		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
Marh 2022 | Vol. 100 No.06

Title:	WEB TECHNOLOGIES FOR MARKETING STRATEGY OF INDUSTRIAL TOURISM DEVELOPMENT
Author:	IGOR KOMARNITSKYI, ALLA KHANENKO, SERGHII HORCHYNSKYI, OKSANA BORISYUK, SERGIY POPOVYCH, LARYSA KUCHECHUK
Abstract:	The article defines industrial tourism, notes its relevance and popularity in the modern world. The advantages of industrial tourism for tourists, enterprises and the region as a whole are highlighted. Also, the strategic marketing directions of industrial tourism are highlighted: educational, scientific, professional, business, investment, extreme, environmental, cognitive, social, cultural, event, hobby. Various objects of industrial tourism are distinguished by activity: active, inactive and restored objects. When forming a marketing strategy for industrial tourism development, its specifics should be taken into account. The importance and necessity of using digital technologies in a marketing strategy were also noted, which have several advantages: unlimited amount of information; the ability to combine text, graphic, video and audio data; instant update of information; storage of files and databases; the two-way nature of communication; unlimited number of users, no geographic attachment; unlimited access in time; no costs for expanding the audience; the possibility of integrating the system of direct Internet sales. Considering the peculiarities of industrial tourism and the relevance of digital tools, the result of the article is the compilation of the basic structure of a digital marketing strategy and a methodology for compiling a marketing strategy for industrial tourism.
Keywords:	E-Commerce, Industrial Tourism, Marketing Strategy, Online, SEO, Web Technologies.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	REVIEW OF TEXT BASED PASSWORD AND OTHER AUTHENTICATION METHODS FOR E-COMMERCE DATA PROTECTION
Author:	AZANI CEMPAKA SARI, ALSYA CARISSA ZEVANDA, CHRISTIE CLAUDIA HASIANI MALAU, LAURENSIA VILDA YOVIRA
Abstract:	Significant development of the internet has triggered various new technologies. One of them is e-commerce. This causes the security aspect of e-commerce to be one of important factors, especially to prevent unwanted things such as data leaks and financial losses. The authentication method is one example to provide protection, such as protection of user data and protection of transactions in e-commerce. In short, the authentication system prevents access by unauthorized parties. Authentication systems may vary from the simplest, namely the use of passwords, to other methods. The aim of this study is to explore various authentication methods, the advantages, disadvantages, types of attacks that can occur, and the importance of using an authentication system, especially in the e-commerce environment.
Keywords:	Password, Authentication, Data Protection, E-Commerce, Security
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	A BLOCKCHAIN-BASED SYSTEM FOR PREVENTING DRUG COUNTERFEIT
Author:	ABDULLAH QUZMAR, SARAH ALMAAITAH, AND MOHAMMAD QATAWNEH
Abstract:	The drugs industry is one of the most popular industrial areas, which suffers from counterfeit and loss of integrity. For instance, the proportion of counterfeit drugs in the world reached 10-15%. This paper proposes a secure Blockchain-based system for reducing drug counterfeit. The proposed system was implemented using the NodeJS language with a hyper ledger fabric platform. We analyzed network overheads to assess how many network messages we need to reach a consensus on a single block. The results show that to reach a consensus in a system of N peers, 2N*(N-1) messages are required. In addition, the proposed system has high performance in terms of less time needed to validate and append transactions into BC system.
Keywords:	Blockchain, Counterfeiting, Hyper Ledger Fabric, Consensus, Smart Contract.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	IMPLEMENTATION OF MACHINE LEARNING TECHNOLOGY FOR CONSUMER CREDIT SCORING IN BANKING INDUSTRY: STUDY CASE OF PT BANK BNI SYARIAH
Author:	FIRNANDO MUSLIMIN, TUGA MAURITSIUS
Abstract:	Banking industry mainly runs their business on financing business. This business type currently still plays a role as a core business of PT Bank BNI Syariah among other business models in the company. Financing or credit business is not only provided by bank where we know that non-bank organization is also capable to provide similar services to customer which called as Financial Technology (Fintech). Fintech delivers its service to end-user through a portable application that can be accessed by end-user anytime and anywhere. Various automation is implemented in order to give excellent service level agreement (SLA) towards the product. Another high technology is implemented to obtain a very fast decision-making process for each loan request is powered by Artificial Intelligence (AI) technology. This technology is built on top of machine learning where loan requests can be determined just less than 10 minutes. The same service is mostly performed manually by a bank, where at this point there are a lot of manual processes that should be handled by a human. Physical interaction is needed to verify the customer as a set of activities of due diligence. By this condition, bank should be able to catch up to keep up with the direct or indirect competitors by the implementation of machine learning to perform credit approval.
Keywords:	Credit Scoring, Fintech, Classification Algorithm, Machine Learning, Consumer Banking
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	INTERNET-OF-THINGS: A SYSTEM DEVELOPMENT LIFE CYCLE (SDLC)
Author:	MAI ALFAWAIR
Abstract:	The Internet-of-Things (IoT) is a revolutionary technology that connects everyday objects to the Internet. The utilization of IoT systems created integrated systems that transformed communication, administration, and monitoring in various fields such as smart homes, healthcare monitoring, and even environmental monitoring, giving users more control over everyday objects and adding to the complexity of such systems. The successful development of IoT systems requires software engineering to extend beyond the traditional development strategies or System Development Lifecycle (SDLC), particularly owing to the heterogeneity and complexity of such systems. This paper provides an innovation by expanding the traditional System Development Lifecycle (SDLC) to accommodate the nature of IoT systems, making the traditional SDLC more convenient for use to develop IoT systems. This has been achieved by editing some of the already existing SDLC processes, as well as adding some other processes to the traditional SDLC. Such additions include aspects unique to IoT systems development, for example, things requirement, communication requirement, system component integration, and system operation, as well as other additions to the traditional SDLC. Results clearly demonstrate that IoT application development has become more systematic, efficient, and hence, requiring less time for development since the IoT SDLC has facilitated project management and improved the overall quality of the process.
Keywords:	Internet-Of-Things (IOT), System Development Lifecycle (SDLC), Network Development, Software Engineering
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	MACHINE LEARNING TO SUPPORT SMART CITY INITIATIVES
Author:	ADNANE FOUNOUN, MAHDI ALAOUI HANAFI, AAWATIF HAYAR, ABDELKRIM HAQIQ
Abstract:	Machine learning is one of the technologies coming to help the deployment of smart cities in all phases. The diagnosis is a crucial phase that comes to ensure the implementation of a project adapted to the reality of the city diagnosed; this step requires a significant financial commitment. This paper comes to deploy a frugal diagnostic approach of the smart environment component while using self-learning techniques. In addition, assessments are reported and regulatory maturity with respect to this new concept is explored through machine learning. In the near future machine, learning will play a crucial role in the implementation of this kind of concept.
Keywords:	Natural Language Toolkit; Machine Learning; High Performance Computing; Smart Governance ;Smart Cities, Oriented Topic Modeling.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	IMPLEMENTATION OF DATA MINING ON CUSTOMS FALSE DECLARATION DETECTION
Author:	ILHAM DEWANTORO, TUGA MAURITSIUS
Abstract:	Importation control in Indonesia is in need of an efficient method to oversee import declarations suspected of misleading information. This study offers a data mining method through Cross-Industry Standard Process for Data Mining (CRISP-DM) to provide a reliable method to predict false customs declarations. The method is tested using imports data from three major ports in Indonesia between 2019 and 2020. This study used decision trees algorithm as prior customs data mining study. The algorithm is compared with random forest and naïve bayes to detect false import declaration based on classification accuracy, precision, and recall scores. Testing results showed that random forest is the algorithm with the best classification accuracy, precision, and recall scores. Dataset preparation is very crucial since importation data has high cardinality and imbalance issues. This study used Synthetic Minority Oversampling Technique (SMOTE), normalization, and data transformation techniques to find a suitable dataset for a better prediction. The study finds that the model has a higher precision score than false declaration prediction based on whistleblower tips. This study is an addition to the limited amount of references pertaining to customs data mining.
Keywords:	Customs, False Declaration, Data Mining, CRISP-DM, SMOTE
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	PERFORMANCE COMPARISON OF THREE DIFFERENT TYPES OF AUTOENCODERS USING RECOMMENDATION SYSTEMS
Author:	AHED MLEIH AL SBOU, NOOR HAFHIZAH ABD RAHIM
Abstract:	Recommendation system is one of the modern applications to solve information overload problem in a way to provide recommendations of interest to users. Websites such as Amazon, Netflix, Facebook, YouTube, and others apply recommendation system in recommending their products. This also includes recommending news to the readers. However, the systems suffer from some challenges such as high dimensional data, data sparsity, and cold start. To address these problems, deep learning techniques have recently been integrated with recommendation systems and achieve good performance. Autoencoder is one of the most widely used deep learning techniques in recommender systems, especially used for feature extraction, data dimensionality reduction, fast convergence, unsupervised learning, and data reconstruction. In this paper, a performance comparison between three different models of autoencoder is presented which applying in the recommendation systems to further improve the quality of recommendations provided to users. The models are Hybrid Collaborative Recommendation via Semi-AutoEncoder (HRSA), Recommendation via Dual-Autoencoder (ReDa), and Hybrid Collaborative Recommendation method via Dual-Autoencoder (HCRDa). These models work by retrieving the potential latent factors from the sparse rating matrix and predict the missing ratings. The performance is compared based on reconstruction loss that applies to the MovieLens 100K dataset with three different sets of training data: 70%, 80%, and 90%. As a result, it was found that the HCRDa is outperformed the other models in terms of reconstruction loss based on the RMSE evaluation metric and the use of side information in the model. Thus, it is the most effective technique in terms of enhancing the quality of user recommendations.
Keywords:	Autoencoder, Deep learning, Dual-autoencoder, Recommendation systems, Semi-Autoencoder.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	MODEL FOR THE DECISION SUPPORT SYSTEM DURING THE PROCEDURE OF INVESTMENT PROJECTS ASSESSMENT IN THE FIELD OF ENTERPRISE DIGITALIZATION CONSIDERING MULTIFACTORALITY
Author:	T. KARTBAYEV, V. LAKHNO2, V. MALYUKOV, A. TURGYNBAYEVA, ZH. ALIMSEITOVA, F. MALIKOVA, G. KASHAGANOVA
Abstract:	It demonstrates the essentiality of wider application of the computer-based decision support systems (DSS) to increment the reliability of recommendations provided by analysts (decision makers — DM) in various fields, especially regarding the investment projects assessment in the field of digitalization of enterprises. A model for the developed DSS during the procedure of investment projects assessment in the field of enterprise digitalization considering the multifactorial nature of the given task is described. Unlike existing approaches, our model is based on solving a bilinear multistep quality game with several terminal surfaces. In this work, a new class of bilinear multistep games describing the interaction of objects in a multidimensional space is considered for the first time. This allows us to adequately describe the process of finding rational strategies for players (investors) in investing in enterprise digitalization related projects. A software product “Investing in digital enterprises” was developed in the Android Studio environment during the research process. Our model and the developed software product make possible to reduce discrepancies in the forecast assessment of investment projects in the field of digitalization of enterprises and the real return on investment. It is also possible to solve problems related to the investment strategy optimization.
Keywords:	Enterprise Digitalization, Investment Strategies, Multidimensional Case, Decision Support, Multi-step Game, Software
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	GENETIC ALGORITHM FOR SOLVING THE PROBLEM OF SCALING A CLOUD-ORIENTED OBJECT OF INFORMATIZATION
Author:	LAKHNO V. , BEREKE M. , ADILZHANOVA S. , CHUBAIEVSKYI V. , KRYVORUCHKO O. , DESIATKO A. , PALAGUTA K.
Abstract:	This article discusses the problem of mathematical modeling performed in the process of choosing server platforms and the required additional amount of RAM for the deployment of additional virtual workstations in the cloud-oriented object of informatization, for example the cloud-oriented learning environment (COLE) of university. At the same time, a number of requirements are imposed on COLE virtual machines (VM). The requirements are primarily related to the required amount of RAM for the server infrastructure of the educational institution's private cloud and the minimization of the modernization overall cost. This paper proposes a modified genetic algorithm (MGA) to solve such a problem. The algorithm can be used to solve problems related to the scaling of the university COLE. As a special case, the problem of analyzing options for scaling virtual workstations of COLE users was considered. Unlike existing solutions, it was proposed to apply a modified coding method. In addition, it was proposed to use an elitist strategy. With use of such an approach, the best individuals are selected for the gene bank. The use of a gene bank made it possible to reduce the number of generations in the search for a solution associated with the selection of the necessary configuration option for the COLE server infrastructure according to the parameters of the required amount of RAM for the servers of the educational institution private cloud and at the same time minimizing the total cost of its modernization.
Keywords:	Cloud-Oriented Learning Environment, Virtual Workstation, Virtual Workplace, Server Equipment, Optimization
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	AN IN-SHIP LOCALIZATION ALGORITHM FOR CLOSE CONTACT IDENTIFICATION
Author:	QIANFENG LIN, JOOYOUNG SON
Abstract:	Concern about the health of people who traveled on board was raised in the COVID-19 outbreak on the Diamond Princess cruise ship. The ship narrow space offers an environment conducive to the virus spread. Close contact isolation remains one of the most important current measures to stop the rapid spread of the virus. Contacts can be identified efficiently by detecting smart devices nearby. The smartphone Bluetooth RSSI signal is significant data for positioning. The traditional indoor positioning algorithm cannot be directly applied in the mobile ship environment. It is necessary to study the indoor positioning algorithm which applies to the mobile ship environment. In this paper, we propose an in-ship localization algorithm, which can achieve indoor positioning without the fingerprint map, with an RMSE of 1.63 m.
Keywords:	Indoor Positioning, In-Ship Localization, Reference Point, Close Contact
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	COMPARATIVE ANALYSIS OF MACHINE LEARNING TECHNIQUES ON GENETIC MUTATION BASED CANCER DIAGNOSIS DATA
Author:	ASHOK REDDY KANDULA , Dr. R. SATHYA, Dr. S. NARAYANA
Abstract:	There are still several research studies about how precision medicine and advanced genetic testing are highly disrupted by how cancer-like diseases are treated. The major disadvantage is that identifying cancer disease by checking gene mutations is a manual process which leads to lot of misclassifications. The paper tries to intend several machine learning techniques to make the manual process into an AI-assisted process that makes the work much easier and efficient. The cancer dataset has a certain kind of complicated format. One such is text category; thus, to address the issue, the paper successfully established a complete data analysis that highly gave a detailed view about the data which is performed in the previous. The article applies several machine learning techniques like Naïve Bayes, K- Nearest Neighbours, and Logistic Regression to classify the data with and without class balancing to analyse the cancer dataset.
Keywords:	Genetic testing, Gene Mutation, Naïve Bayes, K-Nearest Neighbour, Logistic Regression.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	AN EMPIRICAL INVESTIGATION ON FACTORS INFLUENCING ERP ALIGNMENT WITH OPERATIONAL PERFORMANCE OF JORDAN PHARMACEUTICAL COMPANIES
Author:	RAWAN H. ALSHAREDEH, HAYEL T. ABABNEH, SALEH ALQATAN, HUSSAM THNEIBAT
Abstract:	In spite of the fact that Implementing and running ERP software’s offers great advantages and benefits for pharmaceutical companies, ERP software’s in Jordanian pharmaceutical companies has been highly unsuccessful. In this case, the alignment between business and ERP is a vital matter especially when ERP is an integral portion of the business and is utilized in leveraging certain special business competencies, in merging companies, restructuring industries, and also in facilitating global competition. However, there is still the lack of researches that investigates the factors influencing business-ERP alignment in the pharmaceutical companies. The study investigates the factors influencing ERP adoption and implementation in pharmaceutical companies. The questionnaire was distributed to the target sample and the obtained data was analysed through the SPSS statistical software. Results of the analysis revealed that all factors positively influenced business-ERP operational alignment in pharmaceutical companies. The study provides advanced knowledge of business-ERP operational alignment in pharmaceutical companies, which will help the ERP providers in such enterprises to understand the factors that influence the business-ERP operational alignment in pharmaceutical companies.
Keywords:	Enterprise Resource Planning, Pharmaceutical Companies, Task-Technology Fit Model (TTF),The Success of Information Systems Model (IS Success Model), Business-ERP Operational Alignment.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	E GITHA, THE FOREST TREE MODEL ON INTEGRATED KEKIDUNGAN INFORMATION SYSTEM
Author:	OKA SUDANA, OKA WIBAWA, AYU WIRDIANI, DWI RUSJAYANTHI
Abstract:	Kekidungan, often called Gegithan or Nyanyian, is a type of oral literary culture that Indonesia owns. Kidung or githa, especially in Bali are Traditional Balinese Song, where the details are in the form of Panca Githa, have a significant role in the implementation of a Yadnya Ceremony as well as daily entertainment. Many Hindu communities, especially Bali, do not know or understand the type, purpose, when, and where the song is used or sung. This is because lack of information about Kekidungan, and the inherited literature on this subject increasingly difficult to find. Based on these problems, it is necessary to develop an application that can accommodate information about Kekidungan, both related to the Yadnya Ceremony in Bali or merely the daily entertainment of Balinese people. This song or gegithan can stand alone or collaborate with other arts, such as drumming and dance. In addition to providing information quickly and efficiently about Balinese songs to the public, this information system aims to preserve the literature by using technology assistance. The system that has been successfully created is the Kekidungan Information System or E-Githa that integrated with the E-Yadnya System, which is made web-based and implements the Forest Tree Model as the basic structure of the hierarchical model.
Keywords:	Forest Tree Model, Information Systems, Kidung, E-Githa, E Yadnya.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	A RING BASED LEADER ELECTION ALGORITHM FOR HIVE NETWORKS
Author:	MOHAMMED AL-REFAI, YOUSEF ALRABA NAH
Abstract:	Leader Election Algorithms (LEAs) play a vital role in distributed systems. The leader organizes and synchronizes processes in distributed systems and communication networks. The leader is prone to fail which in turn makes the network inconsistent. LEAs solve the leader failure problem by electing a new one. In this paper, a new LEA is proposed to solve the leader failure in hive networks. The proposed algorithm elects one node with the highest priority to be the new leader. The algorithm is evaluated theoretically by calculating number of messages and time steps required to elect a new leader. We show that the algorithm needs O(n) messages in O(∛n ) time steps in the best case, while it needs O(n1.3) messages in O(∛n) time steps in worst case.
Keywords:	Leader Election Algorithm, Hive Networks, Network Cost, Honeycomb Networks, Distributed Systems.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	ARTIFICIAL BEE COLONY FOR CURVE RECONSTRUCTION USING QUARTIC BÉZIER
Author:	NUR AFIFAH RUSDI, ZAINOR RIDZUAN YAHYA, WAN ZUKI AZMAN WAN MUHAMAD, NURSHAZNEEM ROSLAN
Abstract:	This work presents the use of Artificial Bee Colony Algorithm (ABC) for curve reconstruction using Quartic Bézier. Quartic Bézier curve is rarely used by the researchers in the application of medical images. Therefore, by increasing the degree of the Bézier curve, a better curve with small error can be obtain. The process of curve reconstruction involved was boundary and corner point detection of the medical image, parameterization and curve reconstruction by using ABC. By applying these processes, the fitted Quartic Bézier is obtained. The Sum Square Error (SSE) is used to record the error between the fitted Quartic Bézier curve with the original image. The results of SSE is recorded after the process is repeated 10 times with the average error of . Because the final output of the fitted curve resembles the original image, the suggested method can be considered as an option method for curve reconstruction applications. ABC algorithm is an interesting algorithm that can be explored in more detail and can be applied in various problems.
Keywords:	Curve Reconstruction, Quartic Bézier Curve, Medical Image, Artificial Bee Colony Algorithm.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	AN ARTIFICIAL INTELLIGENCE BASED WEED CLASSIFICATION USING VGG16 CLASSIFIER AND RMSPROP OPTIMIZER
Author:	D.N.V.S.L.S. INDIRA, M. SOBHANA, T.SUMALLIKA, M. VIJAYA SUDHA
Abstract:	From the start of farming as a profession, the weeds have been a problem and the problem still continue. The main factors are the competition for nutrients, water, and space and for disease and pesticides. Weed management is becoming popular in crop production with the arrival of high yield varieties and heavier doses of fertilizer application. One important way of improving fertilizer use efficiency is to control weeds in good time. We developed a web application which uses in-depth learning, to capture an input and to detect whether an image is normal or weed image. In this paper VGG16 classifier and RMSPROP optimizers are used for distinguishing a plant and a weed. The dataset is downloaded from Kaggle and Signal handling gathering of the Aarhus. Four plants, common wheat and sugar wheat, common weeds, cleavers with a totality of 942 pictures have been successfully classified. Finally, around 92% precision with a 5.5% rise in current classifications is projected by this work.
Keywords:	Crop, Weed Classification, VGG16, RMSPROP Optimizer, Deep Neural Networks
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	COMMUNITY-BASED TOURISM AND TECHNOLOGY RELATIONSHIP: A BIBLIOMETRIC ANALYSIS
Author:	HENDRO NINDITO, SPITS WARNARS HARCO LESLIE HENDRIC, SFENRIANTO, HARJANTO PRABOWO
Abstract:	This study aims to find the direction and objectives of research in the current Community-based tourism (CBT) and relationship with technology domain. We Use the five phases of bibliometric analysis method, we extracted 272 documents from the Scopus database for the period 1991 to 2021 and refined keywords by adding inclusion criteria to produce 176 documents. We analyzed the document metadata with features from the Scopus website, exported it to a RIS-type dataset and then processed it using VosVewer to visually map keywords for further analysis. The result, we found the trend of publications related to this topic by time period, the most influential publications, trends in the main topics and potential topics for future research as well as the relationship between the CBT and IT domains. The Conclusion for this research on this domain has increased publication interest from year to year, but the results visualized that there is no direct relationship between the two and also the density diagram for information technology area is bright, which shows that the novelty level is still high for future research.
Keywords:	Community-Based Tourism; Bibliometric; Visualisation; Technology, VosViewer
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	EXPERIENCE OF CONNECTING SENSORS TO THE CONTROLLER BASED ON THE ARDUINO BOARD FOR USE ON MULTICOPTERS
Author:	‪TALSHYN KERIBAYEVA, ZHARAS AINAKULOV, RUSTAM YERGALIYEV, GULZHAN KURMANKULOVA, IGOR FEDOROV‬, RAZIYAM ANAYATOVA
Abstract:	The possibility of obtaining data on areal humidity based on unmanned aerial vehicles is being investigated. Modern humidity sensors are mostly stationary and provide point measurements. With the advent of mobile hardware and software tools that make it possible to automate the process of obtaining data, the problem of obtaining information distributed over a given area is being solved. And also there is the possibility of recording and saving data to the hard disk. One of the advanced areas in which multicopters are used is the creation of electronic field maps, as well as maps of vegetative NDVI indices. This paper discusses DHTxx temperature and humidity sensors. The small dimensions of the sensors, a sufficient number of I / O ports (data transfer, control of peripheral devices) made it possible to assemble many devices based on Arduino. The use of unmanned aerial vehicles greatly simplifies the collection of the necessary information about the state of crops. Unlike spacecraft, an unmanned aerial vehicle, in our case multicopters, is more mobile, with more detailed data (the ability to obtain images with a resolution of up to 1 cm). Due to the fact that the flight altitude of a multicopter is usually within 1 to 200 meters above the ground, it is possible to use various sensors (temperature, humidity, etc.), which were previously used by agronomists (farmers) for ground weather stations. The temperature and humidity sensors of the DHTxx family can be attributed to such sensors, which are necessary in terms of monitoring agricultural lands. The temperature and humidity sensors DHT11 and DTH22 include two measuring instruments useful for agriculture - a thermometer and a hygrometer. The progress of modern society cannot be imagined without the development of science and technology, without the introduction of technological innovations, in particular controllers and sensors with different functionality. The results of this study can be applied both to the design of multirotors in general and to the arrangement of sensors and actuators.
Keywords:	Unmanned Aerial Vehicles, Multicopter, Arduino, Temperature and Humidity Sensor, NDVI, Monitoring, GIS
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	AN OVERVIEW OF IDENTIFICATION AND ESTIMATION NUTRIENT ON PLANT LEAVES IMAGE USING MACHINE LEARNING
Author:	DEFFA RAHADIYAN, SRI HARTATI, WAHYONO, ANDRI PRIMA NUGROHO
Abstract:	Lack of nutrients affects plant growth and causes plant damage. Deficiency of macronutrient such as nitrogen, potassium, calcium, and phosphorus are big problem for agriculture and its prevention will be very useful for agro-industry. The destructive methods for identifying nutrient deficiencies are soil analysis, plant tissue analysis which requires expert knowledge and laboratory testing, but the test results are not necessarily accurate due to human error. Non-destructive methods such as computer vision can help digital farmer who lack knowledge of botany to identify macronutrient deficiencies. Identification and estimation of macronutrient deficiencies using computer vision consists of several stages, namely data acquisition, preprocessing, segmentation, feature extraction, to identification and estimation method. Image data in the form of RGB, NIR, etc. Several researchers have conducted studies to identify and estimate macronutrient deficiencies using different method. These methods are traditional methods such as rule based to K-Nearest Neighbor (KNN), Linear Regression, Artificial Neural Networks (ANN), Deep Learning with various architectures, and others. Several studies have their respective results and limitations, therefore this paper focuses on reviewing current research developments and providing an overview of the work and challenges in the future. The result of the comparative study is that Deep Learning such as CNN is a promising method because most studies can identify macronutrient deficiencies with an accuracy of more than 80%. However, there are still some challenges such as overcoming overlapping images with complex backgrounds, identification of multi-deficiencies, and estimation of the content of each macronutrient in RGB images.
Keywords:	Deep Learning, Classifier, Feature Extraction, Macronutrient Deficiency, Image Processing.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	RESILIENCE HIDDEN MARKOV MODEL BASED SUPPORT VECTOR MACHINE FOR CROSS - DOMAIN SENTIMENT CLASSIFICATION IN BIG DATA
Author:	RAMAJAYAM G, Dr. R. VIDYA BANU
Abstract:	Sentiment Analysis (SA) utilizes text contextual mining to identify and extract core subjective information from the source material. Businesses can use SA to monitor online comments or reviews about their brand, product, or service to understand how people feel about their organization. Currently, available classifiers are developed to classify sentiments only in a specific domain, and if it is applied in different domains, it will never give its better performance. General machine learning-based algorithms cannot give the best performance when applied in big data. This paper proposes a Resilience Hidden Markov Model based Support Vector Machine (RHMM-SVM) to classify sentiments in different big product review datasets. RHMM - SVM makes use of a forward - backward strategy to attain better classification accuracy in different big product review datasets. RHMM - SVM is compared and analyzed against existing classifiers with benchmark metrics, namely Precision, Matthew Correlation Coefficient, F1 - Score and Classification Accuracy. Results make a clear indication that RHMM - SVM has better performance than previous classifiers.
Keywords:	Classification, Product Review, HMM, Big Data
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	CROSSCUTTING CONCERNS (ASPECTS) IDENTIFICATION IN THE EARLY STAGE OF ASPECT-ORIENTED SOFTWARE DEVELOPMENT
Author:	AWS A. MAGABLEH, RAZAN RABABAH
Abstract:	Aspect-oriented programming (AOP) can effectively solve code-tangling and code-scattering that are caused by the attributes of crosscutting concerns or aspects. To date, research in the field of aspect orientation has concentrated on the implementation stage of the software development life cycle. Also, quite a good number of studies on aspect orientation have been conducted on the later stage of software development. However, less attention has been paid to aspect orientation at the requirement analysis stage, i.e., the early stage of software development. Therefore, the aim of this research is to propose an approach for analyzing and extracting crosscutting aspects from software requirements specifications by using a natural language processing technique, namely, the educated text stemmer algorithm. Moreover, this research focuses on the auto analysis and extraction of aspects from specifications written in the Arabic language because a lot of companies and organizations are still using English language-based requirements approaches for Arabic systems. The results of the proposed approach show promise because the proposed Arabic miner tool was able to extract the greatest number of candidate aspects from Arabic requirements specifications. The approach was evaluated by comparing the results that it automatically extracted with those extracted manually by software engineering experts. The accuracy of the experts’ efforts was 88%, whereas the accuracy of the proposed approach was 36%, which can be ascribed to the poorness of the Arabic data set and Arabic WordNet tool. Nevertheless, the proposed approach has potential, and the experimental results offer insights on how to further develop the proposed tool.
Keywords:	Crosscutting concerns, Aspects, Aspect-oriented, AO, Aspect identification, Aspect elicitation, Early stage of software development life cycle, Arabic requirements specification, AO miner.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	ANALYSIS STUDY TO DETECT STUDENT LEARNING PROBLEMS IN ONLINE LEARNING USING TEXT MINING
Author:	YEFTA CHRISTIAN
Abstract:	How big the level of comfort and level of satisfaction of students in participating in learning needs to be known by the organizers of learning to improve the quality of learning and increase student interest in learning. One of them is by providing a facility in the form of an Academic Guidance System that students can use to express their complaints and opinions regarding the learning activities carried out. In this study, the author will classify with a text mining algorithm on any complaints or opinions given by students. The method used in this research is Lexixon Based Sentiment Analysis using two tools, namely Flair NLP Framework Application and KNIME Application. These two tools can classify every complaint or opinion into two categories, namely positive and negative. Positive can mean that there are no problems related to the lectures being carried out while negative means the opposite. The results of the application of the text mining algorithm on the KNIME Workflow that were applied in this study succeeded in mapping positive and negative sentiments from student learning, with an accuracy of 70%, still less than the desired standard of 85%.
Keywords:	Students, Learning Problems, Online Learning, Text Mining, Lexicon Based
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	DETECTING OBJECTS FROM AERIAL IMAGES USING SINGLE-STAGE DETECTION METHOD
Author:	ANGELICA FAUSTINE, GEDE PUTRA KUSUMA
Abstract:	One of the applications of object detection and recognition are detecting object from aerial images. There are various further applications of object detection in aerial images, it can be used for tracking objects, implementation for unmanned aerial vehicles (UAV), traffic surveillance, and calculating objects. As the applications of detecting objects from aerial images get wider and more common, the accuracy of object detection becomes more important. This paper evaluates the effects of changing the backbone of YOLOv4 (You Only Look Once), the current state-of-the-art single-stage object detection method, with EfficientNet and EfficientNetv2, the image classification method. The experiment was done with the CARPK dataset, a dataset of aerial images of cars in a parking lot taken by drones that suit car detection. The result of changing the backbone of YOLOv4 with EfficientNetB3 manage to increase the detection accuracy to 99.23% in the CARPK dataset.
Keywords:	Aerial Image, Car Detection, EfficientNet, EfficientNetv2, YOLOv4
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	USE OF ARTIFICIAL INTELLIGENCE (AI) FOR OPTIMAL DELIVERY IN URBAN LOGISTICS
Author:	SOUMIA TABIT, AZIZ SOULHI
Abstract:	Performance In an urban area, the delivery of products in a short delay represents a vital requirement for the customer, but a permanent challenge for the providers, because this parameter "delay" is affected by several factors, which makes its prediction a delicate matter. This paper presents an approach to predict the delivery time in urban areas through a decision-making model based on the fuzzy logic method. This model relies on three input factors namely: traffic density, mileage and road infrastructure quality to determine the delivery time which is the output parameter. The importance of this model lies in its ability to accurately delineate the impact of each input parameter and adjust them in order to reduce the delivery time and therefore satisfy the customer.
Keywords:	Fuzzy Logic, Delivery Of Products, Industrial Performance, Decision Making Model, Traffic Density, Mileage And Road Infrastructure Quality.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	THE STUDY OF THE TRANSITION TO PERSONALIZED LEARNING OF SCHOOLСHILDREN IN THE REPUBLIC OF KAZAKHSTAN BASED ON A LOGICAL-STRUCTURAL APPROACH
Author:	ZHANAT SEITAKHMETOVA, SAULE KUMARGAZHANOVA, LEONID BOBROV, SAULE SMAILOVA
Abstract:	This article discusses the issue of transition to personalized learning in schools of the Republic of Kazakhstan. The expert study was conducted on the basis of the results of a survey of the main participants of the study - students, parents and teachers of the network of Nazarbayev Intellectual schools. The results obtained allowed us to identify three strategic directions that ensure the transition to a personalized format within the framework of a research project.
Keywords:	Personalized Learning, Electronic Educational Environment, Expert Assessment, Logical-Structural Approach, Ranking Method
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	THE CONTRIBUTION OF DATA MINING TO THE EDUCATION SECTOR
Author:	AYOUB ENNASSIRI, RACHID ELOUAHBI, GAMAL ALHAMMADI, IKRAM BOUDALLAA, I.ZRIGUI, SAMIRA KHOULJI
Abstract:	Data mining refers to the process of analyzing massive volumes of data and big data from different angles in order to identify relationships between data and transform them into actionable information. The Revolution through the digitization of the economy and the circulation of various data, in volumes never before reached and in record time, is probably fundamentally shaking up the functioning of our organizations. Organizations are thus faced with a gigantic wave of data both endogenous and exogenous to their own environment. Artificial intelligence represents, for its part, the impacting part for employment of this new industrial revolution, promising the conversion of a new category of tasks, previously performed by humans, towards a new type of robotization even more elaborate than that of previous industrial revolutions, in volumes that no one can still fully appreciate today. In the interest of having a much broader and clearer vision on Data Mining and its impact on education, it is necessary to draw up a judicious plan for the realization of the project by answering the following problem: How Big Data can influence the education sector?
Keywords:	Data Mining, Performance, Intelligent System, Education.
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	AUTOMATIC CLASSIFICATION OF MOSQUITO GENERA USING TRANSFER LEARNING
Author:	RESHMA PISE, KAILAS PATIL, NEERAJ PISE
Abstract:	Certain species of mosquitoes are the main vectors of arboviruses that cause Dengue, Yellow fever, Chikungunya, Zika and Japanese encephalitis. These species are contained in the genera Anopheles, Culex, Aedes. Mosquito-borne diseases pose significant threat to public health. Therefore, vector surveillance and vector control strategies are crucial. Automation of genera identification is essential to implement effective vector control strategies. In the past decade several machine learning and deep learning models have been investigated for image-based automatic and accurate classification of vector mosquitoes. Such applications also aid entomologists in insect identification task. In this study, a deep convolutional neural network technique to classify two genera of mosquitoes: Aedes and Culex based on the morphological features is proposed. In our work, an optimization technique i.e., transfer learning using the pretrained deep learning models has been employed. Transfer learning saves the model training time and addresses the problem of low performance due to insufficient amount of training data. This paper presents the architecture of three state of the art pretrained neural networks, including VGGNet, ResNet and GoogLeNet. The models were trained with our own dataset of images of the two genera of mosquitoes. Classification performance of the models is evaluated in terms of classification accuracy and loss during training and validation phases of model building.
Keywords:	Artificial Neural Networks, Image Classification, Machine Learning, Vector Control
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	ANALYSIS OF THE EFFECT OF GAMIFICATION ON CUSTOMER LOYALTY OF THE USE OF THE ONLINE TRANSPORTATION APPLICATION
Author:	WILLY KRISTIAN, TOGAR ALAM NAPITUPULU
Abstract:	The purpose of this paper is to see what factors influence customer loyalty in the use of the Gojek online transportation application. Then the data collection was carried out by distributing questionnaires through the google form media to 410 respondents who were users of the Gojek application in the Jabodetabek area. All data that has been collected is processed using the Smart PLS 3.0 application. Based on the analysis conducted, the results show that the gamification variable, namely Entertainment, has an influence on Hedonic Value, as well as the Intimacy and Novelty variables have a significant influence on Hedonic Value and Utilitarian Value, while the Trendiness variable has a significant influence on Hedonic Value but does not have a significant effect on Hedonic Value. influence on Utilitarian Value. Then Hedonic Value and Utilitarian Value have a significant effect on Satisfaction and Satisfaction has a significant influence on Continuance Intention. Then Hedonic Value, Satisfaction, and Continuance Intention have a significant influence on Loyalty. Meanwhile, Utilitarian Value has no effect on Loyalty.
Keywords:	Gamification, Gojek, Customer Loyalty, Online Transportation, GoClub. Grab
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	IMPROVING HADOOP THROUGH DATA PLACEMENT STRATEGY
Author:	MOHAMED EDDOUJAJI, HASSAN SAMADI, MOHAMMED BOUHORMA
Abstract:	Hadoop assumes that the computing capability of cluster's nodes is similar. In such a homogeneous environment, every node is assigned an identical load, such approach allows total use of cluster's resources and minimize multiple idle or over headed nodes. However, in real world applications, clusters are frequently deployed in a heterogeneous context [9,13–15]. In such environments, there is possibly multiple different physical servers and different virtual nodes specifications, which provide per consequence different services capabilities. Therefore, Hadoop still uses the same native strategy that distributes data blocks equally among each DataNode, similarly the load is evenly assigned between nodes, then the basic overall performance of Hadoop may also be reduced. The main objective during the phases of this research is to find an optimal scheme and an improved architecture to optimize the classical architecture of HADOOP and MapReduce, by focusing mainly on the algorithm of locality and data distribution in a heterogeneous ecosystem composed of several nodes heterogeneous. Despite of the native Data Placement strategy that Hadoop framework maintains by default, we present in the following a new approach that take in consideration the difference between the cluster nodes computing capabilities, with respect to the nature of tasks to adjust data blocks distribution. The design of our solution is presented under two major phases, the first one is implemented during the HDFS input, and the second one is implemented while processing tasks are initiated.
Keywords:	Data, Big Data, Distributed Systems, Heterogeneous Systems, Hadoop Distributed File System; Distributed Storage; Distributed Computing, Sequencefile, Mapfile
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text

Title:	HENON CHAOTIC MAP BASED IMAGE ENCRYPTION SCHEME USING BIT-LEVEL CIRCULAR SHIFT
Author:	SYED SAQLAIN HASSAN, ZESHAN IQBAL, MUHAMMAD JAWAD IKRAM, MOHAMMED ISHAQUE
Abstract:	Recently, privacy has become a major issue in digital images transmitted over public networks. Although the said environment is suitable and quite useful, the unfortunate reality is that there exist numerous privacy and security threats. This article addresses the problem by proposing a new image encryption technique using a chaotic system and bit-level circular shift. A Henon Map has been used as a chaotic system to do the bit-level circular shift to encrypt the image. According to the experimental results, the proposed algorithm overcomes the shortcomings of conventional encryption techniques. The proposed technique has lower computational complexity and shows promising results in terms of various security tests. The keyspace is too large to avoid brute-force attacks. For the encrypted image, the histogram is uniformly distributed and far away from the original image. Thus, the statistical attack is not applicable here. The correlation test of the adjacent pixels shows no correlation between them. The proposed algorithm is key sensitive; tiny key-value modifications will end up with another different image. Therefore, the new technique is compatible with real-time image-encryption applications over public networks.
Keywords:	Bit-Level Circular Shift, Chaotic System, Encryption, Decryption, Henon Map
Source:	Journal of Theoretical and Applied Information Technology 31^st March 2022 -- Vol. 100. No. 06 -- 2022
Full Text