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

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

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

Journal of Theoretical and Applied Information Technology
June 2022 | Vol. 100 No.12

Title:	ENHANCED CT-IMAGE FOR COVID-19 CLASSIFICATION USING RESNET 50
Author:	LOBNA M. ABOU EL-MAGD, AMIRA. A. ELSONBATY, MANAL SOUBHY ALI ELBELKASY
Abstract:	Disease caused by the coronavirus (COVID-19) is sweeping the globe. There are numerous methods for identifying this disease using a chest imaging. Computerized Tomography (CT) chest scans are used in this study to detect COVID-19 disease using a pre-train Convolutional Neural Network (CNN) ResNet50. This model is based on image dataset taken from two hospitals and used to identify Covid-19 illnesses. The pre-train CNN (ResNet50) architecture was used for feature extraction, and then fully connected layers were used for classification, yielding 97%, 96%, 96%, 96% for accuracy, precision, recall, and F1-score, respectively. When combining the feature extraction techniques with the Back Propagation Neural Network (BPNN), it produced accuracy, precision, recall, and F1-scores of 92.5%, 83%, 92%, and 87.3%. In our suggested approach, we use a preprocessing phase to improve accuracy. The image was enhanced using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, which was followed by cropping the image before feature extraction with ResNet50. Finally, a fully connected layer was added for classification, with results of 99.1%, 98.7%, 99%, 98.8% in terms of accuracy, precision, recall, and F1-score.
Keywords:	COVID-19; CNN; Resnet50; BPNN; CLAHE; CT-scan.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	THE EFFECT OF AMBIDEXTROUS LEADERSHIP AND SOCIAL MEDIA ON CORPORATE PERFORMANCE: THE MEDIATING ROLE OF DIGITAL TRANSFORMATION
Author:	MARINDRA BAWONO, IDRIS GAUTAMA, AGUSTINUS BANDUR, FIRDAUS ALAMSJAH
Abstract:	This paper aims primarily to examine the effect of ambidextrous leadership and social media on company performance and to measure the mediating role of digital transformation of telecommunications companies in Indonesia. For this main purpose, a quantitative research dimension is applied with particular reference to surveys. This research was conducted using quantitative methods to collect and analyze data, integrate findings, and draw conclusions. The sample in this study amounted to 180 (0.72%) complete questionnaires which were processed in quantitative testing. The main results show that Based on the discussion above, it is concluded that ambidextrous leadership has a positive effect on company performance, ambidextrous leadership has a positive effect on digital transformation, Social Media has a positive effect on digital transformation, Social Media has a positive effect on Firm performance and Digital transformation has a positive effect on Firm performance. . The study suggests utilizing extraordinary plans to identify external and internal situations during and after the coronavirus (COVID-19) pandemic.
Keywords:	Ambidextrous leadership, Social Media, Digital transformation, Corporate performance
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	ANALYSIS OF CROSSED DIPOLE ESA FOR WIRELESS COMMUNICATION APPLICATIONS
Author:	KATIREDDY. HARSHITHA REDDY, M. VENKATA NARAYANA, GOVARDHANI. IMMADI
Abstract:	A compact size of (35mm x 35mm) single band ESA has been simulated and fabricated for wireless communication applications like Bluetooth, cordless phone etc. The Design consists of a circular slot and it is embedded with cross type structures. The overall dimensions of this antenna are reduced to satisfy the rules of ESAs, two dipoles are arranged in a cross shape (plus shape) on the surface of the substrate inside the circular patch to achieve impedance bandwidth. The simulation of the ESA is done through HFSS and it is fabricated on FR4 with a thickness of 1.6mm, ℇr of 4.4mm and the size of ESA is 35mmx35mm. The return loss(S11) of the Simulated and fabricated proposed antenna is greater than -10db which is acceptable for practical applications and there is a good agreement between the simulated and fabricated results.
Keywords:	ESA, Cross shape, Circular slot, Return loss and Bluetooth.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	IMPACT OF SCRUM PRACTICE ON SOFTWARE DEVELOPMENT IN INDIVIDUAL AND TEAM PERFORMANCE DURING COVID-19 PANDEMIC
Author:	ANDRE LAZUARDI AMIN, RIYANTO JAYADI
Abstract:	Software development has always been an essential sector in companies that implement information technology, pandemic impacting how people manage IT projects. Scrum is one of the most used frameworks in Agile methodology commonly adopted in multiple companies as the concept has a robust way to track the task and people. This paper seeks to understand whether the implementation of Scrum will affect employee performance during the pandemic, either in individual or team aspects. The data was analyzed using inferential statistics and structural equation modeling. The questionnaire received 117 responses from scrum practitioners in Indonesia. Factor analysis supported the validity of the scales, and shows good coefficient of determination percentage for the impact of scrum practice on the perceived individual performance with 62% (majorly affected by self-determination and self-control) and perceived team performance with 71.1% (majorly affected by trust and communication).
Keywords:	Project Management, System Information, Agile, Scrum, Employee Performance
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	UNDERSTANDING EMPLOYEE SECURITY BEHAVIOR IN USING INFORMATION SYSTEM OF ORGANIZATIONS: EVIDENCE FROM JAKARTA GREATER AREA, INDONESIA
Author:	RIDIPURNOMO, RIYANTO JAYADI
Abstract:	Almost all organizations currently have implemented the use of technology in running their business to enhance productivity and performance, there by gaining competitive advantage and achieving strategic goals. However, the use of this technology is very vulnerable to data breaches. Data breach incidents became a big topic in Indonesia during 2020 since the leaks of millions of users' personal data from some of the largest e-commerce sites. This incident should certainly be a warning to all organizations, especially in Jakarta Greater Area (Jabodetabek), Jakarta, Indonesia, to pay more attention to the security of their company's information. Most of organizations have prioritized a technology approach to protect their information assets from potential attacks. Some of the commonly used information security technologies are firewall devices, Antivirus software, IDS, etc. Although the prevention of attacks by technical means is important, the risk of insider threats must be taken into account, Users or employees tend to be the main factor in many information security breaches. This research aims to determine whether security education & training, information security awareness, employee relationships, employee accountability, organizational culture, and national culture have a significant effect on employee security behavior. The empirical analysis relies on a survey data from a cross section of employees from 10 companies in Jabodetabek and a structural equation modeling approach via SmartPLS 3. The results showed no direct and significant effect of security education & training on improving employee security behavior in Jabodetabek. The security education & training influences all mediators (information security awareness, employee relationship and employee accountability), and all the mediators influences employee behavior in using the company's information system. The most influential variable is employee accountability. Organizational culture and national culture influence employee behavior in using company information systems.
Keywords:	Data Breach, Employee Security Behavior, Security Education & Training, Information Security Awareness, Employee Relationships, Employee Accountability, Organizational Culture, National Culture
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	IMPLEMENTATION OF RECOMMENDATION SYSTEM IN E-COMMERCE USING APPROXIMATE NEAREST NEIGHBOR
Author:	HANDY TANTYO, TUGA MAURITSIUS
Abstract:	At least 20 e-commerce businesses in Indonesia have stopped operating due to human resource problems. The recommendation system is an important feature in e-commerce which was initially done manually. However, a computing field has emerged that can replace human labor in recommendation systems, reduce human errors and work more efficiently. This paper aims to implement an efficient and scalable recommendation system using Machine Learning techniques. The content-based filtering used in this paper uses the Approximate Nearest Neighbor algorithm with different indexes that provide similar product recommendations. Data is collected from Tokopedia product information, which is divided into five categories. The optimal Nprobe is found at 6% which is the standard Nprobe for each index. The index that has the best recall@R parameter, fastest prediction time and training time respectively are IDMap,Flat, IVF1024_HNSW32,Flat and IDMap,Flat.
Keywords:	E-commerce, Recommendation System, Machine Learning, Content Based Filtering, Approximate Nearest Neighbor
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	ENHANCED SPATIAL PYRAMID POOLING AND INTERSECTION OVER UNION IN YOLOV4 FOR REAL-TIME GROCERY RECOGNITION SYSTEM
Author:	SAQIB JAMAL SYED, PUTRA SUMARI, HAILIZA KAMARULHAILI ,VALLIAPPAN RAMAN, SUNDRESAN PERUMAL ,WAN RAHIMAN
Abstract:	The ability to recognize a grocery on the shelf of a retail store is an ordinary human skill. Automatic detection of grocery on the shelf of retail store provides enhanced value-added to consumer experience, commercial benefits to retailers and efficient monitoring to domestic enforcement ministry. Compared to machine vision-based object recognition system, automatic detection of retail grocery in a store setting has lesser number of successful attempts. In this paper, we present an enhanced YOLOv4 for grocery detection and recognition. We enhanced through spatial pyramid pooling (SPP) and Intersection over union (IOU) components of YOLOv4 to be more accurate in making recognition and faster in the process. We carried an experiment using modified YOLOv4 algorithm to work with our new customized annotated dataset consist on 12000 images with 13 classes. The experiment result shows satisfactory detection compare to other similar works with mAP of 79.39, IoU threshold of 50%, accuracy of 82.83% and real time performance of 61 frames per second
Keywords:	Grocery Recognition, Yolov4, Object Localization, Deep Learning, Machine Vision
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	PERFORMANCE ANALYSIS OF OBJECT DETECTION MODELS FOR VEHICLE-RELATED IMAGE SERVICES
Author:	JUN-HYUNG KO, NAMGI KIM
Abstract:	Object detection is an actively researched field of computer vision, and notable research outcomes have been presented through an integration with deep learning. However, most previous studies on object detection have focused on evaluating the object detection performance for multiple classes. To a practical extent, such detection contrasts with how the type of classification required for object detection models is limited to a few numbers of classes. For example, the object detection classes required for autonomous vehicles or in vehicle detection services are limited to small specific classes, such as vehicles, persons, and road signs. In other words, the need has arisen to confirm which model exhibits an excellent performance for a small, specialized class such as vehicle object detection. Therefore, we evaluate representative object detection models to identify which models is more appropriate for vehicle object detection services. The results show that CenterNet [9] achieves the best performance for vehicle object detection during autonomous driving and for CCTV use among the three models, followed by YOLOv4 [7] and SSD [8].
Keywords:	Object detection; Image processing; Deep learning
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	AUDIO STEGANOGRAPHY METHOD USING LEAST SIGNIFICANT BIT (LSB) ENCODING TECHNIQUE
Author:	EESA ABDULLAH ALSOLAMI
Abstract:	MP3 is one of the most widely used file formats for encoding and representing audio data. One of the reasons for this popularity is their significant ability to reduce audio file sizes in comparison to other encoding techniques. Additionally, other reasons also include ease of implementation, its availability and good technical support. Steganography is the art of shielding the communication between two parties from the eyes of attackers. In steganography, a secret message in the form of a copyright mark, concealed communication, or serial number can be embedded in an innocuous file (e.g., computer code, video film, or audio recording), making it impossible for the wrong party to access the hidden message during the exchange of data. This paper describes a new steganography algorithm for encoding secret messages in MP3 audio files using an improved least significant bit (LSB) technique with high embedding capacity. Test results obtained shows that the efficiency of this technique is higher compared to other LSB techniques. The aims to add effectiveness and performance for hide message in MP3 file and explains all detail in steganography process in MP3 files, and The new proposed method was able to increase the capacity and robustness, while improving imperceptibility.
Keywords:	Steganography; Least Significant Bit (LSB); MP3.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	DIGITIZING IN BUSINESS MODEL INNOVATION: PRELIMINARY RESEARCH OF COURIER, EXPRESS, AND PARCEL SECTORS
Author:	CHARLES SITORUS, IDRIS GAUTAMA SO, ASNAN FURINTO, WIBOWO KOSASIH
Abstract:	This study aims to identify digital business model innovations carried out by Indonesian courier service companies to meet customer needs. This research also uses three case studies and several references or previous research as the main data sources. This study uses a qualitative approach with the Historical method, with the sampling method used is a purposive sample with three case studies at DiDi Taxi, Cisco, Dell companies. This study found that e-commerce needs to make some innovations in adjusting to the needs of today's customers, especially in the era of digitalization. Some of the innovations that can be done consist of product terms, service features, customer satisfaction, involvement in the e-commerce marketplace, and in terms of delivery patterns. Based on this, this study designs several recommendations based on crucial issues that need to be studied further from the issue of digital business innovation models in Indonesian courier service companies. The results of this study are expected to be able to recommend several crucial issues that need to be studied further from the issue of digital business innovation models in Indonesian courier service companies. Therefore, this review is expected to initiate further research related to the scope of the research.
Keywords:	Digitalization, Business Model Innovation, Case-Study, Courier, Express, Parcel Sectors
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	SOLVING A NEW MATHEMATICAL MODEL FOR A PERIODIC VEHICLE ROUTING PROBLEM BY NEIGHBORHOOD SEARCH METHOD
Author:	MARLAN, HERMAN MAWENGKANG
Abstract:	For a Periodic Vehicle Routing Problem (PVRP), this study offers a new mathematical model which optimizing vehicle travel expenses based on many assumptions. Periodic planning includes consideration of the following four issues that is a vehicle routing problem with time windows (VRPTW), a capacitated vehicle routing problem (CVRP), a vehicle routing problem with split service (VRPSS) and a vehicle routing problem with simultaneous pickup and delivery (VRPSPD). In large-scale issues, the computational complexity of this problem can be handled by any optimization program in a reasonable amount of time since it is based on a single model that we have created. In this paper a neighborhood search meta-heuristic is proposed.
Keywords:	Periodic VRP, Logistics, Split Service, Meta-heuristic, Neighborhood Search
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	MOBILE APPLICATION FOR PRODUCTS COMMERCIALIZATION IN PULAU TUBA, LANGKAWI USING AGILE DEVELOPMENT
Author:	MUHAMMAD AZIZI MOHD ARIFFIN, MOHAMAD YUSOF DARUS, MUHAMMAD ADLAN AKMAL ABDUL AZIM KHOR
Abstract:	Digital Divide is one of the factors which cause income inequality and poverty among the rural population. In Malaysia, one of the poorest rural communities is Pulau Tuba Langkawi. The Island is located 5 kilometres away from the main Pulau Langkawi island, rich with forest herbs, seafood, and natural beauty. Although the island has basic infrastructure such as electricity, running water and a telecommunication tower, the population lived in poverty as half of the population has a monthly income of RM500 although they have an abundance of natural produce. To address the problem and poverty among the Pulau Tuba population, this paper proposed an easy-to-use e-commerce application using a dynamic mobile and web-based framework for commercializing the rural area product to the external market. The design of the proposed e-commerce application will incorporate a simple interface to help users with a limited ICTs skillset. The development of the mobile application uses Agile methodology to enable continuous features development to cater for the needs of the rural population at the later stage of deployment. Moreover, the application was developed using the Ionic framework, Angular for frontend and Firebase for back-end implementation. After the mobile application has been developed, several individuals in Pulau Tuba are chosen as a tester for the Beta version of the mobile application. Based on tester feedback, the majority agree that the apps help them to market their product and the apps are easy to use even for individuals with no ICTs skills. This has the potential to ease the process of commercializing the rural area product and eventually reduce the poverty among the island population.
Keywords:	E-Commerce, Digital Divide, ICTs, Rural Area Development, Internet, Agile Methodology
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	AUTOMATION OF INCIDENT RESPONSE AND IT TICKET MANAGEMENT BY ML AND NLP MECHANISMS
Author:	M.VENKATA SUBBARAO, KASUKURTY VENKATARAO, CH. SURESH
Abstract:	In todays digital world, Ticket Management Systems are widely utilized in various businesses and organizations since they are essential for efficiently resolving client requests and difficulties. Moreover, in real-world application contexts (e.g., technology support platforms and defect detection systems), properly labeling new requests is essential to improving ticket handling quality, grade and productivity. This research aims to discover the factors affecting customers’ online ticket purchasing behaviors and proposes an effective technique for systematic ticket categorization that effectively clusters and labels. Information technology (IT) tickets quickly using Machine Learning and Natural Language Processing techniques. The framework’s performance in numerous ticket categorization jobs has been indicated by experimental results based on a specific usage situation that involves data from ticket mining the ServiceNow platform and filtering a vast dataset, among other things. To develop a Machine Learning model that significantly predicts an incident resolution category with supervised ML algorithms. The models’ performance was estimated using various NLP techniques LDA with TF-IDF and 3 Gram, and stop-word removal and lemmatization produced the best results, with a precision of 96.46 percent.
Keywords:	Natural language processing (NLP), Machine Learning, classification, Incident Response, Text Mining, Information Retrieval
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	PERFORMANCE EVALUATION BY FEATURE REDUCTION USING DEEP LEARNING FOR IDENTIFYING MALICIOUS WEBSITES
Author:	SHAIK IRFAN BABU, DR.M.V.P. CHANDRA SEKHARA RAO
Abstract:	Now a days, Internet activities are growing in exponential rate so are the criminal activities, with the growth of internet usage. Internet is also a source of malicious web pages. Automatic Malicious URL identification resulted a relative novel and sensitive security challenging area. The area would aim in aiding the users to overcome security threats due to the presence of malicious webpage’s resulting in a better network security. The present study makes attempt in assessing and identifying malicious websites, a malicious identification model is proposed using deep learning ideas. The present work uses the URL and HTML based features to identify malicious websites. PCA is applied to reduce features, dominating features are identified. It is found that dominating features play vital role in segregating the URLs into malicious and non-malicious. Dataset from PhishTank and Alexa is used in this study. Seven Layer Neural Network has shown significant improvements resulting in accuracy of 94%. The proposed work gave true-positive rate 95.51 and False-malicious rate 9.51.
Keywords:	PCA, Neural Network, TMR, FMR.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	DATA MANAGEMENT FRAMEWORK IMPLEMENTATION FOR FINANCIAL SERVICE AUTHORITIES (FSA): CASE STUDY IN ASIA PACIFIC REGION
Author:	RENDY DALIMUNTHE, WIRIANTO WIDJAYA, INDRAJANI SUTEDJA, ARMAND WAHYUDI HARTONO
Abstract:	The digital economy is transforming financial service industry, raising critical question for regulatory and supervisory authorities about the appropriate process, tools, and infrastructure to manage the explosion of data . Unfortunately, data governance is a new field in which guidance is limited and practical implementations among organizations are vary wildly due to various interpretation. While substantive practical progress has been made on how regulatory and supervisory agencies manage and govern their data, there is still a lack of academic literature that pivot towards the characteristics of resilient architecture of data management, particularly in financial regulatory & supervisory environment. Using the research method of benchmarking, this study analyses exemplary data management cases in four Asia Pacific’s financial supervisory agencies (FSA), to articulate resilient concepts and strategies that foster effective architecture of data management. Proprietary eighteen items of comparison are used to benchmarked data management and governance implementation in each FSA. Results of analysis yield three common underlying characteristics that define effective data management architecture for financial regulatory agencies. These characteristics can provide significant direction and be used as foundations in designing resilient and practical integrated data management architecture. Furthermore, the eighteen items of comparison formulated for this study can be utilized by other organizations wishing to conduct benchmarking study to extract the characteristics of data management and governance operations.
Keywords:	Data Management Architecture, Data Governance, Financial Regulators, Benchmarking
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	ATTITUDE AND COMPETENCE TO USE MADRASATI (M LMS) AMONG SCHOOL TEACHERS IN RIYADH, SAUDI ARABIA
Author:	HAMAD MUAYBID ALHARBI, HABIBAH AB JALIL, MUHD KHAIZER OMAR, MOHD HAZWAN MOHD PUAD
Abstract:	Attitude and competence are two factors that affect the acceptance and utilization of new technology in education. In this regard, the full utilization of the new Madrasati (M) technology among teachers in public schools in Riyadh is still challenging. Thus, this study aimed to determine the moderating effect of gender and age on the relationship between teachers’ attitudes and competence in utilizing M LMS technology in public schools in Riyadh, as mediated by behavioral intention. The survey method and quantitative approach were employed. Data were collected from 374 teachers out of the population of 13,782 teachers in schools implementing M LMS in Riyadh. The finding of the tested model showed a potential positive mediation role of BI on attitude (ATT) and competence (COM) to use M LMS among public school teachers in Riyadh. The overall mean showed that ATT1 was high among the eight items used after CFA testing, while ATT11 had the lowest mean score. Among the seven items used for CFA testing, COM18 had the highest mean score. The results also indicated that the utilization of M LMS is high among teachers. They visit M LMS three times a week and spend between 61–90 minutes per visit. The finding also revealed the direct effect of COM over ATT on M LMS utilization through mediator BI. The relationship between ATT and M LMS, as moderated by gender and age, is statistically insignificant, suggesting that ATT has no significant moderating effect on M LMS utilization among teachers. Meanwhile, COM to use M LMS positively and significantly affects M LMS acceptance and utilization in Riyadh. In conclusion, the COM to use M LMS plays a more crucial role in accepting and utilizing public school teachers in Riyadh than their ATT. Therefore, it is recommended that future studies use a longitudinal design to obtain more accurate findings.
Keywords:	Attitude, Competency, Madrasati (M LMS), Utilization
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	A CRITICAL ANALYSIS OF SWARM INTELLIGENCE FOR REGRESSION TEST CASE PRIORITIZATION
Author:	BAKR BA-QUTTAYYAN, HASLINA MOHD, YUHANIS YUSOF
Abstract:	In software development, applications always undergo frequent modifications to cope with the changing needs of the users. Hence, this will affect the reliability of the applications. Regression testing is used to tackle this problem in which test case prioritization (TCP) is considered as one of the effective approaches. Optimization methods are employed to enhance the proficiency of prioritizing test cases in terms of efficiency and effectiveness. Swarm intelligence (SI) algorithms are mostly applied to TCP as one of the effective optimization methods. This paper aims at providing state-of-the-art for TCP using SI algorithms. The methodological process of performing this review includes conducting a search in the Scopus database using predetermined keywords to obtain relevant primary studies where suitable papers have been selected according to a set of predefined criteria. Predefined research questions also provide a basis for assessing nominated studies. Hence, the most relevant papers (57 out of 420) have been identified, analyzed, and classified. Based on the findings, it is learned that the deployment of swarm intelligence algorithms in prioritizing test cases yields promising results. Moreover, this study also includes suggestions that can be deployed to improve existing studies.
Keywords:	Swarm Intelligence, Software Testing, Regression Testing, Test Case Prioritization, Optimization Algorithms
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	DATASET MISSING VALUE HANDLING AND CLASSIFICATION USING DECISION TREE C5.0 AND K-NN IMPUTATION: STUDY CASE CAR EVALUATION DATASET
Author:	WAHYU WIDYANANDA, MUHAMMAD FAUZAN EDY PURNOMO, MUHAMMAD ASWIN, PANCA MUDJIRAHARDJO, SHOLEH HADI PRAMONO
Abstract:	Data mining is a data analysis process using software to find certain patterns or rules from a large amount of data which is expected to find knowledge to support decisions. However, missing value presence in data mining often lead to loss of information. Information loss inside dataset such car evaluation can result in poor predictive models. The purpose of this study is to improve the performance of data classification with missing values precisely and accurately using Decision Tree C5.0 and k-NN Imputation. The test method is carried out using the Car Evaluation dataset from the UCI Machine Learning Repository. RStudio and RapidMiner tools were used for testing the algorithm. This study will result in data analysis of the tested parameters to measure the performance of the algorithm. Using test variations: 1. Performance at C5.0, C4.5, and k-NN at 0% missing rate. 2. Performance on C5.0, C4.5, and k-NN at 5-50% missing rate. 3. Performance on C5.0 + k-NNI, C4.5 + k-NNI, and k-NN + k-NNI at 5-50% missing rate. 4. Performance on C5.0 + CMI, C4.5 + CMI, and k-NN + CMI at 5-50% missing rate. The results show that C5.0 with k-NNI produce better classification accuracy than other tested imputation and classification algorithms. For example, for 35% missing in the dataset, this method obtains 93.40% in validation accuracy and 92% accuracy in the test. C5.0 with k-NNI also offers fast processing time compared with others methods.
Keywords:	Missing Value Handling, C5.0, k-NNI, R-Studio, RapidMiner
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	SENTIMENT ANALYSIS OF COVID-19 VACCINE WITH DEEP LEARNING
Author:	MARYAM NUSER, EMAD ALSUKHNI, AHMAD SAIFAN, RAMA KHASAWNEH, AND DINA UKKAZ
Abstract:	After the emergence of the Covid-19 virus, pharmaceutical companies began making vaccines against this virus. Peoples’ reactions towards vaccines varies between acceptance and rejection. Information about these reactions can be found in social media which has become the largest and best source of users' opinions on a specific topic nowadays. One of the most important social media through which this data can be collected is Twitter. It is important to analyze people's opinions about these vaccines to find out the percentage of supporters and opponents of vaccines. Sentiments analysis can be used to analyze people's opinions. In this paper, we proposed a hybrid deep learning model to analyze user sentiment towards the COVID-19 vaccine. The contributions of our work are to adopt an efficient-designed model by combines Convolutional Neural Network (CNN), which has the capability to extract features, and Long Short-Term Memory (LSTM), which can monitor and study long-term dependencies between words. And provide the proposed network topology setting that contributed in producing high performance in sentiment analysis of the COVID-19 vaccine tweets. Extensive experiments have been conducted on a data set of 13,190 tweets. The results proved that the proposed model with the proposed topology setting outperformed the other machine learning models.
Keywords:	CNN-LSTM, Deep learning, Hybrid Model, Natural Language Processing (NLP), Sentiment Analysis.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	QURANIC COLLOCATIONS EXTRACTION USING STATISTICAL MEASURES
Author:	MAJED ABUSAFIYA
Abstract:	Collocations are a common phenomenon in natural languages in general and in Arabic in specific. Quran is widely considered to be the most eloquent and authentic Arabic text. This fact should motivate researchers to explore and study the collocations of this miraculous book. One approach to find collocations for a given corpus is by identifying pairs of words that are more likely to exist adjacent than being separate using special statistical measures. Chi-squared, t and mutual information are three broadly accepted statistical measures that are used for this purpose. In this paper, these three statistical measures are used to extract the collocations of Quran. None of these measures gave perfect results. So, a human interaction is required to filter the best candidates from the found collocations. The t measure gave the best set of collocations. The other two showed bias towards pairs of adjacent words that are unique or exist with very low frequencies in Quran. To give a generic notion of Quranic collocations that are extracted using this approach, those that were found by the t measure are studied and categorized.
Keywords:	Natural Language Processing, Quran, Collocations, Statistical Approach, Algorithms
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	THE SENTIMENT ANALYSIS OF THE INDONESIAN PALM OIL INDUSTRY IN SOCIAL MEDIA USING A MACHINE LEARNING MODEL
Author:	RANGGA PRADIPTA, RIYANTO JAYADI
Abstract:	This research is a sentiment analysis of opinion data obtained from the Twitter social network about the palm oil industry in Indonesia. The opinion data used is text in Indonesian to show the palm oil industry in Indonesia and text in English to show issues of the palm oil industry happening globally. The palm oil industry in Indonesia is one of the strategic industries engaged in agriculture, so it is necessary to monitor public sentiment with information on the Internet, especially on social media. This research has produced a model for classifying public opinion on the palm oil industry from Twitter data. The data collection technique used is the Twitter Developer API, and it obtained 14,048 words for Indonesian and 12,421 words for English. This data collection begins in July and ends in September 2021. This study uses a machine learning model with the Naïve Bayes Classifier and Support Vector Machine algorithms to separate sentiment into two labeling classes, namely positive and negative, then compares which algorithm best serves to classify opinion data. The model generated by the Naive Bayes algorithm has the highest accuracy value, namely for domestic (Bahasa Indonesia) data of 82% and international (English) data of 85%.
Keywords:	Sentiment Analysis, Machine Learning, Naïve Bayes, Support Vector Machine (SVM), Palm Oil Industry
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	COMPARATIVE EVALUATION ON THE ATTRIBUTES OF SOFTWARE DEVELOPMENT COST MODEL WITH EXPONENTIAL AND INVERSE-EXPONENTIAL DISTRIBUTION PROPERTY
Author:	HYO JEONG BAE
Abstract:	In this study, attributes of software development cost were evaluated by applying the exponential type distributions (Exponential-exponential, Inverse-exponential) which are utilized in the reliability testing field to the software development model. Also, the proposed distribution models were compared with the Goel-Okumoto basic model to verify cost property, and the optimal development cost model was presented. For this study, a total solution was performed using software failure time data generated during desktop application operation, parameter calculations were solved using the maximum likelihood estimation (MLE) method. As a result, fist, when the testing cost per unit time and the cost of eliminating a single fault detected during the development testing process increase, the development cost increases, but the release time does not change. But, if the fault correction cost detected by the operator during normal system operation increases, the development cost increased along with the delay of the release time. Second, it can be confirmed that the Exponential-exponential distribution model is the most efficient among the proposed models as it has the best performance in terms of development cost and releasing time. Third, if software developers and operators can utilize this analysis information efficiently, they can predict and design a reasonable development process by analyzing the related cost and time attributes.
Keywords:	Goel-Okumoto, Exponential-exponential, Inverse-Exponential, mean value function, Software Development Model, Cost Attributes.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	SOFT VOTING MACHINE LEARNING CLASSIFICATION MODEL TO PREDICT AND EXPOSE LIVER DISORDER FOR HUMAN PATIENTS
Author:	MOHAMMAD A. ALSHARAIAH, LAITH H. BANIATA, OMAR AL ADWAN, ORIEB ABU ALGHANAM,AHMAD ADEL ABU SHAREHA, MOSLEH ABU ALHAJ, QAIS ABDALLAH SHARAYAH, MOHAMMAD BANIATA
Abstract:	The liver is the most significant organ in the human body since it handles a significant role in food digestion and progression in our body. Mainly it takes an essential part in enzyme activation, fat metabolism, bile synthesis, vitamin, glycogen, and mineral storage. Depending on the role it controls, it has a sophisticated accidental of coming in contact with harmful creation that goes inside the body. Hence, the diagnosis of liver disorder has been subjective at best, based on subjective approaches. Liver disorders are challenging to detect, and as a result, they are regularly overlooked in the early stages due to a lack of precise symptoms. Hyperbilirubinemia is one of the most substantial signs of most liver illnesses, and it can be demanding to differentiate early on. However, in most of cases, this isn't certain, and the ability to detect and confirm the presence of liver disease lead to a better understanding of enzyme levels. The prediction of liver illnesses has been done using a variety of machine learning techniques. In this investigation, the recommended ensemble soft voting classifier offers binary classification and utilize the ensemble of three machine learning algorithms: Decision Tree, Support Vector Machine, and Naive bayes classifiers to predict and expose liver disease by Binary Classification of the dataset into two particular types of patients with or without liver disease (patient suffering liver sickness or not). The unbalanced dataset comprises materials about human patient attributes such as Gender, Age, Alanine, Total Bilirubin, Aminotransferase, Aspartate Aminotransferase, Direct Bilirubin, Albumin, Alkaline Phosphatase, Globulin Ratio and the Result and Total Proteins Albumin. Furthermore, the accuracy and various error calculations of the predictions from the aforementioned algorithms are analyzed to recognize and identify the best- convenient algorithm.
Keywords:	Liver Disorders, Machine Learning Techniques, Unbalanced Data Set, Classification, Liver Hyperbilirubinemia
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	REVIEW ON FOREST FIRES DETECTION AND PREDICTION USING DEEP LEARNING AND DRONES
Author:	MIMOUN YANDOUZI, MOUNIR GRARI, IDRISS IDRISSI, OMAR MOUSSAOUI2, MOSTAFA AZIZI, KAMAL GHOUMID, AISSA KERKOUR ELMIAD
Abstract:	Forests everywhere in the world are essential components for protecting the biosphere. They strongly contribute to the global carbon cycle and sustain a wide variety of plant and animal life forms. In many areas of the globe, forest fires are one of the major threats to living beings; it leads the ecosystem in jeopardy, including animals, plants, and even people. Last year, the Mediterranean and North African regions were devastated by wildfires. The earlier discovery of forest fires is strongly required to save lives and properties. Forest fires detection or prediction are difficult tasks because wildfires start small and are difficult to see from a distance, and then can quickly spread to become large and dangerous fires. The combination of drones and deep learning can be used to detect wildfires using images with high accuracy. The use of drones can help to identify the location of the fire and its spreading area, while deep learning can be used to identify the characteristics of the fire. This combination is a key foundation to create a system capable to detect wildfires more accurately. This paper examines current state-of-the-art published research papers on detecting forest fires using deep learning and drones.
Keywords:	Forest Fires, Wildfire, Deep Learning, Drone, UAV
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	CHOOSING A STRATEGY FOR THE LONG-TERM DEVELOPMENT OF THE COMMUNICATION SYSTEM FOR RURAL AREAS
Author:	AMIRALI SEILOV, SHAKHMARAN SEILOV, YERDEN ZHURSINBEK
Abstract:	Strategies that include communication systems for rural development as a significant aspect of rural development are utterly needed. The article proposes a strategy of a long-term development of communication system for rural areas, used to solve a number of actual problems including improving economy and social aspect of people’s life. Depending on specific scenario different methods of organization of access are proposed for rural areas. A model of multiservice network is described in the form of a random graph and a multiphase teletraffic system, including crucial aspects of modernization of infrastructure in country area.
Keywords:	Communication System; Multiservice Network; Rural Area; Multiphase Teletraffic System;
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	DIGITAL PLATFORM FOR MANAGING ENTERPRISES' BUSINESS PROCESSES IN AN INNOVATIVE ECONOMY
Author:	AYSALKYN ASANOVA, OLEKSANDRA OLSHANSKA, MARIIA SAIENSUS, OLGA USATENKO, ANDRII MAKURIN, ANDRII SUKHOSTAVETS
Abstract:	The aggravation of the international political situation throws new challenges to industrial enterprises operating in the export-import sector; in light of this, the need to develop effective work methods in the current situation is most acute. The article discusses various approaches to the organization and management of business processes for industrial enterprises whose main activity largely depends on export-import operations. In the context of digitalization, the approach itself is to organizing export-import activities is primarily aimed at reducing the costs of ineffective organizational measures and avoiding critical errors in creating the management system base. As a basis for creating the scheme for managing export-import activities, the article proposes to consider the approach of using a digital platform based on a single window. The proposed method of work focuses not only on creating a mechanism for a particular enterprise but also on the design and organization of the system's core, participation in which will be beneficial to all interested parties.
Keywords:	Business Process Simplification; Digital Platform; Electronic Document Management; Export-Import Operations; Single Window Technique.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	TMRSG: TOPIC MODEL BASED RICH SEMANTIC GRAPH METHOD FOR ABSTRACTIVE MULTI-DOCUMENT SUMMARIZATION
Author:	Dr. K. ARUTCHELVAN, R. SENTHAMIZH SELVAN
Abstract:	Multi-Document Summarization (MDS) has gained more popularity among the industrialists and researchers in recent days. Extractive MDS simply extracts the important contents from multi-documents and gives a summary based on required length. Abstractive MDS provides summary based on the important of words that are presented across various documents. This research work is mainly focused on providing abstractive MDS using rich semantic graph-based methodology and topic modelling. The proposed approach generates summary by using graph-relations across multiple documents based on the relevant topics. The proposed approach is build using the centrality node ranking technique. The weighted graph ranking technique is applied to obtain the sequence of the sentences. The summary is generated using the highest rank scores of the sentences. The proposed technique is evaluated using the CNN/Daily Mail datasets.
Keywords:	Semantic Graph, Multi-Document Abstractive Summarization, Sentence Ranking, Similarity Measure, Topic Modelling
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	THE INFLUENCE OF SOCIAL MEDIA, TRUST, AND PURCHASE DECISIONS ON CUSTOMERS BUYING INTEREST
Author:	ATIKA SYILFA LAINI, DAVID KENNEDY, JULIA SINTA, MICHSON BRYAN LIE, VANESSA DELLA, TANTY OKTAVIA
Abstract:	This study discusses the influence of social media, trust, and purchasing decisions on consumer buying interest who is entering the era of globalization with rapidly developing technology. With this research, it can be seen that there are advantages in marketing through social media which can optimize marketing with the influence of social media in order to develop marketing strategies. In addition, there are also methods from the research model and methodology used in this study, which are based on previously studied literature, and use variables in questionnaire development where the survey is conducted online in Google Forms. In the findings, it can be seen that all variables can be positively related to customer demand to buy a product
Keywords:	Purchase Decision, Purchase Interest, Trust, Social Media, Marketing, Customers, E- Commerce
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	AN OVERVIEW OF THE DATA AND USER REQUIREMENT OF RESIDENT'S SECURITY AND SAFETY APPLICATION ON SMARTPHONE
Author:	AMZARI ABU BAKAR, NORHAYATI HUSSIN, ZAHARUDIN IBRAHIM, HASNAH HASHIM
Abstract:	This paper discusses the crucial elements of developing a resident's security and safety application on the smartphone. The discussion focuses on identifying and determining the applicable requirement of the apps to be used by the residents. The collated data and user requirements will comprise security and safety parameters prevalent in the state and crucial features that residents would like to use when implementing the mobile application. This paper aims to construct an understanding of mobile apps and discuss the component that creates a firm foundation for advancing knowledge and facilitating based on the development of the apps. The method used is a literature survey. The secondary data source of information has been identified to explore the element in developing the security and safety of the mobile application for the large population. The information gained from the previous journal nationally and internationally ensures the right components are discussed. The paper's outcome will significantly contribute to and benefit potential mobile application developers, the communities, higher learning institutions, the federal government of Malaysia, academicians, and researchers. It can also contribute to the body of knowledge in the field of information management. Lastly, the execution of this study will help bolster the government's plan of the National Digital Economy Initiative (Digital Malaysia) towards strengthening the digital information economy of the nation.
Keywords:	Safety, Security, Mobile Application, Data Requirement, User Requirement
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text

Title:	TVERSKY INDEXIVE CRAMER–SHOUP CRYPTOGRAPHY BASED DEEP STRUCTURED BELIEF NEURAL LEARNING FOR SECURED ROUTING IN MANET
Author:	Mrs.R.NAVAMANI, Dr.N.ELAMATHI
Abstract:	A secure routing is a significant concern due to its self-organizing and cooperative nature, capable of independent process, rapid changing topologies, limited physical security and so on. With the routing being a critical aspect for MANETs, existing routing protocols are not sufficient for security constraints. In this paper, a novel routing algorithm called a Tversky Indexive Cramer–Shoup Cryptography based Deep Structured Belief Neural Learning (TICSC-DSBNL) technique is introduced with security and higher data confidentiality in MANET. The TICSC-DSBNL technique comprises one input layer, three hidden layers and one output layer. The number of mobile nodes is taken as input in the input layer and sends the mobile node to the hidden layer 1. For every mobile node in the hidden layer 1, the trust value is calculated to identify the node as normal node or malicious node using Tversky Similarity index. The index is used to find the similarity between mobile nodes for classifying the node as normal node or malicious node. After that, the normal nodes are given to the hidden layer 2. In that layer, a route path between the nodes gets established and selects the shortest route path. In third hidden layer, the Cramer–Shoup cryptosystem is applied for encryption and decryption to perform secure routing with higher confidentiality in MANET. Simulation is conducted in with different performance metrics such as packet delivery ratio, packet drop rate, and delay, throughput, and data confidentiality rate with respect to the number of data packets. The discussed results indicates that the proposed TICSC-DSBNL technique improves the performance of secure routing with higher delivery ratio, data confidentiality with lesser delay as well as packet drop than the state-of-the-art methods.
Keywords:	MANET, Secure Routing, Deep Structured Belief Neural Learning, Tversky Similarity Index, Cramer–Shoup Cryptosystem.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2022 -- Vol. 100. No. 12 -- 2022
Full Text