cover
Contact Name
Rahmat Hidayat
Contact Email
mr.rahmat@gmail.com
Phone
-
Journal Mail Official
rahmat@pnp.ac.id
Editorial Address
-
Location
Kota padang,
Sumatera barat
INDONESIA
JOIV : International Journal on Informatics Visualization
ISSN : 25499610     EISSN : 25499904     DOI : -
Core Subject : Science,
JOIV : International Journal on Informatics Visualization is an international peer-reviewed journal dedicated to interchange for the results of high quality research in all aspect of Computer Science, Computer Engineering, Information Technology and Visualization. The journal publishes state-of-art papers in fundamental theory, experiments and simulation, as well as applications, with a systematic proposed method, sufficient review on previous works, expanded discussion and concise conclusion. As our commitment to the advancement of science and technology, the JOIV follows the open access policy that allows the published articles freely available online without any subscription.
Arjuna Subject : -
Articles 59 Documents
Search results for , issue "Vol 8, No 4 (2024)" : 59 Documents clear
Knowledge-Based Intelligent System for Diagnosing Three-Wheeled Motorcycle Engine Faults Ary Setyadi, Heribertus; Supriyanta, Supriyanta; Nurohim, Galih Setiawan; Widodo, Pudji; Sutanto, Yusuf
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.2487

Abstract

Three-wheeled motor engine damage is one of the most serious problems with all motorcycles. When problems appear, it becomes difficult for users to repair and diagnose faults because knowledge about machine breakdown symptoms is minimal. Most motorcycle repair shops don’t have mechanics who understand tricycle motorbike engines, so they are less accurate in diagnosing damage symptoms, only based on estimates. Three-wheeled motorbikes have several differences in structure and spare parts compared to motorcycles because tricycle motorbikes have an axle like a car. For this problem, an information system is needed with a method that combines an expert's experience, expertise, and knowledge to develop expert system applications based on several cases that have been experienced and are known as case-based reasoning. This research aims to produce a web-based expert system to diagnose and solve tricycle motorbike engine damage problems. The case-based reasoning method with the K-Nearest Neighbor algorithm is used to assist in analyzing engine damage and give solutions to the issues in three-wheeled motorbike engines. Using two methods is appropriate because of the answers found and the similarities calculated by the cosine similarity method, which experts then review to get the proper solution. From testing using 20 samples of diagnostic data, an accuracy percentage of 85% was obtained. The calculation result for precision is 85%, and recall is 85%.
Harmonizing Emotion and Sound: A Novel Framework for Procedural Sound Generation Based on Emotional Dynamics Hariyady, Hariyady; Ag Ibrahim, Ag Asri; Teo, Jason; Md Ajis, Ahmad Fuzi; Ahmad, Azhana; Md Yassin, Fouziah; Salimun, Carolyn; Weng, Ng Giap
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3101

Abstract

The present work proposes a novel framework for emotion-driven procedural sound generation, termed SONEEG. The framework merges emotional recognition with dynamic sound synthesis to enhance user schooling in interactive digital environments. The framework uses physiological and emotional data to generate emotion-adaptive sound, leveraging datasets like DREAMER and EMOPIA. The primary innovation of this framework is the ability to capture emotions dynamically since we can map them onto a circumplex model of valence and arousal for precise classification. The framework adopts a Transformer-based architecture to synthesize associated sound sequences conditioned on the emotional information. In addition, the framework incorporates a procedural audio generation module employing machine learning approaches: granular and wavetable synthesis and physical modeling to generate adaptive and personalized soundscapes. A user study with 64 subjects evaluated the framework through subjective ratings of sound quality and emotional fidelity. Analysis revealed differences among samples in sound quality, with some samples getting consistently high scores and some getting mixed reviews. While the emotion recognition model reached 70.3% overall accuracy, it performed better at distinguishing between high-arousal emotions but struggled to distinguish between emotions of similar arousal. This framework can be utilized in different fields such as healthcare, education, entertainment, and marketing; real-time emotion recognition can be applied to deliver personalized adaptive experiences. This step includes acquiring multimodal emotion recognition in the future and utilizing physiological data to understand people's emotions better.
Grade Classification of Agarwood Sapwood Using Deep Learning Hatta, Heliza Rahmania; Nurdiati, Sri; Hermadi, Irman; Turjaman, Maman
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.2257

Abstract

The agarwood tree (Aquilaria sp.) is a tree that produces agarwood, which is a black resin that has a distinctive fragrant smell. In Indonesia, one that is commonly traded is sapwood agarwood. Agarwood sapwood is black or brownish-black wood obtained from the parts of the agarwood-producing tree containing a strong aromatic mastic. Based on the Indonesian National Standard (SNI) 7631:2018, agarwood sapwood has three classes: Super Double, Super A, and Super B. However, many agarwood farmers need to learn to differentiate and classify the agarwood sapwood classes, and traders exploit this to buy cheap. So, deep learning can be used to classify the agarwood sapwood class. One of the uses of deep learning is in image processing. Image processing is used to help humans recognize or classify objects quickly and precisely and can process many data simultaneously. One of the deep learning algorithms used in image processing is the Convolutional Neural Network (CNN). In this study, it is proposed that the deep learning model used is CNN with batch normalization. The dataset used is 72 agarwood sapwood images with a white background, each consisting of 24 Super A, 24 Super B data, and 24 Super Double data. The dataset is divided into 80% training and 20% testing data. The evaluation results of the proposed method at 100 epochs show an accuracy of 87.5%. The research implications will help agarwood tree farmers differentiate and classify agarwood sapwood so that farmers get the right price from buyers.
Validating a Quality Model through Expert Review for Green Information Systems Muhammad, Shireen; Jusoh, Yusmadi Yah; Haizan Nor, Rozi Nor; Jussupbekova, Gulzat Tyrysbekovna; Baidibekova, Aidin Orisbayevna
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3648

Abstract

Software developers use a quality model as a guide to help them determine the quality factors of a software product they are designing. This study aims to validate a quality model for green information systems, or green IS, towards achieving eco-sustainability. Thus, this study aims to identify quality factors for green IS that will contribute to eco-sustainability. This study's methodology included two rounds of expert evaluation with four experts. Two strategies were deployed in each round to discover the quality factors. In the first round, the strategy was to take existing software quality factors and interpret them in the context of eco-sustainability. In the second round, existing eco-sustainability goals were adopted and clustered into categories; in this study’s context, quality factors were aligned with the eco-sustainability goals. An initial model consisting of 35 quality factors was synthesized from a green IS design framework, sustainable software, and social media literature. The experts presented and assessed the model in the first round. Thus, 18 quality factors have been selected for the next second-round review. Five quality factors— accuracy, completeness, accessibility, customization, and collaboration emerged from the second-round review. Each quality factor was aligned to the eco-sustainability sub-goals of eco-efficiency, eco-equity, and eco-effectiveness, which resulted in the development of a proposed model. The experts concluded that the revised model could be employed in a data collection survey since it closely resembles the green IS quality model for eco-sustainability.
Named Entity Recognition in Medical Domain: A systematic Literature Review Kusuma, Selvia Ferdiana; Wibowo, Prasetyo; Abdillah, Abid Famasya; Basuki, Setio
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3111

Abstract

Biomedical Named Entity Recognition (BioNER) is essential to bioinformatics because it identifies and classifies biological entities in biomedical texts. With the increasing number of biomedical literature and the rapid progress of the BioNER approach, it is essential to conduct a systematic literature review (SLR) on BioNER. This SLR consolidates existing information and provides directions for future studies in the BioNER field. This review systematically explores scientific journals and conferences published from 2019 to 2024. This research uses PubMed and Scholar as reference search databases because of their affiliation with other well-known publishers such as IEEE, Elsevier, and Springer. The results show a transition from conventional machine learning to deep learning. Neural networks and transformers show better performance in deep learning methods. The datasets often used in BioNER development are BC2GM, BC5CDR, and NCBI-Disease. Precision, Recall, and F1-Score are used in most papers to evaluate model performance. The performance of these models mostly depends on the availability of big annotated datasets and significant computational tools. Therefore, it is vital for future research to address the issues of annotated data and resource availability to build accurate models. Researchers should investigate the creation of ideal designs that lower computing complexity without compromising performance. Overall, this SLR offers a thorough overview of the latest research on BioNER. It provides significant insights for academics and practitioners in bioinformatics and medical research, helping them understand the innovative aspects of BioNER research.
The Use of Hyperparameter Tuning in Model Classification: A Scientific Work Area Identification Rahmi, Nadya Alinda; Defit, Sarjon; Okfalisa, -
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3092

Abstract

This research aims to investigate the effectiveness of hyperparameter tuning, particularly using Optuna, in enhancing the classification performance of machine learning models on scientific work reviews. The study focuses on automating the classification of academic papers into eight distinct fields: decision support systems, information technology, data science, technology education, artificial intelligence, expert systems, image processing, and information systems. The research dataset comprises reviews of scientific papers ranging from 150 to 500 words, collected from the repository of Universitas Putra Indonesia YPTK Padang. The classification process involved the application of the TF-IDF method for feature extraction, followed using various machine learning algorithms including SVM, MNB, KNN, and RF, with and without the integration of SMOTE for data balancing and Optuna for hyperparameter optimization. The results show that combining SMOTE with Optuna significantly improves the accuracy, precision, recall, and F1-score of the models, with the SVM algorithm achieving the highest accuracy at 90%. Additionally, the research explored the effectiveness of ensemble methods, revealing that hard voting combined with SMOTE and Optuna provided substantial improvements in classification performance. These findings underscore the importance of hyperparameter tuning and data balancing in optimizing machine learning models for text classification tasks. The implications of this research are broad, suggesting that the methodologies developed can be applied to various text classification tasks in different domains. Future research should consider exploring other hyperparameter tuning techniques and ensemble methods to further enhance model performance across diverse datasets.
A Theoretical Framework of Knowledge Management Systems on Quality Management Systems Nizam Mohammad, Mohammad Fakhrul; Abdullah, Rusli; Ab. Jabar, Marzanah; Haizan Nor, Rozi Nor; Mohd Nur, Nurhayati
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3633

Abstract

Developing knowledge management systems (KMS) significantly supports, manages, or enhances the organization's knowledge management (KM) processes and activities. However, studies have shown that very few discussions focus on formulating the theoretical framework to support the development of KMS. Therefore, this paper aims to fill the void and gap in developing a more effective and efficient KMS. This study proposes a theoretical framework for KMS in the context of quality management systems (QMS), formulated based on three domain areas: established theories, knowledge management (KM) framework or model, and past KMS. This research output derived seven components of KMS (strategy, actors, KM process, source of knowledge, information management, continuous improvement, and infrastructure). This study has also contributed to the body of knowledge in KM by enriching the formulation of a theoretical framework for KMS. Although this study is conceptual and has yet to include the framework's validity and reliability testing, it has addressed a gap that can be potentially fulfilled and refined with more intense discussion and empirical studies.
A Systematic Literature Review on Characteristics Influencing Software Reliability Subramanium, Lehka; Hassan, Saadah; Osman, Mohd. Hafeez; Zulzalil, Hazura
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3665

Abstract

Reliability, as a non-functional requirement, is a crucial aspect that refers to the system's ability to perform its intended functions consistently and without failure over an extended period. It is essential in designing and implementing software systems, as it affects software quality. Maintaining software reliability is a significant challenge, as it is directly impacted by factors such as the complexity of the software design, the amount of code, and the measures taken to secure the system from unauthorized use. There are significant growing appeals for predicting reliability to account for risks. Research on reliability risk assessment has a long tradition; unfortunately, comprehensible reliability characteristics are still vague when determining potential risks. Clearly defining, prioritizing, and addressing reliability characteristics is essential for delivering reliable, high-quality software that meets user needs and business goals. The ignorance and lack of comprehensive reliability characteristics have evolved into inaccurate risk assessment, triggering malfunctions in the operational environment. Comprehensive characteristics are key elements to predict and estimate software reliability. The reliability characteristics could determine the precise objective of reliability efforts. This systematic literature review aims to identify the key characteristics influencing software reliability, the potential risks associated with these characteristics, and the metrics used to measure and assess them. Thirty-one research articles related to research questions have been reviewed. The findings indicate that comprehensive reliability characteristics could identify, classify, and prioritize potential risks, improving current metrics. It can be concluded that the accurate potential reliability risk can demonstrate the consequence of failure.
Metaheuristic Optimization in Dynamic Unit Commitment of Power Systems: Current Trends and Future Prospects Widayanti, Lilis; Afandi, Arif Nur; Herwanto, Heru Wahyu; Fitria, Vivi Aida
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.2423

Abstract

This paper discusses various optimization algorithms, a mathematics and computer science method essential to solving challenging real-world problems. The presented real-world scenario centers on a power system with dynamic unit commitment. Power systems involve many variables and constraints that can be changed. Metaheuristic optimization can be an effective method for finding an excellent solution to a problem. Dynamic unit commitment optimization is a critical aspect of power system operation. Dynamic unit commitment discusses determining the operating schedule of generating units and how much their production capacity is at each specific time interval to minimize production costs. This research aims to investigate the current trends and future challenges in applying metaheuristic optimization algorithms to power system problems, using the PRISMA approach to conduct a systematic literature review (SLR). This research starts by formulating research questions: what metaheuristic methods can be employed to tackle dynamic unit commitment challenges in power systems, and how effective are these methods in optimization? We established specific criteria for including and excluding studies, such as choosing articles published in English and concentrating on unit commitment in power systems. Out of the 487 papers discovered from the abstracts, only 14 were chosen for review after an extensive screening process based on complete studies that specifically addressed dynamic unit commitment. The conducted analysis provided insights into the accuracy and efficiency levels attained when using metaheuristic algorithms to solve the dynamic unit commitment problem. The research underscores the pivotal role of metaheuristic optimization in modern energy and power systems, highlighting its significance in tackling diverse challenges associated with enhancing the efficiency and effectiveness of power system utilization. Using metaheuristics in academic research has significantly improved scientific publications, resulting in an average annual increase of 43% in citations. This research's real contribution to the academic field is to provide an alternative reference for approximately 66 ASEAN universities with power system engineering majors. 
Predicting Different Classes of Alzheimer's Disease using Transfer Learning and Ensemble Classifier Tamim, Mubasshar-Ul-Ishraq; Malik, Sumaiya; Sneha, Soily Ghosh; Mahmud, S M Hasan; Goh, Kah Ong Michael; Nandi, Dip
JOIV : International Journal on Informatics Visualization Vol 8, No 4 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.4.3038

Abstract

Alzheimer's disease (AD), the most prevalent cause of dementia, affects over 55 million individuals globally. With aging populations, AD cases are expected to increase substantially, presenting a pressing public health challenge. Early diagnosis is crucial but remains challenging, particularly in the mild cognitive impairment stage before extensive neurodegeneration. Existing diagnostic methods often fall short due to the subtle nature of early AD symptoms, highlighting the need for more accurate and efficient approaches. In response to this challenge, we introduce a hybrid framework to enhance the diagnosis of Alzheimer's Disease (AD) across four classes by integrating various deep learning (DL) and machine learning (ML) techniques on an MRI image dataset. We applied multiple preprocessing techniques to the MRI images. Then, the methodology employs three pre-trained convolutional neural networks (CNNs): VGG-16, VGG-19, and MobileNet - each undergoing training under diverse parameter settings through transfer learning to facilitate the extraction of meaningful features from images, utilizing convolution and pooling layers. Subsequently, for feature selection, a decision tree-based RFE method was employed to iteratively select the most significant features and enable more accurate AD classification. Finally, an XGBoost classifier was used to classify the multiclass types of AD under 5-fold cross-validation to assess the performance of our proposed model. The proposed model achieved the highest accuracy of 93% for multiclass classification, indicating that our approach significantly outperforms state-of-the-art methods. This model could apply to clinical applications, marking a significant advancement in AD diagnostics.