		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 2023 | Vol. 101 No.12

Title:	PRODUCT RECOMMENDATION SYSTEM DESIGN USING GRAPH DATABASE
Author:	FAUZAN RISQULLAH, EDWIN TUNGGORO, DHIKA NUR AISYAH, INDRAJANI SUTEDJA
Abstract:	The growth of data in the world is getting bigger, each person currently produces a lot of data that comes from their daily activities. To accommodate large data, appropriate data storage devices are needed. One of the data storage tools that is currently popular is the graph database. Therefore, this study aims to prove the capabilities of the graph database by creating a product recommendation system using one of graph database tools, TigerGraph. This research began by doing literature research for previously related researches that had been done. This research will use the database development cycle method in the database development process. The results obtained from this study are graph database capable of providing product recommendations that are in accordance with the trends and preferences of each user. The conclusion from this study is that graph database has reliable performance in processing data and it relationships and has a short time to process it so that users can get appropriate recommended product in a short time.
Keywords:	Graph database, Product Recommendation, TigerGraph, Cosine Similarity
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ASPECT-ORIENTED SUGGESTION MINING FROM OPINION REVIEWS
Author:	NAVEEN KUMAR LASKARI, SURESH KUMAR SANAMPUDI
Abstract:	Suggestion Mining refers to extracting suggestions from the opinionated text. The majority of existing re-search in suggestion mining does the binary classification of the given opinion review text as a suggestion or non-suggestion. The pioneering work ignored the fine-grained analysis, such as identifying the target to-wards which aspect the suggestion was mentioned or the target audience towards whom it intended to. However, such fine-grained analysis is more important in various use cases. A novel end-to-end hybrid model for fine-grained analysis of suggestions with aspect orientation has been proposed in this paper. We have utilized two different datasets of SemEval-2019 Task 9. The performance has been evaluated using other models from machine learning, neural network, and transfer learning with combinations of word em-beddings. The experiment results demonstrate that our approaches worked well for aspect-oriented sugges-tion mining.
Keywords:	Suggestion Mining, Word Embeddings, Aspect Extraction, Text Classification, Rule-Based System
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ESTIMATING THE LOCATION OF AN INDOOR CHAIR OBJECT FROM A SINGLE IMAGE USING A PERSPECTIVE GRID APPROACH
Author:	DARMA RUSJDI, YAYA HERYADI, GEDE PUTRA KUSUMA, EDI ABDURACHMAN
Abstract:	Estimating the 3D location of an object from a single camera is an important topic in the field of computer vision and computer graphics. The problem of transforming a 2D point from a single image to a 3D point is difficult unless it is located in the same plane, using an RGBD camera or at least using two images. Our study aims to discuss the perspective grid concept for estimating the 3D location of chair objects accurately on the floor surface using a single image from a cellphone camera. Our proposal to predict the 3D location of a single image from a camera goes through three experimental stages. First, setting the nine locations and four actual object orientations over the floor pattern in the room to get the bounding box position by utilizing the object detection pre-trained model. The second stage is the development of the perspective grid algorithm as a transformation of 2D points in the projected image to 3D points on the floor plane. The third stage is predicting the optimal object location in the image from the lower left and lower right bounding box positions (assumed to be on the floor surface where the z value is 0) with a perspective grid approach, to be projected into a 3D location prediction value on the floor plane. Then we evaluate the calculation of the deviation of the average prediction error from nine actual object locations, each object location, and each object orientation. The average error deviation result is 6.47 centimeters. This shows that the results are quite accurate compared to the dimensions of the object and the area of the room.
Keywords:	Bounding Box, Location Estimation, Object Detection, Perspective Grid, Single Image.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	A NEW ALGORITHM FOR LEADER ELECTION IN DISTRIBUTED THREE-DIMENSIONAL HONEYCOMB MESH NETWORKS
Author:	YOUSEF ALRABANAH
Abstract:	Leader failure is a fundamental issue in distributed systems. As multiple nodes (processes) work together to achieve a common task, coordination among them is requisite. Lack of a network leader leads to unstable and unreliable network. Moreover, if the leader crashes, a new else process should replace it as early as possible. This paper proposes a new leader election algorithm for leader failure in Three-Dimensional Honeycomb Networks. To simplify the election and to reduce number of exchanged messages, the algorithm breaks up the network into rings. The complexity analysis of the algorithm proves that the algorithm requires O(n) and O(n1.3) messages for best and worst cases respectively, in O(On) time steps to elect a new leader.
Keywords:	Leader Election, Honeycomb Mesh, 3-DHM, Distributed Systems, Coordinator
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	A NEW ALGORITHM FOR AUDIO FILES AUGMENTATION
Author:	ZAKARIA K. D. ALKAYYALI , SYAHRIL ANUAR BIN IDRIS , SAMY S. ABU-NASER
Abstract:	The study proposes a new approach for augmenting audio data that can be used to improve the performance of machine and deep learning algorithms. Augmentation techniques have been widely used to increase the size and diversity of data sets, but existing methods often fail to preserve the quality and naturalness of the original audio. The proposed algorithm uses the idea of slicing the audio file to generate new audio samples that retain the characteristics of the original recordings while introducing new variations. The effectiveness of the algorithm is demonstrated through experiments on heart problem classification task, where it outperforms existing methods in terms of accuracy and robustness. The proposed algorithm has the potential to enhance the performance of various audio-related applications such as speech recognition, music genre classification, and environmental sound analysis.
Keywords:	Algorithm, Audio, Augmentation, Variation Analysis, Audio Slicing
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	CHALLENGES OF ACCOUNTING PROFESSION ON INFORMATION TECHNOLOGY IN THE INDUSTRIAL REVOLUTION 5.0 ERA
Author:	GATOT SOEPRIYANTO, MEIRYANI, NORISSA LETICIA
Abstract:	Today technology is a basic necessity. An accountant who must be able to adapt to technological developments. In the era of society 5.0, digital disruption is increasingly real. This study aims to find out the challenges faced by the accounting profession with the advancement of information technology in the 5.0 industrial revolution era. This research is qualitative descriptive research guided by the existing problem formulation to examine the situation comprehensively. This study are based on data collected through literature studies and internet searches. This study aims to find out how far the role of accountants will survive in the era of the industrial revolution 5.0 with advances in information technology. The results of this study found that the accounting profession faces many challenges in the era of the industrial revolution 5.0, such as the need to adapt to rapid changes, understand the needs of customers and employers, and build capacity or compensation.
Keywords:	Industrial Revolution 5.0, Accounting Profession, Information Technology, Decision Making
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ANALYSIS OF UI/UX DESIGN IN E-COMMERCE ONLINE LOAN SERVICE THAT AFFECTS USERS DECISION
Author:	TANTY OKTAVIA, MARVELLA GUNAWAN, GLORIA PREYSILIAN EMOR, GLADYS PATRICIA, LISA POLIMAN, MAUREEN VALERIE
Abstract:	Online loan (also known as peer-to-peer lending) is a type of internet finance that is primarily used to meet the financial needs of small and medium-sized businesses as well as groups of individuals because of the large number of online loan applications that are currently being developed, each application has a distinct feature to emphasize in order to attract application users. In the previous research there are not specifically focus on the design of the application. Most of them prefer to describe functionality approach. Therefore, this research is to determine whether the design of the user interface and user experience influences user interest in using online loan applications. Including the main factors influencing lender trust, user decisions, and the impact of these factors on loan intentions. An online questionnaire was developed and disseminated to collect data from respondents within the scope of online loan users in Jakarta with different ages, gender, occupation, and experiences. After the usable data are collected, it is analysed through the SMART PLS (Version 4) software using the Partial Least Squares – Structural Equation Modelling (PLS-SEM) method with the objective of testing the hypotheses. The result from 120 qualified respondents shows that among the 5 existing variables, only Speed of Loan Approval (SL) have significant effect on User Interest (US) in customer’s interest to use the online loan service in E-Commerce applications.
Keywords:	P2P, online loan, SMART PLS-SEM, User Interest, User Acceptance, Decision
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	EVALUATION OF MULTIVARIATE DATA ACQUISITION OF NETWORK EMBEDDING SCHEME FOR HEALTHCARE APPLICATIONS
Author:	PAVAN MOHAN NEELAMRAJU, MOHAMED EL-DOSUKY, SHERIF KAMEL
Abstract:	In recent years, recommendation systems have evolved to provide valuable information with respect to a multitude of domains. In the ongoing medical revolution, they have been widely utilized for identifying trends from electronic record data. Techniques were developed to compute the correlation between patients suffering from diseases with similar symptoms, identification of treatment procedures and drug identification. However, the feasibility of the heterogeneous network embedding schemes needs to be studied in the dimension of varying input data formats and the corresponding performance. In the following work, emphasis is placed on understanding the impact of a variety of data, volume and the number of recommendations produced by the system. Further, the metrics such as precision and recall were utilised to evaluate the overall performance of the recommendation system, which is built upon Metapath2Vec. The current study extrapolates the effectiveness of the recommendation system using data gathered from 1500 influenza patients, further elucidating the ability of recommendation systems to identify distinct trends from the disease's symptoms that are perceptible to people. In addition to the implementation of Metapath2Vec and corresponding analysis, a detailed note is provided on elucidating the future of network embedding schemes and recommendation systems.
Keywords:	Network Embedding, Recommendation System, Metapath2Vec
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	COMPARISON ANALYSIS OF BOLDI-VIGNA ζ2 ALGORITHM AND END-TAGGED DENSE CODE ALGORITHM ON AUDIO FILE COMPRESSION
Author:	HANDRIZAL, PAUZI IBRAHIM NAINGGOLAN, AFIF REFANO MUFID
Abstract:	In this modern era, everything is done online including data-sending activities. However, the problem faced today is the large size of the data, which causes the length of the sending process and the use of large storage capacity. Therefore, to overcome this problem, data processing techniques are needed, one of which is compression techniques. Data compression aims to reduce the size of the data, reduce the bandwidth required when transmitting data, and reduce the need for data storage. Wav files are widely used in game creation, which is commonly used for sound effects and music, wav files tend to have a large size. So compression techniques are needed to reduce the size of data or files. The Boldi-Vigna algorithm takes advantage of locality and similarity in graph data. This algorithm mostly supports random access, except for the implementation of the required reference compression. In the End-Tagged Dense Code (ETDC) algorithm, instead of using a flag bit to signify the beginning of a codeword, the flag bit is used to signify the end of a codeword. This study tested a comparison of data compression between the Boldi-Vigna ζ2 algorithm and the End-Tagged Dense Code algorithm using audio files in 8-bit format with an extension of *.wav. Based on testing in this study, it was found that the Boldi-Vigna ζ2 algorithm is better in the audio file compression process with an average Ratio of Compression of 73.81%, an average Compression Ratio of 1.58, and an average Space Savings of 26.18%. While the End-Tagged Dense Code algorithm has a better compression time with an average compression time of 1.05 seconds. It can be concluded that the Boldi-Vigna ζ2 algorithm is better at compressing audio files, while the End-Tagged Dense Code algorithm is faster at performing the compression process. The compression results obtained are influenced by the number of the same digital values contained in the wav audio file that needs to be compressed. Both algorithms can restore the whole audio file like the original audio file through the decompression process.
Keywords:	Compression, Audio, Boldi-Vigna ζ2, End-Tagged Dense Code
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	UNCOVERING USER PERCEPTIONS TOWARD DIGITAL BANKS IN INDONESIA: A NAÏVE BAYES SENTIMENT ANALYSIS OF TWITTER DATA
Author:	MULYANI KARMAGATRI, CLARISA FEZIA AMANDA AZIZ , WINI RIZKI PURNAMA ASIH, ISMA ADDI JUMRI
Abstract:	The use of digital banks in Indonesia has rapidly increased in recent years in response to the adoption of new technologies and changes in consumer behavior. User responses to digital banks vary depending on their experience throughout their transactions on the application, which may result in satisfaction or dissatisfaction. Social media platforms such as Twitter have become a space for companies to obtain textual data related to customer reviews and their brand image. In this study, data obtained from Twitter have undergone the stages of data crawling and data cleaning. The subsequent stages involved classification using the Naïve Bayes algorithm and word cloud visualization to identify the most commonly used words based on user responses. The results of this study indicate that users' positive sentiment towards digital banks is influenced by the application's ease of use, while dissatisfaction is caused by technical constraints experienced during the administrative process. The positive, negative, and neutral sentiments in this study are used to identify business opportunities for digital banks and practical implications for future digital banking services.
Keywords:	Digital Bank, Sentiment Analysis, Naïve Bayes, User Experience, Machine Learning
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	DIGITAL TWIN OF THE QUALITY MANAGEMENT SYSTEM FOR ENVIRONMENTAL CONTROL OF THE NEAR-AIRDOM ENVIRONMENT
Author:	LEKEROVA FARIZA, KOSHEKOV KAIRAT, ALIBEKKYZY KARLYGASH, BELGINOVA SAULE, BYGUBAYEVA ALINA, ISMAILOVA RAUZA
Abstract:	The purpose of this study is to develop a formal approach in order to assess the reliability and risks in the airfield control system. This referred to the digital transformation of the aviation industry business. To achieve this goal, the following tasks are solved: primarily, the geometric model of controlled airspace were justified in the area of the Almaty airport. This geometric model is presented in the form of an atmospheric cylinder with a given radius and height. In addition, there was developed a functional and technological model of the airfield quality monitoring system in Almaty. This was based on the use of unmanned aerial vehicles with constant radio communication operated by environmental control center at the airport. Also, there was built a virtual-spatial information 3D model of atmospheric pollution near the aerodrome environment in the "Digital Twin" format. Therefore, a fuzzy model of an integral criterion for assessing air quality in the controlled area of the Almaty airport has been developed. Additionally, there have been developed a probabilistic model on order to assess the reliability and risks of air pollution control in the near airfield environment.
Keywords:	Aviation Industry, Digital Twin, Risk, Technology, Model, Reliability, Probability
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	GENETIC FEATURE SELECTION AND NAIVE BAYES FOR EFFICIENT HEART DISEASE PREDICTION
Author:	Dr. RALLA SURESH , Dr.NAGARATNA PARAMESHWAR HEGDE
Abstract:	Heart disease is the leading cause of death in the world and it is easier to treat when detected early. The data in the health sector are huge but have not been used potentially because of its complexity in the system. The main reason for the complexity is the lack of adequate data analysis tools in the key patterns. Machine learning can help in the retrieval of useful information from existing data and it also helps in the training of a model to forecast patients' health, which is faster than clinical experimentation. The Cleveland heart datasets have been used in a lot of studies. The existing K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Logistic Regression, Naive Bayes, and other classifiers were used to limit the number of selected attributes. The present research applied Genetic algorithm (GN) modeling to discover the 16 related features of the heart data set from hospitals, in India. The proposed model showed transparent and reliable graphical representation with other attributes which has the ability to predict the disease. The proposed model obtained 95 % accuracy better than existing models.
Keywords:	Artificial Intelligence, Genetic algorithm, machine learning, Naive Bayes Classifier.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	LOW RESOLUTION FACE RECOGNITION USING COMBINATION OF GPEN SUPER RESOLUTION AND FACENET
Author:	KHAIRUL SHALEH ZEBUA, IMAN HERWIDIANA KARTOWISASTRO, GEDE PUTRA KUSUMA
Abstract:	Face Recognition has been one of the most active research areas in computer vision nowadays. It has widely applied in various applications in real human activity and has reached super good performance in term of accuracy. Deep learning approach significantly improves the accuracy. But it’s mostly evaluated in High-Resolution (HR) images. Nevertheless, the Low-Resolution Face Recognition (LRFR) remains a challenging part. Recognizing face of images in low-resolution (LR) scenarios could possibly decrease the accuracy of predictions due to that LR images usually lack discriminative details. One of the solutions commonly used to improve accuracy by applying concept of Super Resolution (SR) to produce the better quality of image from LR to HR. This research aimed to solve the issue in LRFR problem to get the better accuracy by using combination of SR method with GPEN and FR with FaceNet. The model is evaluated on labelled faces in the wild (LFW) dataset. LFW dataset is filtered to person that has at least five images of faces per label so that found 423 classes. The filtered LFW dataset with 423 classes then augmented with horizontal flip to generate more dataset as input to FaceNet model. Accuracy of training, testing and validation are captured and presented at this report. The results are compared with bicubic interpolation method with data augmentation and without data augmentation. Based on that, with data augmentation the accuracy is getting better. In result, this combination method can produce training accuracy score of 82.8%, validation accuracy score of 66,6% and testing accuracy score of 69% with data augmentation.
Keywords:	Super Resolution; Face Recognition; Generative Adversarial Network; GPEN Model; FaceNet Model
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	PENETRATION TESTING IN MOBILE DEVICES, VULNERABILITIES AND SOLUTIONS
Author:	MARIAM ALHAMED, RAWAN BUKHOWAH , SARA ALSAHAIM, AND MOUNIR FRIKHA
Abstract:	Mobile phones have become an essential thing these days, in education, entertainment, even in the medical field, all these uses for mobile phone led to the fact that mobile phone contains a huge number of data should be protected. Mobile phones with all of its features have also vulnerabilities could anyone exploits, to maintain the security of the mobile phone it has to scan in every specific and regular time to determine vulnerabilities and the security issues to patch and fix by using the penetration testing operation. This paper will represent the OWASP mobile top ten security vulnerabilities, as will identify the different mobile threats and their countermeasures, and the research will review the models for penetration testing threats. This research represents a Mobexler mobile application penetration-testing framework to verify the security vulnerabilities in IOS application, which is LinkedIn application, the methodology divided into seven phases: 1. Planning 2. IPA file and information gathering 3. Selecting application 4. Selection security tools 5. Setup and analysis 6. Manual review of Appxmanifest.xml 7. Dynamic analysis which checks for vulnerabilities and detect security misconfiguration.
Keywords:	Penetration Testing; Mobile Devices, IOS, OWAPS, Threat
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	OPTIMAL POWER FLOW PROBLEM SOLUTION USING DIVERSE SOFT COMPUTING TECHNIQUES
Author:	VEMULAPALLI HARIKA, HEMALATHA JAVVAJI, GUDAVALLI MADHAVI, MOHAMMED AZAHARAHMED, G.VEERANNA, MAJAHAR HUSSAIN MAHAMMAD
Abstract:	In attempting to discourse the optimal power flow (OPF) problem, various effective and trustworthy evolutionary-based methodologies are laid out in this article. The suggested methods make use of several algorithms to configure OPF issue control variables optimally. The constraints put on the optimized objective functions are greatly reduced when the social group optimization (SGO) technique is used to solve the OPF problem. The anticipated method has been investigated and tested on the industry-standard IEEE 30-bus test system and IEEE 57 bus test system with a variety of goals in mind, including reducing fuel costs. Results from the suggested strategy have been contrasted with those from other optimization methods. The results are encouraging and demonstrate the resilience and efficacy of the suggested strategy.
Keywords:	Optimal Power Flow(OPF), Differential Evolution(DE), Artificial Bee Colony Algorithm(ABC), Particle Swarm Optimization(PSO), Firefly Algorithm(FF), Social Group Optimization(SGO).
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	EXAMINATION OF VOLTAGE STABILITY BY CONSIDERING CPF ALGORITHM WITH STATCOM UNDER CONTINGENCY
Author:	GUDAVALLI MADHAVI, VEMULAPALLI HARIKA, HEMALATHA JAVVAJI, K.KIRAN KUMAR, MOHAMMED AZAHARAHMED, MAJAHAR HUSSAIN MAHAMMAD
Abstract:	The use of Continuation power flow (CPF) analysis is introduced in this paper as a means of assessing and analyzing the voltage stability and controlling power flow in large scale -systems. This method initially starts with system base values and progresses to the critical point while continuous maintaining stability even with single precision computation. In the event of transmission line and failure of transformer, the other branches may become overloaded, and there exits the system voltage fluctuations. This paper mainly aims the specific case of line contingency (emergency) and examines the impact STATCOM on various parameters like system voltage, reactive power, and voltage stability using the CPF Algorithm.
Keywords:	Continuation Power Flow; Contingency; STATCOM; Stability Index.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	SWARM INTELLIGENCE ALGORITHMS FOR PHISHING WEBSITE DETECTION
Author:	SOHA ALHELALY
Abstract:	Phishing websites are one of the biggest threats Internet users face today, and they require constantly updated techniques to combat the increasing number of such threats. So far, various methods have been proposed to increase the efficiency of phishing website detection. Swarm intelligence (SI) is one of the approaches that has garnered the interest of researchers working in the phishing website detection field. This article presents an up-to-date review of the SI techniques used for phishing website detection, which deserves wider investigation by researchers. Another contribution of this paper is to provide a comparison of the effectiveness of various SI-based phishing website detection techniques. Based on the survey result, we provide a clear overview of which approach is more suitable for each case and highlight the need for future research efforts devoted to the unique features of the SI for phishing website detection.
Keywords:	Phishing website detection, Swarm intelligence, Anti-phishing, Bat algorithm (BA), Particle swarm optimization (PSO), Artificial bee colony (ABC), Ant colony optimization (ACO), Gray wolf optimizer (GWO), Salp swarm algorithm (SSA), Firefly algorithm (FA),
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ARE THERE POINTS OF SIMILARITY BETWEEN THE CLASSIC OBJECT-ORIENTED APPROACH AND THE MODEL PROGRAMMING APPROACH?
Author:	AZIZ SRAI, FATIMA GUEROUATE
Abstract:	NoSQL databases (also known as Not Only SQL databases) are non-relational database systems used to store and retrieve data. Today, NoSQL databases are widely used in real-time web applications. NoSQL databases can also be referred to as big data databases or cloud databases. NoSQL databases are generally faster than SQL databases, so NoSQL databases are used for big data usage. In this article, we compare the two approaches, the classic approach (object-oriented development) and the new approach (model-driven approach or Model Driven Architecture), taking NoSQL databases as a case study. We first developed a software solution applied to the NoSQL database using the classic object-oriented approach using Spring Boot and secondly, we developed the same software solution through the use of the model approach or MDA in order to reconcile the two approaches in terms of implementing platform independence and in terms of development cycle time. We took as a case study, a use case of an eStore platform (class diagram). Considering an application in its entirety is a difficult task, which is why we first represented the platform with a simple class diagram.
Keywords:	Big Data, MDA approach, NoSQL, QVT, PIM model.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	CLASS IMBALANCE LEARNING WITH COSTSENSITIVE- ACGAN
Author:	ATHIRAH HAZWANI BINTI ABDUL HALIM, NORIDAYU BINTI MANSHOR, NOR AZURA BINTI HUSIN
Abstract:	The class imbalance problem has been recognized in many real-world applications and negatively affects machine learning performance. Generative Adversarial Networks or GANs have been known to be the next best thing in image generation. However, most GANs do not consider classes and when they do, cannot perform well under the imbalance problem. Based on related works, the modification of the loss function and various resampling methods have been commonly applied to counter the problem of class imbalance. In this study, CostSensitive-ACGAN is introduced which is a variation of Auxiliary Classifier GAN (ACGAN) that can work better under the class imbalance condition. This method incorporated the idea of applying cost-sensitive learning in the loss function to further improve the classification of minority classes. Cost-sensitive parameters are determined adaptively according to the classification error of the class to improve minority classes presence. By applying higher misclassification costs for minority classes, these instances can be magnified and recognized by the discriminator thus improving image generation altogether. This method has shown comparatively competitive results with existing benchmark models.
Keywords:	Computer Vision, Generative Adversarial Networks, Imbalance Learning, Cost-sensitive, Convolutional neural network, Loss function, Image generation.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ANALYSIS OF SPEAKER ADAPTATION TECHNIQUES IN AUTOMATIC SPEECH RECOGNITION SYSTEMS USING DEEP NEURAL NETWORKS AND GAUSSIAN MIXTURE MODELS
Author:	VEERA V RAMA RAO M, KUMAR N
Abstract:	The accuracy of automatic speech recognition (ASR) systems can be affected by changes in training and testing environments. In the context of adaptation, narrowing the model-to-dataset discrepancy for a certain speaker or channel is quite effective. Two of the most widely used ASR methods nowadays are deep neural networks and Gaussian mixture models (GMMs). GMM-HMM has been a standard approach in ASR systems for decades. Speaker adaption is especially helpful to AMs in this particular subgroup. Efforts have been made to help this group in several ways. DNN-HMM AMs, on the other hand, have lately beaten GMM-HMM models in ASR tasks. These AMs, on the other hand, frequently have to retrain their accents, which can be difficult for them. As a result, many GMM model modification processes do not apply to DNNs. An explanation of GMM models, as well as ways for increasing speaker adaption, is the primary purpose of this study Domain Adaptation Challenge unsupervised domain adaptation goal data might be collected using DNNs as well (DAC). An out-of-domain system's speaker recognition performance is improved by more than 25 percent by using a DNN trained on data from outside the domain.
Keywords:	Gaussian mixture models, GMM-HMM, Speaker adaptation, AMs, ASR
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	A UNIFIED FRAMEWORK FOR BIG DATA-DRIVEN DECISION MAKING SYSTEM IN HIGHER EDUCATION INSTITUTES
Author:	MAMOUN ABU HELOU
Abstract:	Higher education institutions (HEIs) are increasingly using information and communication technologies in their daily operations, including management, financial, and didactic processes. As a result, the amount of produced data has increased dramatically in heterogeneous formats, and the lack of connectivity between the various systems has made it difficult for decision-makers to obtain integrated and relevant information that accurately reflects the institution's actual condition. Business Intelligence (BI) systems and big data technologies can take advantage of the various data sources accessible at HEIs to facilitate the processes of decision-making by enabling managers to make precise decisions that are efficient and effective with respect to time and formats. Several efforts focused on studying and enabling BI capabilities for managing sustainable information in an HEI context. Despite these attempts, integrating big data into HEIs remains an open challenge, and additional studies are required in order to determine the best techniques for employing big data analytics and enhance the results. In this research, qualitative and analytic research methodologies are used to identify and design a theoretical BI framework that incorporates best practices and takes into account big data analysis capabilities. The proposed framework combines the data analysis steps commonly used by HEIs and provides a framework made up of six components: the key stakeholders; the key business operations; the data identification; the data processing; the presentation of data; and the system's evaluation, validation, and monitoring. The framework is designed such that it can be adapted to various data sources and deploy different analytical scenarios, including descriptive and predictive analytical scenarios. The framework can be used as a guideline for current practice for implementing a BI in HEIs. Open research concerns and challenges are also identified.
Keywords:	Higher Education, Decision Making, Business Intelligence, Data Analytics, Big Data.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	AN IMPROVED SENTIMENT CLASSIFICATION MODEL USING BERT CLASSIFICATION WITH RANGER ADABELIEF OPTIMIZER
Author:	SHIRAMSHETTY GOUTHAMI , DR . NAGARATNA P . HEGDE
Abstract:	Sentiment analysis is a useful technique for extracting opinions from unstructured data that includes language like product and movie reviews. It can be used to gather customer feedback, evaluate brand perception, and conduct market research. In the field of Natural Language Processing (NLP), sentiment analysis of Twitter data has recently emerged as a popular topic. Twitter data sets are compiled using the Twitter API and contain real-time tweets about various topics. Automated text analysis is used to determine public opinion on specific issues. Although many machine learning algorithms are utilized for this purpose, previous approaches have failed to enhance the accuracy of categorization and classification as per industry requirements. To address this issue, a Long Short-Term Memory (LSTM) framework was introduced. This approach was applied to analyze airline customer feedback data from Twitter, and it resulted in improved classification performance. However, the LSTM framework achieve better performance for small and medium size datasets only. The performance degraded when applicable for large amount of data. To address the limitation of LSTM framework, in this research work proposed Bidirectional Encoder Representations from Transformers (BERT) classification and the Ranger AdaBelief optimizer. The BERT classifier is used for classification, and Ranger AdaBelief is employed to optimize loss during the classification process. The proposed model achieved better results than previous research, with an accuracy of 92.54%, precision of 90.15%, recall of 90.24%, and F1-score of 91.14%. The BERT classification with Ranger AdaBelief optimizer significantly outperformed previous approaches for sentiment analysis classification.
Keywords:	Data Pre-process, BERT Classifier, Ranger AdaBelief Optimizer, Sentiment Analysis, Error Rate Analysis
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	DEEP LEARNING APPROACH TO DETECT FACIAL ASYMMETRY FOR PARALYSIS DETECTION
Author:	SAMUEL SUSAN VEERAVALLI , DR. PRAJNA BODAPATI
Abstract:	Facial paralysis is the inability to contract the muscle nerve on one (or both) of the sides of face, which directly results in deforming or a droopy face. This is considered as one of the diseases that is increasing its rate of infection in recent times. There are many causes for Facial paralysis and is also a common symptom in people who have suffered a brain stroke. Although, there are vast applications with the help of technology is being used in different areas of medical diagnosis, there are very few notable models for detection of facial paralysis available presently. So, this work proposes an efficient model with the help of deep learning models which were trained and known to be best for image analysis. In this, the input is a dataset consisting of images that are normal faces and paralyzed, different models are implemented of those to classify them. The algorithms which resulted in obtaining the best accuracy are DenseNet201, VGG19 and InceptionResNetV2, with an accuracy of 99.84%, 99.51%and 99.19% respectively.
Keywords:	Facial paralysis, image classification, DenseNet201, VGG19 and Inception Resnet
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	THE EXPERIENCE OF INTRODUCING DIGITAL TWINS INTO THE EDUCATIONAL PROCESS ON THE EXAMPLE OF TRAINING IN THE REPAIR OF AIRCRAFT EQUIPMENT UNITS
Author:	ZHARAS AINAKULOV, KAYRAT KOSHEKOV, NATALYA ASTAPENKO, ILDAR PIRMANOV‬, ABAY KOSHEKOV
Abstract:	The utilization of digital twins in education is a promising approach that offers novel possibilities for delivering theoretical and practical knowledge. Digital twins transform the way users interact with devices, allowing for experimentation and innovation without the fear of damaging expensive hardware. Aircraft repair training is a complex and costly process that requires innovative educational tools and technologies. In this study, we developed a training software that utilizes an adaptive interval repetition method based on H. Ebbinghaus, P. Pimsler, and S. Leitner's methods to train learners in aircraft repair. We utilized 3D models created in SolidWorks and Blender3D software packages and implemented the program script in the Unreal Engine environment. To evaluate the effectiveness of the mechanism, we collected feedback from participants and analyzed learning outcomes in both experimental and control groups. Our training software employs an asynchronous approach to information acquisition, enabling learners to create personalized learning trajectories. Our results demonstrate the effectiveness of the proposed mechanism for educational systems and virtual reality technology in general. This innovative approach is not limited to aviation but can be applied in other engineering disciplines as well.
Keywords:	Digital Twins, Interval Repetition Method, Virtual Reality, Training Software, 3d Model, Higher Education
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ENHANCING CONTROLLER EFFICIENCY IN HYBRID POWER SYSTEM USING INTERVAL TYPE 3 FUZZY CONTROLLER WITH BACTERIAL FORAGING OPTIMIZATION ALGORITHM
Author:	J. VINOTHKUMAR, DR R. THAMIZHSELVAN
Abstract:	Microgrids (MGs) are designed with the help of effective power extracted from renewable sources such as rooftop solar panels, photovoltaic cells, batteries, floating PV and solar PV with the grid. In a hybrid microgrid, Interlinking Converter (ILC) is a key component to connect the AC sub-grid and DC sub-grid. DC-DC converters are being used as power converters in between load and source to enforce and increase the PV depending on the voltage output signal. Accordingly, the work focused on a Multi-Input (MI) KY boost converter. This Proposed topology gathered maximum power using multi-input KY boost converters for hybrid energy. This hybrid topology operates mainly delivered power from renewable energy sources solar/wind to dc bus. In the absence of any one source, wind or solar supplies power to the dc bus. Without any renewable energy, sources battery deliver the power to the dc bus. The research proposed the interval type 3 fuzzy controller is used for controlling the load frequency of the multi-area system. Swarm-based hybrid metaheuristic optimizer of the Bacterial Foraging Optimization Algorithm (BFOA) is proposed for optimal tuning and controlling the PI controller parameters. Controlling the reactive power of the hybrid power system model with the aid of a Static Synchronous Compensator (STATCOM). A unique controller is deployed to regulate the AC and DC currents of the STATCOM using two PI controllers. In this paper effectiveness of the hybrid power system is simulated through MATLAB/SIMULINK. The battery current and voltage of this produce 2000 A and 205 V, grid voltage produced in this work is 1.9×〖10〗^4 V and the power of the work produce approximately 90 kW. The results show that the interlink converter improves the flexibility of the hybrid microgrid and, in addition, the power quality of the energy supplied in the utility grid is improved. In future, an intelligent control algorithm may be presented to improve the control strategies of the HMG, respectively.
Keywords:	Microgrids, Hybrid Metaheuristic Optimizer Fuzzy Controller, Multi-Input KY, Boost Converter, STATCOM
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	MAYFLY OPTIMIZED EXTREME GRADIENT BOOSTING FOR SINGLE DECOMPOSITION BASED SHORT TERM SOLAR POWER PREDICTION
Author:	RAJ KUMAR PARIDA , MONIDEEPA ROY , AJAYA KUMAR PARIDA , ASIF UDDIN KHAN , SUDAN JHA
Abstract:	Solar power is one of the cleanest form of renewable energy, which can be mostly used for grid interactive mode without much difficulty. PV power prediction plays an important role when grid connected mode is considered. At present scenario proper prediction is greatly valued as it is directly related to various environmental conditions. Accurate prediction helps in proper maintenance planning. This paper develops a hybrid model which employs mayfly optimization and extreme gradient boosting technique (XGB). The Meta heuristic optimization technique is used for obtaining the optimized hyper parameters. As per the previous literature study XGB is observed to give more accurate result as compared to previously implemented techniques like Support Vector Machine, Extreme Learning Machine etc., but the main drawback of XGB is observed when external noise is inserted i.e it faces the over fitting problem. The proposed model with the help of optimization technique optimizes the learning rate and maximum depth thus providing more accurate result. The proposed method is verified under different weather condition and different geographical location. The experimental result supports the fact that the proposed hybrid model performs better than the Random Biased Functional Network technique, Support Vector Machine and Extreme Learning Machine technique. The performance accuracy is supported by different statistical tests like Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Correlation coefficient (R2). The MAPE for RBFN is obtained to be 4.87 % which is greater than the proposed hybrid model by 1.19 %.
Keywords:	Solar Power Prediction, Meta heuristic optimization, mayfly optimization and extreme gradient boosting technique
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	CUCKOO HASH BASED MULTI FACTOR AUTHENTICATION (CH-MFA) - IN SECURED COMMUNICATION WIRELESS SENSOR NETWORK
Author:	C. VENKATACHALAM , Dr.A.SURESH
Abstract:	As a vital component of the information sensing and aggregating for big data, cloud computing and information security in wireless sensor networks (WSN) is critical. Due to constrained sensor node resources, WSN is becoming a vulnerable target to many security attacks. Cuckoo Hash based Multi Factor Authentication (CH-MFA) Mechanism for secured communication in wireless sensor organization. CH-MFA instrument includes two phases, the registration and authentication phases. At first, in the registration phase, the node must register the node's ID and password to the base station. Then, at that point, the registered information is put away in the base station utilizing Cuckoo Hash work. The prototype model for cloud computing's cloud server uses open source technology. The proposed framework shows a close agreement with the standard criteria for security.
Keywords:	Cuckoo, Hash, Multi, Factor, Authentication, communication, Wireless, Sensor, Network;
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	PERFORMANCE ANALYSIS OF GLOBAL AND LOCAL BASED DIMENSIONALITY REDUCTION IN HYPERSPECTRAL IMAGES
Author:	M. R. VIMALA DEVI , DR. S. KALAIVANI
Abstract:	Hyperspectral images possess abundant and fine spectral details compared to other remote sensing images. Hyperspectral images have several hundreds of bands leading to more complexity, issues in handling the images with vast dimension, the need of immense storage and transmission, high correlation between the bands and moreover automatically processing time also becomes high. This makes the need of dimension reduction methods as a pre-processing step in hyperspectral image analysis. An overview of state of art dimension reduction methods and its application in end member extraction stage of spectral unmixing were discussed in this paper. The performance analysis of Scale Invariant Feature Transform (SIFT) based dimension reduction is analysed in two ways by extracting endmembers from a single pixel and from endmember bundles. Also the performances of dimension reduction methods were investigated with the help of spectral angle distance. Further, spectral unmixing can be utilized as a post-processing technique in classification, target detection and identification.
Keywords:	Hyperspectral image, Endmember Extraction, Dimension Reduction, Scale Invariant Feature Transform, Spectral Unmixing.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	NIFR-NODE INTERFERENCE AND FAILURE RECOVERY FRAMEWORK FOR MULTIMEDIA TRANSMISSION IN WMSNs
Author:	CH.JANAKAMMA, DR.NAGARATNA P. HEGDE
Abstract:	The proliferation of mobile communication technologies has led to a surge in demand for multimedia services and applications. Wireless sensor networks facilitate the collection and transmission of multimedia data such as audio and video. However, this also results in a significant increase in the volume of multimedia data, which in turn, places a high demand on bandwidth and energy consumption during the process and transmission of such data. To tackle the challenges associated with multimedia data transmission in Wireless Sensor Networks (WSNs), Janakamma et. al proposed a Novel Routing Protocol for Wireless Multimedia Sensor Networks (NRP-WMSN)[12] which improved network performance and achieved high Quality of Service (QoS) for multimedia data transmission. Although the proposed protocols improved performance, they needed to address node interference and node failure(energy hole) in WMSN. To address the limitations of the existing system, this paper proposes a Node Interference and Failure Recovery (NIFR) framework that reduces node interference by selecting an optimal path and also recovers node failure through trust recurrence method. The proposed framework enhances WMSN by addressing the issues of node interference and node failure. The proposed NIFR framework is implemented using NS2 simulation. Empirical results show that the proposed framework improves the performance of multimedia data transmission in WMSN.
Keywords:	Quality of Service, Node Interference and Failure Recovery, Novel Routing Protocol, Wireless Multimedia Sensor Networks, Node Failure.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	A SYSTEMATIC SURVEY ON CRYPTO ALGORITHMS USING QUANTUM COMPUTING
Author:	GOVINDU SURLA , R. LAKSHMI , I. THAMARAI
Abstract:	The concept of a quantum computer is now well-established. It's the most cutting-edge tech out there, and every nation is competing for quantum supremacy. It is technology that will reduce computing time from decades to hours or minutes. Access to quantum computing capabilities will be a huge boon to the scientific community. The issue it raises, however, is one of the greatest cyber security dangers we face today. To that end, this paper will first present the reader to some fundamental post-quantum algorithms and then elaborate on the effects of quantum computing on modern cryptography. All cryptographic algorithms are theoretically susceptible to attack. When commercial quantum computers with billions of qubits of capacity become available, they will be able to decrypt virtually all existing public-key cryptosystems. The use of public key cryptography has enabled the conduct of secure online transactions. Yet, the security of the most widely used public key cryptography techniques in use today is threatened by breakthroughs in quantum computers. However, quantum cryptography is a promising technique that is set for widespread acceptance in actual cryptographic applications since it has been shown to be secure even in the most general assault allowed by the rules of physics. Using quantum cryptography, two people can build on an existing secret key. To accomplish this, several quantum cryptography techniques have been developed. We go over some of the concerns that protocol designers might need to take into account if it becomes necessary to employ these algorithms and give an overview of some of the developed cryptographic algorithms that, while not yet widely used, were thought to be resistant to quantum computing assaults.
Keywords:	Quantum Computation, Quantum Theory, Cryptography, And Quantum Public Key Distribution
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	NEW SERVICES AND APPLICATIONS CAN LEVERAGE THE POWER OF LOW RELIABLE AND LATENCY COMMUNICATION FOR MISSION CRITICAL DISTRIBUTED INDUSTRIAL INTERNET OF THINGS
Author:	VUTUKURI SARVANI DUTI REKHA , SWARUPA RANI BONDALAPATI, RATNA KUMARI VEMURI , RAMARAO GUDE , PRAVEEN TUMULURU, Dr. SURYA PRASADA RAO, BORRA
Abstract:	It can be expensive and difficult to build up centralised wireless communication systems that achieve ubiquitous, ultra-reliable, low-latency consensus. Consensus mechanisms have been used extensively in distributed systems, and they can provide fault tolerance for the critical consensus even when the reliability of the individual communication links is low. This paper introduces Raft, a popular consensus mechanism, to the Industrial Internet of Things with the goal of achieving an ultra-reliable and low-latency consensus, and it examines the consensus reliability performance in terms of node number and link transmission reliability. By introducing the notion of reliability gain, we demonstrate the linear relationship between consensus reliability and the reliability of the transmission of information through the communication links. Also, we discover that the time latency of consensus undermines its validity. The findings can be used as guidelines for implementing the Raft protocol in decentralized IIoT environments.
Keywords:	Distributed industrial Internet of Things, consensus mechanism, raft, reliability, latency, fault tolerance.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	BILINGUAL SENTIMENT ANALYSIS ON MALAYSIAN SOCIAL MEDIA USING VADER AND NORMALISATION HEURISTICS
Author:	JAMES MOUNTSTEPHENS , MATHIESON TAN ZUI QUEN, LAI PO HUNG
Abstract:	This research addresses a number of important issues involved in performing Sentiment Analysis (SA) on Malaysian Social Media (SM), including an analysis of bilingual or mixed language, choice of sentiment lexicon, normalisation heuristics, and the use of public datasets. This work is the first to quantify the level of language mixing in informal Malaysian text. Analysis of the 2M tweet Malaya dataset revealed a significant level of English sentiment content in Malaysian social media (13.5%), demonstrating the neccessity of a bilingual approach to Malaysian Sentiment Analysis. Significant patterns in noisy Malaysian SM text were identified and heuristics for normalising them were devised. The popular and effective English lexicon-based SA system VADER (Valence Aware Dictionary and sEntiment Reasoner) was translated to Malay using automatic and manual methods, with the combination of English and Malay VADER yielding a bilingual SA system. A subset of the Malaya dataset was both corrected and extended from two to three classes in order to properly test the bilingual SA system. Bilingual VADER with normalisation heuristics was able to achieve an impressive level of performance on a three-class problem (accuracy=0.71, mean F1=0.72), as compared to Malay VADER alone and several popular machine learning-based algorithms.
Keywords:	Sentiment Analysis, Malaysian Social Media, Mixed language, VADER, Normalisation
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	ENERGY CONSUMPTION MANAGEMENT IN WIRELESS SENSOR NETWORKS FOR ECG MONITORING SYSTEM
Author:	MAJDA LAKHAL , MOHAMED BENSLIMANE , MEHDI TMIMI , ABDELALI IBRIZ
Abstract:	Wireless sensor networks are applicable in almost every field of human activity. One of the promising application areas of Wireless Sensor Networks is medicine where WSN technology offers an important support, which allows remote consultations of patients regardless of their geographical location. The network consists of several small sensor nodes that are deployed in the zone to detect. The nodes have the ability to process, communicate and detect, allowing them to perform their functions in coordination. In recent years, this technology has made significant progress, but energy management has not developed to the same extent while the battery is the main source of energy. In addition, the network environment may prevent charging or replacement of the battery after deployment. The classic solution to this energy efficiency problem is to manage the activation period. This involves alternating the active and inactive states of a node periodically or not [15]. In this paper, we focus on the ECG monitoring system which plays a key role as a diagnostic device for cardiac abnormalities, to monitor the cardiac health of patients remotely while minimizing energy consumption.
Keywords:	WSN, WBAN, ECG, Electrodes, Energy.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text

Title:	DESIGNING A USER INTERFACE APPLICATION FOR A COLLECTION OF RECIPES USING THE DESIGN THINKING METHOD
Author:	NURUL ATIAH, WAHYU SARDJONO
Abstract:	The Covid-19 pandemic has changed people's behaviour, so people are more concerned about their cleanliness and environment, one of which is food hygiene. People now prefer to cook by themselves by watching cooking tutorial videos. However, the number of recipes circulating on social media does not guarantee the accuracy, so some people cook them with bad taste. In this paper, we will discuss the design of a User Interface Design for a mobile application called 'Koken' to help users find accurate references to recipes without having to buy groceries directly from the market. The method used in this study, namely design thinking, is an approach and process of thinking in finding the concept of the design of an application. Design Thinking has five stages: empathize, define, ideate, prototype and test. The final result of this research is the user interface design for the 'Koken' application. Koken app has a recipe recommendation feature based on the ingredients it has, a short video collection feature about cooking, and a shopping feature to make it easier for users to find ingredients and tips about cooking. This User Interface Design has also been tested with Usability Testing. It is hoped that this interaction design can be a reference in making the actual application.
Keywords:	User Interface Design, Recipes, Design Thinking, Usability Testing, Mobile Application.
Source:	Journal of Theoretical and Applied Information Technology 30^th June 2023 -- Vol. 101. No. 12-- 2023
Full Text