		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
January 2022 | Vol. 100 No.01

Title:	A CROSS GENE-CHEMICAL-DISEASE(G-C-D) BASED DOCUMENT CLUSTERING AND CLASSIFICATION MODEL USING DEEP LEARNING FRAMEWORK
Author:	JOSE MARY GOLAMARI, D. HARITHA
Abstract:	In the current biomedical repositories, gene and disease identification and prediction are the essential factors for content clustering and classification models. Since, most of the biomedical databases have heterogeneous features with different levels of gene patterns. Gene identification and clustering of high dimensional patterns in cross biomedical repositories are complex and difficult to process due to noise, uncertain and missing values. In the traditional biomedical repositories, data classification algorithms are used to classify the documents using the MeSH terms or user specific keywords. These models are difficult to find the relational genes and its disease patterns in different biomedical repositories. In the proposed work, a hybrid cross gene-chemical-disease based document clustering and classification model is implemented using the deep learning framework. Experimental results proved that the proposed deep learning-based G-C-D document classification has better optimization than the existing models.
Keywords:	Gene Based Micro-Array Dataset, Feature Selection Measures, Gene Classifiction Disease Prediction.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	MOBILE APPLICATION SYSTEM INTEGRATED WITH VOICE ASSISTANT TO ENHANCE STUDENT’S LEARNING PROCESS (STUDY CASE: XYZ UNIVERSITY)
Author:	JENNIFER ALEXANDRA, RIYANTO JAYADI
Abstract:	Information technology which is growing rapidly nowadays has become one of the main needs in all fields and aspects of life, one of them is in education. Every educational institution continuously strives to make innovations that can provide added value and improve quality, including at XYZ University. XYZ University has presented a mobile-based application that can be used by students to make it easy to access information about lectures using a smartphone. However, the total number of users and the level of frequency of use are always increasing. Continuous innovation is needed. One of the innovations that can be done is to provide voice assistant technology in the system. This study presents the design and analysis on the innovation of the application of voice assistant technology in the university and providing the results of technological innovation designs in applications according to the needs of the stakeholder and XYZ university students. Several proposed voice assistant menu features are classroom location, schedule, exam, finance, forum and attendances. The result of the evaluation shows that the proposed voice assistant system design on the mobile application is accepted by the stakeholder and XYZ university students. The proposed design of the voice assistant system on the mobile application is a supporting innovation of the existing system so that this innovation can create effectiveness and efficiency for the students.
Keywords:	Technology, Innovation, Information, Voice Assistant, Learning
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	EXAMINING THE ROLE OF SYSTEM QUALITY ON SATISFACTION OF ONLINE COURSE PARTICIPANT
Author:	HADI KUSYANTO, VIANY UTAMI TJHIN
Abstract:	In this era of industry 4.0, many offline courses have closed and many offline courses have switched to online. In an era of COVID-19, offline courses are no longer possible because the government is forcing them to stay away and limit teaching and learning activities. This causes offline courses to migrate to online. However, many conventional courses that turn to online have failed. Failure is caused by many online course participants being dissatisfied. Here, we will examine the factors that influence the quality of courses and the satisfaction of online course participants in Indonesia. The online course referred to here is a non-formal course institution that focuses on vocational training such as Arkademi, Skill Academy, Dicoding and Duta Academy. The combined MOOC has approximately 5.5 million course participants until July 2021. So in this paper, we will discuss research on the analysis of the factors that affect learning satisfaction on the MOOC in Indonesia.
Keywords:	Online Course, E-Learning Satisfaction, MOOC, Participant.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	CATALOGUE-BASED GUIDELINE FOR MISUSE CASE
Author:	MUHAMMAD ASYRAF KHAIRUDDIN, ABDUL AZIM ABD GHANI, HAZURA ZULZALIL, SAADAH HASSAN
Abstract:	Misuse case is one of the security requirement elicitation techniques that are easy to use and learn. Unfortunately, the current guideline provided is too general. The process of identifying the misuse case and threats is open for the analyst's interpretation. Lack of knowledge in security threats also can make it worse. These problems can lead to analysis paralysis situation. In this paper, we proposed a catalogue-based guideline to support misuse case techniques to elicit security requirements. This guideline consists of two catalogues used to assist software developers in identifying attacks and threats from a misuse case diagram. We experimented with selected students to evaluate the effectiveness of the guideline in identifying threats and types of threats. We also evaluated the usability of the guideline by conducting experts reviews. Experiment's result shows sufficient evidence that using the misuse case with the proposed catalogue-based guideline is more effective in identifying threats and types of threats than using the misuse case without a guideline. Expert review's result also shows that the catalogue-based guideline is more usable in identifying threats than without using the guideline.
Keywords:	Misuse Case, Security Requirements, Threats, Catalogue, Guideline
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	INFORMATION AND FORECASTING SYSTEM FOR DETERMINING THE LAUNCH AND IMPACT AREAS OF ULTRALIGHT LAUNCH VEHICLES, TAKING INTO ACCOUNT THE REQUIREMENTS OF ENVIRONMENTAL SAFETY
Author:	YERMOLDINA G.T., TRUSHLYAKOV V.I., ALIPBAYEV K.A., UTEGENOVA А.U.
Abstract:	The article reviews the state of development of launch vehicles (LV) intended for launching small spacecraft (SS), namely ultra-light LV (UL LV). The authors proposed the concept of information support for the operation of the UL LV, taking into account the requirements of environmental safety, based on the modernization of the rocket and the effective organization of environmental monitoring. This a fundamentally new concept that involves the introduction of technology for the controlled descent of a rocket unit and an ecological, economic, and technical assessment of the effectiveness of its operation.
Keywords:	Ultralight Launch Vehicle, Information And Forecast System, Environmental Safety, Controlled Descent, Impact Area, Spent Stage
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	MULTI-CRITERIA ANALYSIS BETWEEN NOSQL DATABASES CATEGORIES TOWARD A COMPLETE MIGRATION FROM RELATIONAL DATABASE
Author:	ABDELHAK ERRAJI1, ABDERRAHIM MAIZATE, MOHAMMED OUZZIF
Abstract:	In recent times, the world has become highly dependent on computer science which has become extends to various vital and secondary areas of life, such as social communication, security, commerce, marketing, training, and other fields, as many institutions have become dealing with a huge amount of information to Storage and use for their benefit, in order to manage the present and the future well. This situation made many institutions need several means to keep pace with this great development of information in terms of quantity and quality, without losing what they could possess of previous information stored within databases, often relational system which provide easy ways of dealing with the information, also provides the possibility of applying several complex and important calculations and elicit. Developers in recent days have came out with what's called a NoSQL database, that surpasses its previous predecessor, these developers have also made many programs and tools that works with this new structure, that's characterized in 4 different categories, each one differs from the other in its fundamentals, that’s why finding a way to migrate Data Base with all of data and effects from a relational system to this new structure became a must. In this paper, we will study in-depth and comprehensively the different categories of the NoSQL system, by following the comparative approach using WSM method and depending on a set of characteristics and features, in order to determine the optimal category that enables us to completely migrate all data from a relational system with all its details, and capabilities towards a NoSQL system, in order to put the first step to start studying the migration of data from a relational system to a NoSQL system
Keywords:	NoSQL; Big Data; Migration; Relational Database; WSM;
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	ENHANCING DOCUMENT REPRESENTATIONS WITH SYNONYMS GRAPH NODE EMBEDDINGS
Author:	ROMAN SHAPTALA, GENNADIY KYSELOV
Abstract:	Document representations are a key element in solving natural language processing problems, including document classification, clustering, and topic modelling. Modern deep learning-based techniques are able to build such representations with great success. However, they require a lot of data to do so, thus are not applicable in the low-resource setting. Recently, low-resource NLP methods focused on transfer learning approaches which assume the existence of pretrained models, as well as data augmentation approaches which expand available datasets. Our key idea is to use a synonyms dictionary as a transfer learning tool instead of a source for token-level document augmentation. Consequently, the objective of this study is to investigate the improvement of existing document embedding methods in a low-resource setting by the incorporation of synonym dictionary information. Our main research contributions are the demonstration of the effectiveness of synonym node embeddings as a transfer learning method for building document representations and the proposal of a method for enhancing document representations by mixing them with an average of node vectors of words from a synonyms graph of the low-resource language. The experiments show a 2% F-score improvement for Kyiv City petitions topic classification in Ukrainian. The analysis and optimal hyperparameters for training a Node2Vec graph embeddings model as well as the weighted sum fusion of baseline and synonym embeddings are provided. Future work can explore the impact of other node embedding methods or the application of other linguistic dictionaries in a similar fashion.
Keywords:	Low-Resource Natural Language Processing, Node Embeddings, Document Embeddings, Synonyms, Document Classification
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	THE TRADE-OFF BETWEEN ROBUSTNESS AND IMPERCEPTIBILITY PERFORMANCE OF WATERMARKING TECHNIQUE WITH DWT AND SCHUR DECOMPOSITION FOR MEDICAL IMAGES
Author:	MARYAM JASIM ABDULLAH, AMELIA RITAHANI ISMAIL, ADAMU ABUBAKAR
Abstract:	Developing a watermarking algorithm for a medical image is required to conserve the original visual quality and resistance ability to image attacks. The problem is that there is opposite relation between imperceptibility and robustness performance. This paper proposed a watermarking algorithm that applied discrete wavelet transfer (DWT) and Schur Decomposition to produce a watermarked image with high imperceptibility and robustness performance. In the embedding process, the DWT and Schur decomposition is used to decompose the domain of a host medical image, and the modification to hide the watermark bit is evaluated and controlled to keep the imperceptibility performance high as possible for the watermarked image. The imperceptibility, embedding capacity, and robustness are evaluated for Magnetic Resonance (MR), Computed Tomography (CT), and Positron Emission Tomography (PET) medical image modalities. The results obtained from the experiment and showed that the proposed watermark technique has high performance in three measurement terms imperceptibility, embedding capacity, and robustness. The average peak signal-to-noise ratio (PSNR) of the different six watermarked images was 73.65dB. Also have high robustness against JPEG compression, salt and pepper noise, Gaussian noise, and rotation attack.
Keywords:	Robustness, Imperceptibility, Medical Image, Discrete Wavelet Transfer, Schur Decomposition, Watermarking Technique.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	UNDERSTANDING THE PODCAST LISTENER INTENTION TOWARD PERCEIVED USEFULNESS MODERATED BY CONTENT DENSITY: A CASE STUDY OF PODCAST LISTENERS IN INDONESIA
Author:	JERRY S JUSTIANTO, Mts ARIEF, INDAH SUSILOWATI, MUHAMAD ARAS, GILANG SAPUTRA
Abstract:	Music and audio delivery has shifted from the radio broadcasting to podcast audio on demand due to the advance of podcast technologies. Current podcast broadcasting utilizes technologies that have made the access to podcast music, talk and audio debate become more popular among podcast listeners. However, effect listener experience and their listening intention have rarely studied podcast listener research. Consequently, the determinants of listener multitasking activities and program duration towards the perceived usefulness are interesting topic to study. Hence, this study is focused on unraveling the key determinants of driving the listening intention and perceived usefulness while addressing empirically, the moderating role of content density. This research method uses quantitative methods with analysis tools using SEM-PLS to investigate the proposed research model. Among the 339 responders via a web and mobile based survey using SurveyHero.com, the completed answered is by 128 responders. The results revealed that listener experience, multitasking activities, program duration as key antecedents towards listener intention. In addition, listener intention also antecedents of perceived usefulness moderated by content density. This research has implication that the content density must be studied further to evaluate this effect toward the perceived usefulness among the listeners for podcast broadcasting program quality.
Keywords:	Podcast, Listener Experience, Multitasking, Listening Intention, Content Density, Perceived Usefulness
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	DOCUMENT CLASSIFICATION SYSTEM FOR THE SPANISH LANGUAGE
Author:	LUIS GABRIEL MORENO SANDOVAL, LILIANA MARIA PANTOJA ROJAS, NELSON GIOVANNI AGUDELO CRISTANCHO, CRISTINA RAMÍREZ MENESES
Abstract:	The classification of documents is a relevant task in companies to save time in managing information present in specific documents; therefore, the health sector seeks to prioritize documents performing the traceability of any process within its network. This article presents a document classification system to provide a tool divided in software components that faces the challenges of binding to the Spanish language using public sources such as Google and Wikipedia applying long documents related to the health sector in Colombia. For this purpose, a set of Machine Learning classifiers is performed to compare F1-score, Precision, and Recall metrics obtaining the best performance in the Logistic Regression classifier. In addition, the article makes a theoretical survey on the relationships that text mining, Information Retrieval, and Text Summarization have with document classification.
Keywords:	Text Mining, Information Retrieval, Text Summarization, Document Classification, Spanish Language.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	IOT AND CLOUD BASED BLOCKCHAIN MODEL FOR COVID-19 INFECTION SPREAD CONTROL
Author:	AHMED S. SALAMA, AHMED M. EASSA
Abstract:	Due to the increasing number of infected people and the number of deaths from COVID-19 over the world, there is a big challenge towards finding a radical solution to reduce the spread of disease and infection. The early detection, isolating the infected persons and tracing possible contacts are very critical. This paper presents an integrated approach that connects hospitals/laboratories, COVID-19 negative persons, positive persons, and contact persons to a cloud-based consortium blockchain system to guarantee reliable secured COVID-19 spread control. The proposed model guarantees a real time monitoring, tracking, and updating to persons status whether normal, contact, or positive COVID-19 case, and the related updates are done in the blockchain based on the results of execution of the blockchain smart contract rules. Tracking infected persons and their contacts is implemented using IoT sensors to determine contact time and spatial distances between them. The GPS/Bluetooth/UWB was used as IoT sensors technologies to determine the distances between the infected people and those in contact. The proposed blockchain Ethereum system smart contract was implemented by solidity programming language through the Remix IDE. The proposed approach was tested and successfully detected the contact cases and managed the different persons states on the cloud based blockchain system applying the smart contract rules accurately. As the calculated distances using the proposed model in the distance of one meter do not exceed the error rate of 11 cm.
Keywords:	IoT, Cloud Computing, Blockchain, Smart Contracts, COVID-19.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	AN EFFICIENT FILE ACCESS CONTROL TECHNIQUE FOR SHARED CLOUD DATA SECURITY THROUGH KEY-SIGNATURES SEARCH SCHEME
Author:	TARASVI LAKUM, PROF.B. TIRAPATHI REDDY
Abstract:	Through cloud services, the cloud based users and organizations are storing and sharing the data in the advanced cloud computing environment. However, the recent cloud data breaches have raised privacy and secure concerns in the cloud managed data, due to vulnerability in untrusted cloud access control system . However, designing an efficient trusted access control system in cloud through enabling a cryptographically file access control technique is still challenging. In this research contribution, a cloud data security system for an efficient file access control technique that provide practical trusted security for shared cloud data is proposed. Proposed file access control technique revokes Key-Signatures Search Scheme which provides confidential hosted-file data access, by delegating role-based public key-revoking in cloud hosted environment to update encrypted data. In Key-Signatures Search Scheme, the cloud data security is made by encrypting the file by a hosted-file key management, which records hosted-file and its revocation keys simultaneously for key-access enforcement and file-access revocation. In each hosted-file revocations, cloud administrator checks for any in-secure data breach, if found, for that particular hosted-file a new revocation key is updated and request for a new encrypted hosted-file with updated file-access permissions. In Key-Signatures Search Scheme, three stages of key-signatures are monitored and updated based on how hosted-file access if enforced, after enforcing how file is granted for access and finally how revocation of grant hosted-file access is made. By monitoring through these three ways, Key-Signatures Search Scheme, enforces a dynamic hosted-file access control technique at cloud data user side which improves the file access control providing efficiency, which does not require re-submission of revocation keys and repeated file access granting checks, and providing security for a large hosted-files at the cloud data owner side by instant hosted-file key-revoking for access control. Cloud data security framework and system implementation is made in the proposed work to demonstrate the Cloud Data Security and Efficiency of the proposed technique. Proposed Key-Signatures Search Scheme uses formalized shared cloud date framework and cloud owner with user system implementation to establish the cloud data hosted-file security and show efficiency of proposed file access control technique through hosted cloud system design.
Keywords:	Cloud computing, Role-Based Access Control, Key Encryption Schemes, Cloud Data Security, Revocation
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	EXPLORING INSTAGRAM’S VISUAL COMMUNICATION EFFECTS OF INDONESIA’S PREMIUM FASHION BRANDS
Author:	ANIQ TASIA, RICARDO INDRA
Abstract:	This study aims to examine the influence of visual communication towards consumer behavior in purchasing premium local fashion products through the mediating effects of brand image and eWOM on Instagram as the main distribution channel of visual content, and understanding the preferred visual content types by the consumers in Indonesia. This is a quantitative study and was conducted using a structured-questionnaire from 250 Instagram users who are premium fashion brand customers, who lived in Indonesia. Statistical analysis was performed using Partial Least Squares - Structural Equation Modelling (PLS - SEM) approach with path analysis. This study investigated Instagram as visual content distribution channel for Indonesian premium local fashion brand. The result of this study showed that visual communication has significant influence on both brand image and eWOM, the result also shows it has significant influence on purchase intention both directly or through the mediating effect of brand image and eWOM. This study brings theoretical and practical implication in the study of visual content distributed through Instagram and could provide information about the types of visual content which is preferred by customers which may improve brand image and eWOM in social media marketing.
Keywords:	Visual Communication, Premium Fashion, Social Media, Brand Image, eWOM, Purchase Intention.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	A BIG DATA ANALYTICS FRAMEWORK FOR COMPETITIVE INTELLIGENCE SYSTEMS
Author:	BOUKTAIB ADIL, FENAN ABDELHADI
Abstract:	Nowadays, companies are facing a lot of challenges due to the volume and velocity of data available online, the nature of this data which comes in different formats structured, semi-structured or unstructured, forces the adoption of new tools and techniques to process and transform data to knowledge, competitive intelligence systems aims at setting-up tools and software to handle this stream of data from data collection, data analysis, data visualization to the results dissemination for stakeholders to enhance the decision making process of companies. In this paper, we present a big data analytics layer/framework for competitive intelligence systems and we implement it in the case of XEW 2.0 system relying on Apache Spark capabilities and big data analytics technologies, we validate the proposed framework with a case study about Research in Morocco in order to achieve a technological surveillance, the framework shows promising results in providing analysts with a toolbox to extract strategic information.
Keywords:	Big Data, Competitive Intelligence, Big Data Analytics, Apache Spark, Data Mining
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	STOCK PRICE PREDICTION USING DEEP LEARNING TECHNIQUES
Author:	P.N.V. SYAMALA RAO. M, N. SURESH KUMAR
Abstract:	There are two commonly held beliefs when it comes to picking stocks. Fundamental analysis is the initial step in making an investment decision, while technical analysis is the process used in making that decision. Investing involves using two separate analytical tools: fundamental analysis and technical analysis. Fundamental analysis and technical analysis can both tell whether an investment in a company is appealing or unattractive, and then go on to speculate on what the future trends of stocks will be. The combination of fundamental and technical research may provide a complete trading strategy. Artificial recurrent neural network (RNN) architecture, long short-term memory (LSTM) networks. The large-sequence-processing capabilities of LSTMs apply to many data sets. The vast quantity of data that is produced every day in the stock market is ideal for use in artificial intelligence applications. We want to use LSTM to build a financial market forecasting network that uses Technical and Fundamental analysis of businesses to predict the stock prices the next day. To do both kinds of analysis, the input data is pre-processed to contain necessary variables and then trained on LSTM& GRU. In this work we proposed Clustered Gradient Descent Adam optimizer usually perform better than models with Adam optimizer. The GRU model beats the LSTM model when it comes to overall accuracy.
Keywords:	Long Short-Term Memory (LSTM) networks, Deep Learning, Fundamental Analysis, Technical Analysis, Financial Markets.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	DETECTION OF FOREIGN OBJECT DEBRIS (FOD) USING CONVOLUTIONAL NEURAL NETWORK (CNN)
Author:	KUSWORO ADI, CATUR EDI WIDODO, ARIS PUJI WIDODO, UTAMI SRI MARGIATI
Abstract:	Foreign object damage (FOD) is a big problem in aviation maintenance industry that reduces the level of safety for an aircraft. Basically, FOD is known as foreign object (FO) that can cause severity and destruction to the aircraft such as engine failure and loss of human life. Nowadays there is no FOD detection system that can classify the type of FOD that is detected optimally. This study proposes the FOD classification approach using Deep Learning. The Deep Learning method that has significant results in image recognition is the Convolutional neural network (CNN). The purpose of this study is to determine the CNN algorithm model that has optimal accuracy in the FOD classification. Convolutional Neural Network (CNN) is a multilayer neural network with a supervised learning architecture that consists of two parts, namely feature reviewers and classifiers that can be trained. The research began by designing a dataset and CNN algorithm model, then proceed with Training and Testing data. Based on the research, CNN model that has optimal accuracy using a 64 x 64 input image, learning rate value of 0.001, filter size 3 x 3, number of epochs 100, number of training data of 1200 data and test data of 20 data. The number of convolution layers used is 1 layer. The algorithm created is able to classify FOD objects into 6 classes with 86.6% accuracy and provide the best classification results into 4 classes with an accuracy of up to 90%.
Keywords:	Foreign Object Debris, Deep Learning, Convolutional Neural Network.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	IMPACT OF INFORMATION TECHNOLOGY, LEADERSHIP COMMUNICATION, PROTECTION FACILITY, AND LOCAL WISDOM PRACTICE ON SOCIAL READINESS FOR DISASTER IN KRAKATOA
Author:	Z. HIDAYAT, RICARDO INDRA, LIDYA WATI EVELINA, TUKINA, SEREE SUPRATID
Abstract:	The purpose of this paper is to examine the effect of several variables determining the social preparedness in the "ring of fire" area. The survey was conducted on residents around the circle of Mount Krakatoa, Indonesia, with 287 respondents, and data processing used a structural equation model (SEM). The results show that the early warning system and information technology variables, local government communication leadership, citizen protection facilities, and consciousness of living in the ring of fire territory significantly affect social readiness for disaster. Likewise, the willingness to protect nature, community cohesiveness, and willingness to build local wisdom also significantly affect social readiness. This study implies the need for collaboration between communities and government to foster social readiness.
Keywords:	Environmental Communication, Government Communication Leadership, Information Technology, the Ring of Fire, Social Readiness
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	PERFORMANCE ANALYSIS OF LSTM BASED DEEP LEARNING MODELS FOR ABNORMAL ACTION PREDICTION IN SURVEILLANCE VIDEOS
Author:	MRS. MANJU D, DR. SEETHA M, DR. SAMMULAL P
Abstract:	Video surveillance is increasingly being adopted for ensuring safety and security both in public and private places. Automated prediction of abnormal events like theft, robbery, murder etc from continuous observation of surveillance videos is a multidisciplinary study involving computer vision, deep learning and artificial intelligence. Deep learning-based video analysis and categorization is the most researched topic. Many deep learning models based on Long Short Term Memory are proposed for automated prediction of abnormal events. There are two contributions in this paper; the first contribution focuses on five models - Resnet, VGG16, VGG19, 3DCNN and Inception V3. The second contribution has proposed an approach called Recurrent-Residual-Inception V3 (RRIV3). Advantage of RRIV3 is performance will not get effected more by removal of any residual block. This work does a performance analysis of six LSTM based deep learning models for abnormal event prediction from surveillance videos before and after performing preprocessing. Deep learning models are combined with LSTM for the prediction of abnormal events from past observation of events in the video stream. These six models are executed against different benchmarked abnormal event detection datasets one among them is UCF-Crime dataset and efficiency is compared in terms of accuracy, precision, recall and execution time. It is observed that Recurrent-Residual-Inception V3 with LSTM performs better than other models with training accuracy of 90% and test accuracy of 85% compared to other models. The execution time is 20 milliseconds compared to other models.
Keywords:	3DCNN, Inception V3, VGG16, VGG19, Resnet, Recurrent-Residual-Inception V3
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	DEEPFAKE DETECTION BASED ON THE XCEPTION MODEL
Author:	JAMAL EL ABDELKHALKI , MOHAMED BEN AHMED, ANOUAR ABDELHAKIM BOUDHIR
Abstract:	Thanks to artificial intelligence, everybody can easily create deepfakes without any particularly technic knowledge. By analyzing faces movements. But these will become more and more realistic as technological developments progress, and therefore more and more problematic ...The rapid evolution in synthetic image generation and manipulation has now come to a point where it raises significant concerns on the implication on the society. With the advent of fake news and its harmful effects on social networks, the dissemination of deepfakes on the web therefore constitutes a new technological threat. Manipulation, disinformation, humiliation, defamation ... the dangers of deepfakes will be more and more numerous. In this post, first, we will describe in brief how deep learning with Depthwise Separable Convolutions can be the most useful and promising techniques to detect deepfakes
Keywords:	FaceForensics, CNN, Xception, MTCNN, Cyber security
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	METHODS FOR THE SECURE USE OF EXTERNAL SERVERS TO SOLVE COMPUTATIONALLY-COMPLEX PROBLEMS WITH SECRET PARAMETERS
Author:	BANU B. YERGALIYEVA, YERZHAN N. SEITKULOV, DINA ZH. SATYBALDINA
Abstract:	In this work, we study methods for the secure use of external insecure computers (servers) when solving computationally-complex problems with secret parameters. This problem is one of the important scientific directions in the field of information security of cloud computing. The article presents methods for secure outsourcing of the problem of finding the extremum of a function, as well as one method for finding the value of an analytical (holomorphic) function on a secret argument. Note that our main goal is to demonstrate new methods of secure outsourcing of scientific computing, so we model classes of problems in such a way as to clearly show the essence of these methods.
Keywords:	Information Security, Big Data, Secure Outsourcing, Cloud Computing, Computationally-Complex Problem, Client-Server Interactions
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	CYBER-SECURITY KNOWLEDGE AND PRACTICE OF NURSES IN PRIVATE HOSPITALS IN NORTHERN DURBAN, KWAZULU-NATAL
Author:	IAN SINGH, YASHIK SINGH
Abstract:	South African nurses work extensively with predominately paper-based medical information (patient/health records). Private secondary healthcare facilities are leading the transition towards digitised and interconnected Medical Information Systems (MIS). Electronic Health (eHealth) information is extremely lucrative on the black-market; therefore, large MIS databases (found in leading private hospitals) are prime targets for cybercrime. Employee negligence and human error account for almost half of database breach causes globally. Therefore, the security of MIS is significantly dependent on the MIS custodians (nursing, support, pharmaceutical, administration and management) utilising them. As South Africa transitions towards her eHealth strategic objectives, this study evaluated an essential element of information security – the cyber security awareness and practice of her MIS custodians. 185 MIS custodians working in two leading private hospitals in KwaZulu-Natal (KZN), were investigated and their reactions around cyber practice, cyber threats targeting end-users within the healthcare industry (viz. malware, social engineering, spam, phishing and Ransomware), and cyber awareness was evaluated. The results indicate a significant misunderstanding or ignorance of cyber and information terminology; lack of cyber security awareness and secure cyber practice; poor understanding of cyber threats and prescribed mitigations; and uncertainty pertaining to relevant legislation around electronic patient information. The current cyber security practice and knowledge of MIS custodians is concerning warranting intervention.
Keywords:	Cyber-crime; Tele-health; eHealth; Cyber-security; Medical Information Systems
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	A PROPOSED MODEL FOR ENHANCING E-GOVERNMENT SERVICES TO ACHIEVE THE SUSTAINABLE DEVELOPMENT GOALS IN EGYPT " CASE STUDY"
Author:	IBRAHEM M. M. RAMADAN, Prof. Dr MANAL A. ABDEL-FATTAH
Abstract:	In light of the increasing interest of governments in e-government and achieving the sustainable development goals 2030, the governments seek to provide new e-government services and develop strategic plans to achieve the SDGs. This study clarifies the contribution of E-government services in achieving SDGs and the relationship between them and describes how can Enhance e-Government services to achieve SDGs in Egypt. The primary goal of this paper is to present a model for Enhancing E-government services in order to contribute to achieving some sustainable development goals. and also to enhance the researchers and anyone who wants to improve, add a new service to E-government services, or to achieve the SDGs and their domains with data and methods that help them ease of choice and decision making. This study proved that there is a relationship between E-government services and sustainable development goals, and there is an effect of Enhancing E-government services on achieving the sustainable development goals.in this study, the Blockchain technology was being integrated into the E-voting system to submit the prototype of the Egyptian E-Voting System, and that is the significant improvement point against the traditional voting system as the users can cast the vote and check the results after completing all processes by using the web application. the improvement of This service will contribute to the achievement of 18 targets from SDGs.
Keywords:	Sdgs; E-Government; UN; Egypt; E-Government Services; Sustainable Development Goals; Means Of Implementation [Moi]; Blockchain; E-Voting
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text

Title:	ASSOCIATION RULE ALGORITHM FOR WEATHER FACTORS ESTIMATION USING ON-GRID SOLAR PV POWER SYSTEM
Author:	MOHAMMAD A OBEIDAT, AYMAN M MANSOUR, FAYEZ KHAZALAH, JALAL ABDALLAH
Abstract:	Many stations are established worldwide to measure the weather factors such as temperature, humidity, wind speed, and cloud cover. In this paper, A developed model using association rule mining algorithm is utilized to predict weather factors from real power photovoltaic PV system on-grid. This model is tested on Tafila Technical university PV system data. The developed model contributes successfully as a virtual weather station to forecast the weather in Tafila-Jordan region. The extracted rules of the model are examined by a weather forecasting expert in order to validate the developed system. The results show high confidence and accuracy. The predicted weather factors from PV power values matched approximately 97% of the results given by the experts.
Keywords:	Association Rule; Power; Photovoltaic; Weather Conditions; Estimation.
Source:	Journal of Theoretical and Applied Information Technology 15^th January 2022 -- Vol. 100. No. 01 -- 2022
Full Text