed to consider as a benefit the economic profit obtained due to the difference in the composition and performance quality of the functions (considering also possible risk events) provided when using the platform and a similar solution by comparative analysis and determining the indifference price. Based on the indifference prices, it is proposed to determine the recommended range of the cost of a set of digital platform functions for ecological monitoring. The price range of the set of functions for the nuclear energy market has been determined. It is proposed to determine the optimal distribution of profits between suppliers of functions and equipment based on investments in the digital platform and existing production restrictions. The proposed conditions for the application of mathematical models will serve as the basis for launching a digital platform developed by the Leading Research Center Trusted Sensor Systems of the National Research University Moscow Institute of Electronic Technology.
Keywords:	Ecological Monitoring, Efficiency, Mathematical Model, Platform Interaction
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	DETERMINING SUITABLE SPATIAL RESOLUTION TO ESTIMATE NITROGEN STATUS IN MD2 PINEAPPLE CROP CULTIVATED ON MINERAL SOIL
Author:	ROSMIYATI HASNI, HASMAH MOHIDIN, MOHD YAZID MOHD ANAS KHAN, AZLINA NARAWI4, AZILAWATI BANCHIT, KHAIRUL FIKRI TAMRIN, RADZIAH JACK, SYAHIRA JOS, NGAB DOLLAH SALAM
Abstract:	Strengthening of Malaysian food security requires optimum utilisation of agricultural technology to sustainably increase productivity and yield. Digital nutrient monitoring enables more efficient and timely field estimation to complement existing conventional method. However, high UAV acquisition and computational costs can be overwhelming especially when periodical monitoring is involved. This study attempted to improve UAV feasibility by identifying the suitable spatial resolution (SR) to estimate Nitrogen (N) status in MD2 pineapple (Ananas comosus var. MD2) crop on mineral soil. Two field plots, respectively representing Alluvial and Red-Yellow Podzolic (RYP) soils, were built in Samarahan Campus Farm of Universiti Teknologi MARA Sarawak, Malaysia. This Randomised Complete Block Design (RCBD) based experiment was comprised of five treatments, ten replicates, and five different combinations of NPK fertiliser and MD2 pineapple leaf biochar application. N status of crop canopy was sampled using non-destructive and destructive methods; respectively involving DJI Phantom 4 Multispectral UAV, SPAD-502 Chlorophyll Meter, and D-leaf extraction. Scores of four vegetation indices (NRI, VARI, GCI and RECI) representing Predicted N, were regressed against Observed N of D-leaf Total N Content. SPAD Chlorophyll Meter provided Predicted Relative N status. This study compared the capability of SR between 0.47 and 4.01 cm to detect crop canopy and support Predicted-Observed N Status regression. Detection capability in this study corresponded with SR, yet not solely with canopy width. The highest resolutions of SR0.75 (Alluvial) and SR0.47 (RYP) were able to detect all sample crop canopies, and yield the highest Predicted-Observed N correlation based on NRI and VARI estimations. Detectability was largely influenced by canopy width, number of leaves, and crop symmetries. Lower SR estimations were affected by deteriorating pixel purity and biased sample representation. Therefore, SR of below 1.0 cm is recommended for MD2 Pineapple crop N status estimation on mineral soil.
Keywords:	Spatial Resolution, Vegetation Index, N Status, MD2 Pineapple, UAV
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text

Title:	ANTI-MASK: AN AUTOENCODER-BASED DEEP NEURAL NETWORK TO REVEAL HIDDEN KOREAN FACES WITH FACE MASKS
Author:	JUNHWI KIM, JAE WAN PARK
Abstract:	The purpose of this study is to draw the face part covered by the mask using deep learning technology to complete the entire image. In this paper, we introduce a method of predicting the lower canal of the face based on the information on the upper part of the face using the autoencoder structure. For this study, we design our anti-mask model based on transfer learning through VGGace and train, evaluate, and experiment with a dataset of 800 Korean frontal faces. Our anti-mask model trained in this way accurately drew a part of the hidden face. Through the evaluation of the drawn face images, we proved that our anti-mask model can sufficiently depict the lower canal from the upper image of the face. Moreover, in this paper, it was demonstrated that drawing by analogy with a part of the face is more accurate than reconstructing by analogy with the entire face. This study is expected to contribute to the development of various applications.
Keywords:	Autoencoder, Face Mask, Anti-Mask, Vggface, Image Inpainting
Source:	Journal of Theoretical and Applied Information Technology 15^th February 2022 -- Vol. 100. No. 03 -- 2022
Full Text