		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:	IOT AND CLOUD COMPUTING TECHNOLOGIES TO SUPPORT INFORMATION SYSTEM: A SYSTEMATIC REVIEW
Author:	RAKI YOUNESS, MARZAK ABDELAZIZ, MAMOUNI ABDELAZIZ
Abstract:	The Internet of Things (IoT) will be a smart generator of data which support the Information Systems (IS) and Communication Technologies (CT). It offers the opportunity to exchange structured and unstructured data among devices in real time, to process data to be useful as information, from where we can extract out knowledge in this area. With M2M communication technology, IoT services can aims to understand connected devices reactions in order to optimize services and applications. IoT also is a technology which provides special service in cloud environment that can support storage, analyze and modeling IoT-Data phases. However, some resources (memory and CPU) in IoT, cloud and M2M communication systems are overloaded. Because of the different IoT-data features (source, nature and volume) as well as the way to manage this data in order to explain the complexity of IoT systems. In this review, we identify and describe the resources that are used in IoT Cloud environment. we study the possible scenarios that can help us to define relationships between IoT/CLOUD and M2M technologies. Further, we present the benefits of the information system and feature extraction technics that can be explored for the processes management of IoT-data.
Keywords:	IoT-data, Cloud, M2M communication, Sensors networking, Resources overload, Big data.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	A HYBRID MODEL TO ENHANCE RECOGNITION OF MULTI-CLASSES IMAGES
Author:	MANAL A. ABDEL-FATTAH, HAGAR M. El HADAD, AHMED ELSAYED YACOUP, SHAIMAA S. ABDEL-KADER
Abstract:	Nowadays, the volume of digital data increasing very rapidly especially the image datasets. The reason behind this increase is the rapid development of digital technologies and platforms such as Facebook and Instagram etc. From this point of view, the researchers started to build applications based on using image classification models. These models used traditional techniques or deep learning techniques to classify the multi-classes images. Most researchers in the field of image classification concluded that there are different problems such as the wrong classification for objects and low accuracy rate value in the case of using many classes that are found as a result of the classification phase. Focusing on the essential problem is recognizing a huge number of images for different classes with a high accuracy rate. This paper presents an improved model in multi-classes images recognition. This model combines traditional techniques with deep learning techniques where the feature vector of these techniques (VGG16+HOG+SURF) or (ResNet50+HOG+SURF) are combined in one feature vector for classification. The fine-tunning method is used to perform classification by the combined feature vectors to classification layers in ResNet50. VGG16 and ResNet50 are examples of deep pre-trained networks while Histogram of Oriented Gradients (HOG) and Speeded Up Robust Features (SURF) are examples of traditional techniques. The experimental results of the presented model in this paper provide an improvement through an excellent accuracy rate when using a combined feature vector of (ResNet50+HOG+SURF) that reached 98.9% for the recognition of the cifar-10 dataset.
Keywords:	Image Recognition, Feature Extraction, SURF, HOG, Deep Learning, Convolutional Neural Network (CNN), Transfer Learning, VGG16, ResNet50, Cifar-10.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	DIGITAL MODELS OF STABILIZING THE HYDRAULIC MODE OF HEAT SUPPLY SYSTEMS
Author:	N. TOMILOVA, A. TOMILOV, D. KAIBASSOVA, A. KALININ, A. AMIROV, M. NURTAY
Abstract:	This article presents a method and algorithm for solving the problem of stabilizing the hydraulic modes of a heat supply system main fragments based on setting the threshold values of control valves for flow and pressure regulators used in the field of technological processes automated control of the system and using a two-level decomposition of the heat supply system. Research has been carried out to confirm the software computational efficiency of the developed models and algorithms. In the course of this study, models for stabilization of the hydraulic mode by distribution fragments of a heating network were not considered. As a rule, include nodes of connection to main networks a distribution pipeline network with a pipeline diameter of less than 400 mm, step-down and booster pumping stations, respectively, on the opposite and supply pipelines or mixing pumping stations between supply and return pipelines, individual heat points of consumers with dissimilar heat consumption loads. The development of permissible modes of all distribution fragments is the second stage in the search for an admissible mode of a large heat supply system after the search for an admissible mode of the main system fragment is completed.
Keywords:	Heat Supply System, Decomposition, Hydraulic Control, Stabilization, Method, Algorithm, Software Implementation, Efficiency.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	MULTI-EXPERT SYSTEMS: FUNDAMENTAL CONCEPTS AND APPLICATION EXAMPLES
Author:	ALEXANDER MUSAEV, DMITRY GRIGORIEV
Abstract:	In this paper, we propose the concept for creating a multi-expert system (MES) as a distributed decision support system. We identify the fundamental differences between MES and multi-agent systems, and present options for MES structure and formalized models for their description. Furthermore, we consider examples of MES use in management problems of multidimensional non-stationary processes characteristic of unstable immersion environments.
Keywords:	Multidimensional Non-Stationary Processes, Multi-Expert Control, Distributed Decision, Multi-Expert Asset Management, Knowledge Extraction.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	THE ACCURACY COMPARISON AMONG WORD2VEC, GLOVE, AND FASTTEXT TOWARDS CONVOLUTION NEURAL NETWORK (CNN) TEXT CLASSIFICATION
Author:	EDDY MUNTINA DHARMA, FORD LUMBAN GAOL, HARCO LESLIE HENDRIC SPITS WARNARS, BENFANO SOEWITO
Abstract:	Feature extraction in the field of Text Processing or Natural Language Processing (NLP) has its own challenges due to the characteristics of unstructured text. Thus, the selection of the right feature extraction method can affect the performance of the classification. This study aims to compare the accuracy of 3 word embedding methods namely Word2Vec, GloVe and FastText on text classification using Convolutional Neural Network algorithm. These three methods were chosen because they are able to capture semantic, syntactic, sequences and even context around words. Therefore, the accuracy of these three methods was compared on the classification of news from the data set taken from the UCI KDD Archive, which contains 19,977 news stories and is grouped into 20 news topics. The results show that the word embedding with the Fast Text method performs the best accuracy in the classification process. In fact, the difference in accuracy of the three methods is not crucially significant, so, it can be concluded that its usage depends on the applied data set.
Keywords:	Word2Vec, Glove, Fasttext, Word Embedding, Convolution Neural Network, Text Classification
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	IMPACT OF KOREAN SMALL- AND MEDIUM-SIZED MAN-UFACTURERS’ SUPPLY CHAIN TECHNOLOGY STRATE-GIES AND TECHNOLOGY INNOVATION COMPETENCE ON CORPORATE PERFORMANCE
Author:	ROK LEE, SU SUNG JEON, BYEONG CHUL LEE
Abstract:	This empirical study aims to identify the influence of supply chain technology (SCT) strategies and organ-izational capabilities of Korean small- and medium-sized manufacturers, adopting and operating SCT strategies, on corporate performance. SCT strategy factors of small- and medium-sized manufacturers were considered independent variables, while corporate performance variables were considered dependent variables. Both exploratory factor and reliability analyses for the SCT strategy metrics were employed. Results showed that SCT strategies, the impact of technology innovation competence on corporate per-formance, influence of SCT strategies on corporate performance, and the mediating effects on SCT strate-gic factors and corporate performance were significant and adopted. Generally, these results imply that the introduction of Vendor Managed Inventory, Enterprise Resource Planning, Collaborative Planning Fore-casting and Replenishment, Warehouse Management Systems, and Order Management System as SCT strategic factors are directly related to enhanced corporate performance. In the context of technology in-novation competence, the factors are closely linked with capabilities in strategic planning, research and development, manufacturing, and marketing. In the context of SCT strategic factors of small- and medi-um-sized manufacturers, if technology innovation competence is combined, enhancing corporate perfor-mance is possible.
Keywords:	Supply Chain Technology, New Product Development Performance, Financial Performance, Manufacturing Firms, Korea
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	MAMMOGRAM IMAGE CLASSIFICATION USING LOCAL BINARY CONVOLUTIONAL NEURAL NETWORK
Author:	HADEEL ABDULMAJEED, MOHAMMAD SHKOUKANI
Abstract:	Breast cancer is considered one of the most common cancer in women worldwide, reducing the risk of mortality is by early detection of cancer and providing the appropriate treatment. Working on mammography using machine learning can help detecting and diagnosing cancer. Convolutional neural network (CNN) is a deep learning technique which is one of the best for detection and classification of abnormalities in medical images. Training CNN models need large datasets so training it on medical datasets from scratch is difficult job because of their small size and the variation of the abnormality shapes in mammogram images, instead it is possible to use pre-trained network because the generic features from such model can be used for new different task like mammogram image dataset that has limited number of images. This research employed transfer learning by enhancing Local Binary Convolutional Neural Network (LBCNN) model which is deep learning technique to suit our new task and help classifying breast abnormalities in mammogram images by applying it on MIAS database. This includes image preprocessing, feature extraction by optimizing and fine-tuning number of convolutional layers and Finally image classification using new classifier with three classes normal, malignant and benign. The results proved that the enhanced model successfully predicted the presence of normality or not and its type with accuracy reached 90% in 15 minutes using about 1.2 million parameters which saves memory and time compared to 88.7% accuracy in 28 minutes using about 11.3 million parameters on standard CNN, this lead to conclude that the system capable of detecting and classifying mammogram images saving a lot of parameters.
Keywords:	Mammogram Image, Convolutional Neural Network, Classification, Breast Cancer
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	STUDYING THE RELATIONSHIP BETWEEN DISSONANCE OF ARABIC LETTERS AND THE DISTANCE OF THEIR OUTLETS
Author:	MAJED ABUSAFIYA
Abstract:	Spoken texts have varying levels of eloquence. One main feature of eloquent spoken text is the absence of dissonance between its adjacent letters. A number of theories were proposed to reason why a given pair of adjacent pronounced Arabic letters show dissonance. One of these theories refers it to the closeness or remoteness of their mouth outlets. In this paper, the relationship between the dissonance of letters and the distances between their outlets is computationally studied. Our approach is based on finding the outlets distances for adjacent letters in a text of perfect eloquence. Quran was chosen for this study. This is because Quran is known to be the only Arabic text with perfect eloquence and hence shows no letter dissonance. The frequencies of different outlet distances for every adjacent pair of the spoken letters were calculated. Although found varying, these frequencies did not show significant variation. This means that outlet distances is not the reason for dissonance of adjacent letters. Otherwise, we should see very low frequencies for adjacent letters with very far or very close outlet distances. In other words, the letter dissonance between two adjacent letters does not necessarily happen because of their outlets being too close nor too far.
Keywords:	Natural Language Processing, Letter Dissonance, Letter Outlets, Quran
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	A SYSTEMATIC REVIEW ON THE CHALLENGES OF ADOPTING ADVANCED SECURITY SOLUTIONS ONTO IOT-BASED SMART DEVICES
Author:	MATHURI GURUNATHAN, MOAMIN A. MAHMOUD, MOHAMMED NAJAH MAHDI
Abstract:	Recently, the Internet of Things (IoT) has been one of the most active research topics in Smart Applications that attracting much attention from both researchers and developers. IoT aims to connect billions of things by sharing and receiving information using Internet Protocol (IP) that enables IoT devices to store and access online data. However, despite the benefits of IoT in smart applications, security threats are expected to be increased substantially. Security in IoT is one of the most noteworthy challenges in the interconnected world. The Internet of Things will be profoundly joined in our lives now and more in our future, therefore, it is important to venture up and pay attention to cyber threats seriously. Although the increasing number of publications in the area of IoT devices security in smart applications, there still are limitations in the comprehensive literature review. To provide a clear insight into this limitation and support researchers, we need to understand the current state of research in this area. Consequently, this study presents a review of articles published from 2010 to 2019 on IoT devices security in smart applications. A manual search is used to ensure the retrieval of all relevant studies. The final 60 selected papers are reviewed and relevant information extracted based on a set of research questions. The review aims to altogether examine the observational on validating IoT security devices protocol development.
Keywords:	IoT; Smart Devices; Security And Privacy; Systematic Review.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	THE EFFECT OF MANUAL SKETCHING ON ARCHITECTURAL DESIGN PROCESS IN DIGITAL ERA
Author:	AUGUSTINUS MADYANA PUTRA, GAGOEK HARDIMAN, AGUNG BUDI SARDJONO, EVARISTUS DIDIK MADYATMADJA, GERARDA ORBITA IDA CAHYANDARI
Abstract:	The advancement of digital technology allows an architect to be more precise and detail in designing a building. However, the ability to draw manually is an added value for architects. Manual sketching or drawing allows a dynamic relationship between eyes, brain, and hand movement. It is a unit in building perception. In architectural education, a manual sketching subject is taught in the early semester. The purpose is to improve perceptions of form and space. This research is important to understand the role of manual sketching in the world of design. The research involved second-semester architecture students who have the average ability. The participants were 138 students. The research was conducted by collecting questionnaire data and testing students’ drawing skills. The drawing test was conducted to determine the ability of students to recall building objects that had been practiced before. The test results were then assessed and correlated with questionnaire results. Research results showed that the on-site drawing of an object strengthens visual memory. So, manual drawing is a necessary provision to collaborate with digital technology in designing buildings in the present and future
Keywords:	Architectural Sketches, Learning Process, Visual Memory
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	A NOVEL SENTIMENT CLASSIFICATION MODEL USING GRASSHOPPER OPTIMIZATION ALGORITHM WITH BIDIRECTIONAL LONG SHORT TERM MEMORY
Author:	D. ELANGOVAN, V. SUBEDHA
Abstract:	In recent times, social media has received great attention among the research communities towards the domain of sentiment analysis (SA). The proficient design of SA is needed to improve the service and product qualities for the marketing and financial schemes for increasing the company’s profit and user satisfaction. Although several SA techniques are available in the literature, it is needed to further enhance the classification results of the user review which helps to comprehend the user reviews, thereby quality of the products can be improved. This study devises an effective SA and classification technique using grasshopper optimization algorithm (GOA) with bidirectional long short term memory (Bi-LSTM), named GOA-BiLSTM. The GOA-BiLSTM model involves word2vec based feature extraction process to derive a useful set of features. In addition, Bi-LSTM based classifier is applied to determine the optimal class label of the extracted features. Moreover, GOA is utilized for the hyperparameter optimization of the Bi-LSTM model. To ensure the better outcome of the GOA-BiLSTM model, an extensive set of simulations were carried out on four datasets. The simulation outcome verified the superiority of the GOA-BiLSTM model by accomplishing a higher accuracy of 99.57%, 99. 71%, 99. 06%, and 98.98% on the applied Canon, Nokia DVD, and iPod dataset respectively.
Keywords:	Sentiment analysis, Classification, Deep learning, Parameter optimization, Bi-LSTM
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	IMPROVED N2N TRUST BASED MECHANISM TO MITIGATE THE EFFECT OF WORMHOLE IN DYNAMIC SOURCE ROUTING PROTOCOL
Author:	NISHA SHARMA, MUKESH KUMAR GUPTA, DURGA PRASAD SHARMA, M. K. BANERJEE
Abstract:	The Wireless Ad-hoc network or Mobile Ad-Hoc network is multi-hop network and rely on dynamic infrastructure where nodes are generally mobile and require signal as a communication component. Mobile Ad-Hoc Network (MANET) is growing more popular due to its advantages of being adaptable, quick to set up, cost-effective, and durable. On the other hand, it has limitations like limited wireless range, frequently changing routes, packet drop, heterogeneous devices, and limited battery power. Hence, MANET is vulnerable to various types of security attacks unlike the infrastructure-based wired network. One of the most dangerous attack is wormhole attack which causes major impact on routing. In view of the necessity to provide secure routing, identification of malicious node is not enough, isolation of malicious node is necessary without considerable overheads in MANETs. This research work presents Node to Node (N2N) Trust based mechanism for secure routing in MANETs based on Node-to-Node packet delay. It uses aggregated N2N trust to detect source malicious node of wormhole and isolate the malicious node to ensure that the malicious node does not intercept the routing. Thus, the mechanism offers routing of data traffic securely with improved throughput. In this work, we have employed NS3 (Network Simulator-3) simulator for experimental analysis and (Dynamic Source Routing) DSR protocol as reference for implementation of N2N Trust based algorithm.
Keywords:	Wormhole, Trust Based, DSR, MANET, Packet Delay, Accuracy, Innovation.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	PERFORMANCE ANALYSIS OF SUPERVISED MACHINE LEARNING TECHNIQUES FOR CYBERSTALKING DETECTION IN SOCIAL MEDIA
Author:	ARVIND KUMAR GAUTAM, ABHISHEK BANSAL
Abstract:	In the modern days of life, people use many social media sites for information sharing among friends, relatives, and others for personal, business, and official purposes. The use of social media platforms is also raising serious issues in the form of cyberstalking. Cyberstalking has been identified as a growing anti-social problem that affects educational institutions, victims, and entire human society. An intelligent system is required to detect cyberstalking in social media. In this paper, we proposed a cyberstalking detection model and analyzed the performance of six popular supervised machine learning algorithms, namely Logistic Regression, Support Vector Machines (SVM), Random Forest, Decision Trees, K-Nearest Neighbor, and Naive Bayes. These machine learning algorithms were implemented with two feature extraction methods, Bag of Words and TF-IDF, on two datasets of different sizes and distribution containing 35734 and 70019 comments and tweets, respectively. Performance of algorithms was measured in terms of Accuracy, Precision, Recall, f-score, training time, and prediction time. Our experimental results show that Logistic Regression and Support Vector Machine were top performer algorithms for both datasets with both feature extraction methods. Logistic Regression (92.6% with BOW and 92% with TF-IDF) and Support Vector Machine (92.5% with TF-IDF and 91.9% with BOW) achieved the highest accuracy on dataset-1. Logistic Regression and Support Vector Machine also achieved the highest Precision (96.4% and 96.6% respectively) and F-Score (94.3% and 93.8% respectively), while Naïve Bayes provides the best Recall (97.6% with TF-IDF on dataset-1) for both datasets.
Keywords:	Cyberstalking Detection, Machine Learning, Features Extraction, Bag of Words, TF-IDF, Performance Metrics.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	MACHINE LEARNING BASED PERFORMANCE ANOMALY AVOIDANCE SCHEME FOR MEDICAL IOT APPLICATIONS
Author:	ILLAPU SANKARA SRINIVASA RAO, V. SIVAKUMAR
Abstract:	The Restricted access window (RAW) method, which is part of the IEEE 802.11ah standard for the Internet of Things (IoT), reduces the effect of collisions on the network while increasing the overall performance of the network. However, in multi-rate IoT networks based on IEEE 802.11ah, performance anomaly degrades the network performance. The Machine Learning based Performance anomaly avoidance with cluster-based grouping (MLPA-CBG) scheme proposed in this article is intended to address this issue. The proposed scheme makes use of the self-organizing map neural network for the purpose of categorizing devices as per bit rate. Then, each group is assigned a time slot that allows them to access the channels. CBG outperforms the default uniform grouping scheme in terms of throughput, delay and energy consumption.
Keywords:	CBG, SOM, IoT, anomaly, Machine Learning.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	COVID-19 DISEASE RECOGNITION USING DISTRIBUTED DATA MINING AND DEEP LEARNING
Author:	AHMAD ABADLEH, AFNAN AL-SARAIREH, HAMZEH EYAL SALMAN, ANAS AL-AKASASBEH, SAQER ALJAAFREH, AWNI HAMMOURI, RAFAT AL-MSIE’DEEN, AHMAD HASSANAT
Abstract:	Since the first COVID-19 case was reported at the end of 2019 in China, the COVID-19 virus moved to almost every country with rapidly spread among people. It has a destructive effect on people's health and their daily life. The world health organization (WHO) in April 2020 officially declared the COVID-19 as a pandemic. To date, there is no specific treatment for COVID-19. Therefore, the detection of COVID-19 disease is required to avoid the fast spread of disease and halt its chain. In this article, we suggest an approach to recognize COVID-19 through X-ray images using distributed data mining techniques and Convolutional Neural Networks. To validate the proposed approach, we apply it to a public dataset consisting of 2,905 chest X-ray images for COVID-19 patients in addition to Viral Pneumonia and Normal images. The results show that the suggested approach gives promising results in terms of well-known evaluation metrics in the subject.
Keywords:	COVID-19, Recognition, Classification, Deep Learning, CNN, Distributed Data Mining.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	OPTIMIZED MIN-MIN TASK SCHEDULING ALGORITHM FOR SCIENTIFIC WORKFLOWS IN A CLOUD ENVIRONMENT
Author:	SALLAR SALAM MURAD, ROZIN BADEEL , NASHAT SALIH ABDULKARIM ALSANDI, RAFI FARAJ ALSHAAYA, REHAM A. AHMED, ABDULLAH MUHAMMED, MOHD DERAHMAN
Abstract:	Resource allocation and cloudlets scheduling are fundamental problems in a cloud computing environment. The scheduled cloudlets must be executed efficiently by using the available resources to improve system performance. To achieve this, we propose a new noble mechanism called Optimized Min-Min (OMin-Min) algorithm, inspired by the Min-Min algorithm. The objectives of this work are: i) to provide a comprehensive review of the cloud and scheduling process; ii) to classify the scheduling strategies and scientific workflows; iii) to implement our proposed algorithm with various scheduling algorithms (i.e., Min-Min, Round-Robin, Max-Min, and Modified Max-Min) for performance comparison, within different cloudlet sizes (i.e., small, medium, large, and heavy) in three scientific workflows (i.e., Montage, Epigenomics, and SIPHT); and iv) to investigate the performance of the implemented algorithms by using CloudSim. The main goal of this study is to obtain optimum results that satisfy the minimum completion time and achieve better utilization of resources, which lead to increased throughput. The algorithms were implemented in a Java environment. Results were discussed and analyzed by using formulas and were compared in percentages. According to the simulation results, the proposed algorithm produces the best solution among all algorithms in the proposed cases.
Keywords:	Cloud computing, Scheduling, Workflow scheduling, Scientific workflow, DAG
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	EVALUATION OF SUCCESSFUL ERP-BASED INFORMATION SYSTEMS WITH DELONE AND MCLEAN INFORMATION SUCCESS MODEL
Author:	MAY YESSI ASIH JAYA, JAROT S. SUROSO
Abstract:	Private companies in case studies are engaged in companies that provide goods and services in the field of IT (Information Technology) and use ERP (Enterprise Resource Planning) as a solution to carry out the company's operational activities. The private company that is the site of a new case study was established in 2015 and only has about 60 employees. The costs incurred by the company for ERP implementation are significant, while the implementation results have never been evaluated or measured. Therefore, it must be re-evaluated to find out what factors can affect the success of the implementation with the expected results of ERP as a basis to add new modules if needed. DeLone and McLean's success measurement method is used as a modelling in researching with six measurements: System Quality, Information Quality, Use, User Satisfaction, Individual Impact, and Organization Impact. The sample that will be the object of the research is as many as 30 people, and the data taken is processed using SmartPLS. The results showed that four hypotheses were rejected, and four theories were accepted. The research indicates that ERP Information Quality has a significant influence on Use, ERP Information Quality has a considerable influence on ERP User Satisfaction, ERP User Satisfaction has significant power on the Individual Impact of ERP, and Individual Impact of ERP has a substantial effect on the Impact of ERP Organizations on private companies.
Keywords:	Evaluation, ERP, DeLone McLean, Information Systems, SmartPLS.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	MACHINE LEARNING-BASED AUGMENTED REALITY FOR IMPROVED TEXT GENERATION THROUGH RECURRENT NEURAL NETWORKS
Author:	ANASSE HANAFI, MOHAMED BOUHORMA, LOTFI ELAACHAK
Abstract:	1ANASSE HANAFI, MOHAMED BOUHORMA, LOTFI ELAACHAKMachine learning (ML) is a large field of study that overlaps with and inherits ideas from many related fields such as artificial intelligence (AI). The main focus of the field is learning from previous experiences. Classification in ML is a supervised learning method, in which the computer program learns from the data given to it and make new classifications. There are many different types of classification tasks in ML and dedicated approaches to modeling that may be used for each. For example, classification predictive modeling involves assigning a class label to input samples, binary classification refers to predicting one of two classes and multi-class classification involves predicting one of more than two categories. Recurrent Neural Networks (RNNs) are very powerful sequence models for classification problems. However, in this paper, we will use RNNs as generative models, which means they can learn the sequences of a problem and then generate entirely a new sequence for the problem domain, also, we propose an architecture of a learning application that benefits from the advantages of both machine learning and augmented reality to provide a better learning experience and help teachers build adaptive educational content using the proposed model.
Keywords:	Artificial Intelligence, Machine Learning, Classification, Recurrent Neural Networks, Sequence Models, Generative Models.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	FACE RECOGNITION USING DEEP LEARNING XCEPTION CNN METHOD
Author:	PALLAVARAM VENKATESWAR LAL, UPPALAPATI SRILAKSHMI, D.VENKATESWARLU
Abstract:	The continual development of computer vision technology is one of the main research paths in the area of computer vision during recent years. It detects, tracks, recognizes, or authenticates human appearances from any picture or video taken through a digital camera and provides accurate and quick enough recognition functions for commercial use. Widely utilized in mobile payments, safe cities, criminal investigations, and other areas. Much research has progressed into face detection, identification and safety, the main problems are the consideration of those objects that had "different sizes" and "different aspects ratios" in a single framework that prevented or exceeded human level accuracy in human face appearance, such as noise in face images, opposite illumination,,Haar cascade was found to produce optimum accuracy while analyzing the multi focus faces using FERET database and the LFW database, and utilizes Xception (Depth Wise Separable). CNN is used for extracting the feature. Finally, classification is carried out. The suggested approach obtained FERET accuracy by about 96.73%, and LFW data by approximately 98.45%. The research findings have shown that the predicted technique exceeds existing methods.
Keywords:	Face Recognition, Haar cascade, LBP, CNN, Deep Learning, Artificial Neural Network
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	JOB OPPORTUNITIES RECOMMENDATION FOR VISUALLY IMPAIRED PEOPLE USING NATURAL LANGUAGE PROCESSING
Author:	AZIMAH ABDUL GHAPAR, FENINFERINA AZMAN, MASYURA AHMAD FAUDZI, HASVENTHRAN BASKARAN, FIZA ABDUL RAHIM
Abstract:	This paper highlights the importance of job recommendation system and its function in helping job seekers to find available job opportunities. As various efforts focusing on job recommendation systems for sighted people, this study aims to explore how Natural Language Processing (NLP) techniques can assist visually impaired people in finding the suitable job. In this paper, we propose a job recommendation model architecture that enables the job seekers to get the most suitable job match for their profile and also allows the employers to identify qualified individuals for specific job position. The solution is based on an NLP program that will be hosted through an Application Programming Interface (API) service and connected to the Web interface. A comprehensive procedure in the proposed architecture is divided into three layers: input layer, data processing layer, and output layer. The proposed solution is expected to help visually impaired people get the result for the job that matches their qualifications and experiences and also for the employer to find a suitable candidate for the advertised position.
Keywords:	Job Matching, Candidate Filtering, NLP, Job Recommendation, Recommender Systems
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	A SECURITY SYSTEM FOR E-EXAMS USING AN IoT AND FOG COMPUTING ENVIRONMENT
Author:	DALIA KHAIRY, MOHAMED A. AMASHA, RANIA A. ABOUGALALA, SALEM ALKHALAF, MARWA F. AREED
Abstract:	A recently significant confirmation has adopted to e-learning systems are in great demand. Students, instructors, and examiners share large amounts of data, which should be transmitted securely. One of the most support infrastructures to merging intelligent devices, data analysis, and cybersecurity is the Internet of Things(IoT). Specifically, when combined with Fog and cloud potentials to strengthen the performance of various latency-sensitive and computing-intensive. This paper presents the IoT-Fog-Cloud framework to provide security factors in sharing E-exam which poses several security challenges, such as fine-grained access control and security preservation of E-exam. Further, the proposed framework supports bringing closer the services to the students. Besides, this paper improves the efficiency of E-exam data analysis, reduces the encryption burden in terms of computation cost on user’s devices by offloading part of encryption cost to fog servers, and provides fine-grained access control to E-exam content by encrypting with different cryptographic techniques. IoT–fog–cloud framework works in consideration of two main elements: the layer components and the layer processes. Layer components to be integrated include the FGNs, cloud data centers, and GFNs. In layer processes, a series of benefits can be realized, since distribution processes help students to reduce latency and enhance response times and the preservation of privacy and security . Finally, this paper shows that the proposed IoT-Fog-Cloud framework can achieve data confidentiality, fine-grained access control, collusion resistance, and unforgeability to ensure secure procedures to apply the proposed framework.
Keywords:	Internet of Things (IoTs), E-Exams, Fog Computing, Security system, E-learning.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	SIMULATION AND QOS ANALYSIS OF TCP, UDP/AODV
Author:	SAED THUNEIBAT
Abstract:	One of the rapidly growing technologies is the ad-hoc (MANET) network, the standards, technical issues, and security aspects are not fully studied and established. Routing is an important function for the reliable utilization of networks. In this paper, we design and build a simulation based system, we compare AODV protocol with TCP and UDP. We design and simulate Ad-hoc network in both cases using NS-2 software. Results of simulation compare delay, jitter, and throughput values for these cases versus simulation time.
Keywords:	TCP, UDP, AODV, WLAN, QoS
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text

Title:	MODELING THE FAIR VALUE OF BANKING COLLATERAL USING REAL ESTATE WEBSITE DATA AND MACHINE LEARNING TECHNIQUES - THE CASE OF CASABLANCA CITY, MOROCCO
Author:	YOUSSEF TOUNSI, HOUDA ANOUN, LARBI HASSOUNI
Abstract:	In recent years, big data has been widely used to understand emerging trends in several markets. With this paper, we consider the use of real estate websites data and machine learning in the problem of knowing the current fair value of banking collateral in Morocco. In our study, we are going to utilize the online data, containing housing sales advertisements, extracted from three websites: (Avito.ma, Mubawab.ma and Sarouty.ma), popular online portals for real estate services in Morocco, in order to develop forecasting models of apartment prices using artificial intelligence for the city of Casablanca. Each record of the database contains information on the listed housing unit (asking price, district, floor, area, number of rooms, balcony, terrace…), on the building (elevator, garage, garden, etc.), on the ad (publication date, apartment sector) and a short description. After collecting the database and the deduplication process, we make additional controls on the dataset to address potential incoherence errors in the data. After validating the clean dataset against official statistical sources, we construct forecasting models for real estate sale prices, based on artificial intelligence and statistical methodologies.
Keywords:	Housing Price Prediction, Mortgage lenders, Machine Learning Algorithms, Big Data.
Source:	Journal of Theoretical and Applied Information Technology 31^st January 2022 -- Vol. 100. No. 02 -- 2022
Full Text