cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Anis R. Amna
Contact Email
anis.r.amna@ub.ac.id
Phone
+62341577911
Journal Mail Official
jitecs@ub.ac.id
Editorial Address
Faculty of Computer Science, F Building - 8th Floor - Journal Publishing Unit (BPJ), Universitas Brawijaya Jl. Veteran, Ketawanggede, Lowokwaru, Kota Malang, East Java, Indonesia - 65145
Location
Kota malang,
Jawa timur
INDONESIA
Journal of Information Technology and Computer Science
Published by Universitas Brawijaya
ISSN : 25409433     EISSN : 25409824     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering
The Journal of Information Technology and Computer Science (JITeCS) is a peer-reviewed open access journal published by Faculty of Computer Science, Universitas Brawijaya (UB), Indonesia. The journal is an archival journal serving the scientist and engineer involved in all aspects of information technology, computer science, computer engineering, information systems, software engineering and education of information technology. JITeCS publishes original research findings and high quality scientific articles that present cutting-edge approaches including methods, techniques, tools, implementations and applications.
Arjuna Subject : -
Articles 284 Documents
 25   26   27   28   29 
Heart Disease Prediction System Employing Machine Learning Rian Nopiardi; Raka Dimas Saputra; Niken Fitria Apriani; Al Hafiz Akbar Maulana Siagian; Shidiq Al Hakim; Fatyanosa, Tirana Noor
Journal of Information Technology and Computer Science Vol. 10 No. 2: August 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025102926

Abstract

Heart disease places a significant strain on healthcare systems. Moreover, it kills millions of people each year, which is a leading cause of death worldwide. Hypertension, diabetes, unhealthy lifestyles, and genetic predispositions are all risk factors for heart disease. However, it is not easy to identify a heart disease. For this reason, helping in identifying the heart disease is important to prevent a death, e.g., caused by a heart attack. In this study, we aim to develop a heart disease prediction system. The system is developed according to the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework by employing machine learning algorithms. In this work, Logistic Regression (LR) and Random Forest (RF) are utilized as our machine learning algorithms for classifying heart disease using a heart disease dataset from Kaggle. Our results show LR has an AUC value of 0.921 and F1-Score 0.89 that outperforms RF with an AUC value of 0.920 and F1-Score 0.84 in this work. Then, we select LR to be applied to the developed heart disease prediction system.
Enhanced Hand Gesture Classification for a Myoelectric Prosthetic Hand Using Compact CNN with Wearable EMG Sensors Ristanti, Dini Eka; Widasari, Edita Rosana
Journal of Information Technology and Computer Science Vol. 10 No. 2: August 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025102927

Abstract

In Indonesia, many people experience upper-limb functional loss, which limits their ability to perform daily activities. Myoelectric prosthetic hands offer a promising solution for transradial amputees by using electromyography (EMG) signals to control hand movements. However, conventional wired systems may introduce noise that affects EMG signal quality and gesture recognition performance. Therefore, this study proposes an enhanced hand gesture classification approach for myoelectric prosthetic hands using wearable EMG sensors, Savitzky-Golay (SG) filtering, and a compact convolutional neural network (CNN). The dataset consists of EMG signals acquired from eight subjects using an eight-channel wearable EMG sensor, covering four hand gestures: rock, paper, scissors, and OK. The SG filter is applied to smooth the EMG signals and reduce noise while preserving important signal characteristics. Since filtering alone is insufficient to distinguish all gesture types, a compact CNN model is employed for classification. The proposed model achieved an accuracy of 95.15%, precision of 95.16%, recall of 95.15%, and F1-score of 95.15%, demonstrating its effectiveness for EMG-based hand gesture classification in myoelectric prosthetic hand applications.
Leveraging Stacked Vessel Segment and Channels of Fundus Image for Eye Disease Detection using Hybrid U-Net-Residual Convolutional Candra Dewi; Novanto Yudistira; Daffa Izzuddin; Nazura Wirayuda Tama; Fatyanosa, Tirana Noor
Journal of Information Technology and Computer Science Vol. 10 No. 2: August 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025102928

Abstract

Fundus images can be used to identify symptoms of various eye diseases. However, a limitation of using fundus images for classification is the generalization of information from the entire image, which can reduce recognition accuracy. To address this, this study proposes a combination of RGB channels from fundus images and segmented images for the identification process. Segmentation is performed using U-Net, which produces a segmentation of the blood vessels from the retinal image. The combined image is then used as input for the identification process with different ResNet models, including ResNet18, ResNet34, ResNet50, ResNet101, and ResNet152. Three model tuning scenarios are explored to obtain an optimal hybrid segmentation and classification model: learning using ResNet without U-Net (nounet), learning using a ResNet model with a frozen U-Net model (frozenunet), and learning using both the U-Net and ResNet models (hotunet). Testing is carried out to recognize normal, cataract, and glaucoma classes. The results show that the highest accuracy of 0.82 is achieved with the hybrid U-Net and ResNet152 model using frozenunet learning. This indicates that the addition of segmented images can improve identification results, with the best performance for glaucoma having a precision of 0.90, recall of 0.86, and F1-score of 0.88.
Predicting Heart Disease with Enhanced Genetic Algorithms: The Role of Latin Hypercube Sampling and Hamming Distance-Based Diversity Sifaunnufus Ms, Fi Imanur; Amila Fadhila Rahmaniati; Maulida Khairunisa Argaputri; Yonathan Fanuel Mulyadi; Lailil Muflikhah
Journal of Information Technology and Computer Science Vol. 10 No. 2: August 2025
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2025102946

Abstract

Heart disease remains a predominant cause of mortality globally and in Indonesia, impacting both older and younger demographics due to pervasive unhealthy lifestyles, heredity, and lack of awareness of heart disease. This study addresses the critical problem of necessitating early detection methods to mitigate severe complications and fatalities associated with heart disease. With that, it is crucial to develop a robust and highly accurate prediction model for heart disease by integrating Artificial Neural networks (ANN) with Genetic Algorithms (GA). The model starts by constructing an ANN model utilizing the Keras Framework for streamlined training, followed by hyperparameter optimization through GA. As a result, this research found that the integrated ANN and GA model attains superior predictive accuracy, with the optimal configuration achieving an accuracy of 85.33%, precision of 92.55%,  recall of 81.32%, and f1-score of 86.57% via Latin Hypercube Sampling (LHS). These show that the combination of ANN and GA can significantly increase prediction accuracy and model efficiency, as a solution for more effective heart disease identification at an early stage.
Implementation of YOLOv8 Instance Segmentation for Automatic Counting and Identification of Multispecies Bacterial Colony Al Riza, Dimas Firmanda
Journal of Information Technology and Computer Science Vol. 11 No. 2: August 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2026112666

Abstract

This study introduces the implementation of YOLOv8 instance segmentation model, for automating the quantification and identification of multispecies bacterial colonies. In microbiological research, accurate counting and rapid identification of various species within colonies are essential. YOLOv8's real-time capabilities and high accuracy make it particularly well-suited for this task. We demonstrate its efficacy in accurately detecting and segmenting individual bacterial colonies, even when they comprise multispecies like Bacillus subtilis, Escherichia coli, Pseudomonas aeruginosa, and Staphylococcus aureus. This innovation streamlines the labor-intensive processes of colony counting and species identification. To improve precision, we incorporate post-processing techniques to handle overlapping colonies, significantly enhancing accuracy compared to manual counting methods. Our proposed method exhibits superior performance and provides a valuable tool for microbiologists and researchers, expediting bacterial colony analysis. In this study, we fine-tuned hyperparameters to achieve the best mean average precision (mAP) for masks and bounding boxes. We used a primary and a secondary dataset for training. The hyperparameter modifications, including using an Adam optimizer with a learning rate of 0.01 and an epoch value of 50, resulted in mAP values of 90%. These findings underscore the importance of optimizing the optimizer type, learning rate, and the number of epochs, revealing their impact on the model's performance in automating bacterial colony quantification and identification.
Comparative Analysis of Random Forest, Support Vector Machine, and K-Nearest Neighbor with Image Feature Extraction for Rice Leaf Disease Detection Nadia Nafista; Wawu Tri Ambodo; Analicia; Ulfa Siti Nuraini
Journal of Information Technology and Computer Science Vol. 11 No. 2: August 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2026112856

Abstract

Plant diseases and pest infestations have caused a decline in global food production of up to 40%, including in Indonesia, making an efficient and accurate disease detection system essential to support food security. This study proposes a supervised learning approach to detect rice leaf diseases based on image processing. Leaf images are processed through the stages of image segmentation, normalization, Gaussian blur, Canny edge detection, visualization of diseased areas, and hybrid feature extraction. Supervised learning algorithms such as Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) were trained and compared. Test results show that Random Forest delivers the best performance with an accuracy of 97%, outperforming SVM and KNN. These findings indicate that the proposed approach can serve as an effective and reliable solution for the automatic detection of rice leaf diseases.
Predicting On-Time Graduation Using the C 4.5 Algorithm with Forward Selection Optimization (Case Study: Computer Engineering Study Program, Faculty of Computer Science, Brawijaya University) Bangse, Ni Nyoman Dinda Permata Putri; Wijoyo, Satrio Hadi; Bachtiar, Fitra Abdurrachman
Journal of Information Technology and Computer Science Vol. 11 No. 2: August 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2026112871

Abstract

On-time student graduation is a key indicator of academic effectiveness and higher education quality. Timely graduation reflects efficient academic management, while delays may negatively impact institutional performance and accreditation. Graduation delays are influenced by various academic and non-academic factors, making early prediction essential. This study aims to develop an on-time graduation prediction model using the C4.5 algorithm optimized with the forward selection method. The research was conducted in the Computer Engineering Study Program, Faculty of Computer Science, Universitas Brawijaya, using student data from the 2018–2021 cohorts. The dataset includes both academic and nonacademic attributes. The modeling process followed the CRISP-DM framework, and model performance was evaluated using a confusion matrix. The results show that the C4.5 model without feature selection achieved an accuracy of 63%, while the application of forward selection significantly improved accuracy to 83%. These findings indicate that feature selection plays a crucial role in enhancing prediction performance. The proposed model can support academic stakeholders in data driven decision making and in designing strategies to improve on-time graduation rates.  
Detection of God Class Smells in PHP Systems Using Object-Oriented Metrics Toofani, Naveed; Priyambadha, Bayu; Arwan, Achmad
Journal of Information Technology and Computer Science Vol. 11 No. 2: August 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2026112892

Abstract

Software maintainability becomes difficult when object-oriented systems contain God Class code smells, where a single class handles excessive responsibilities and controls large portions of system behavior. Most existing God Class detection approaches use metric thresholds developed for statically typed languages such as Java, which may not accurately represent the architectural characteristics of dynamically typed PHP systems. This problem can reduce software maintainability, increase system complexity, and complicate future development and testing activities. This study applies a quantitative empirical research approach to evaluate metric-based God Class detection in PHP systems. Twelve open-source PHP projects containing 7,866 classes were collected from GitHub and analyzed using the PDepend static analysis tool. The extracted object-oriented metrics included Weighted Methods per Class (WMC), Number of Public Methods (NPM), Depth of Inheritance Tree (DIT), and Lines of Code (LOC). A class was classified as a God Class when at least three out of four threshold values were exceeded. The detection results were validated using statistical analysis, K-Means clustering, machine learning consistency validation, PHPMD comparison, and expert manual validation. The results identified 421 God Classes and showed that WMC, NPM, and LOC are strong indicators of God Class behavior in PHP systems, while DIT has lower influence due to framework-based inheritance structures. The study demonstrates that metric-based detection can effectively identify maintainability problems in PHP applications and provides a foundation for future PHP-specific threshold development.
Deep Learning-Based Edge Proctor System: A Resource-Efficient Multi-Modal Exam Monitoring Solution for Indonesian Schools Junaidi, Vicent Imanuel; Braniva, Petra Kanisia; Widjanarko, Alexander; Purnawirawan, Okta
Journal of Information Technology and Computer Science Vol. 11 No. 2: August 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2026112898

Abstract

Academic dishonesty in computer-based exams reaches 67.5% in Indonesia, threatening educational evaluation validity and undermining academic certificate credibility. This research develops the Edge Proctor System, a deep learning-based digital proctoring system integrating three detection modalities: object detection for identifying prohibited items, one-shot learning for identity verification, and audio recognition for detecting suspicious whispering. The research methodology employs systematic literature review and benchmark testing to compare YOLOv8n and COCO SSD performance. Data collection was conducted through interviews with the Head of Computer and Network Engineering Department and field testing with the Principal of SMK Kristen Petra Surabaya. Performance analysis utilizes inference time, FPS, and CPU usage metrics on edge computing architecture. Results demonstrate that COCO SSD achieves 79.05 ms inference time (10.9× faster than YOLOv8n), 9.09 FPS, and 78.43% CPU usage, 37-48% more efficient than previous studies. Stakeholder testing shows the system effectively enhances exam integrity with intuitive monitoring and resource-efficiency, suitable for massive implementation in Indonesian schools with limited technological infrastructure.
Development of the "Pulih" User Interface: A Smartwatch-Integrated Digital Counseling Application for Survivors of Post-Traumatic Stress Disorder due to Violence and Sexual Abuse Nur, Ahmad Zulfi’Azwan; Purnama, Primada; Widjanarko, Alexander; Iskandar, Firza Aurellia; Purnawirawan, Okta
Journal of Information Technology and Computer Science Vol. 11 No. 2: August 2026
Publisher : Faculty of Computer Science (FILKOM) Brawijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jitecs.2026112899

Abstract

The high prevalence of mental health disorders resulting from trauma caused by violence and sexual abuse has not been matched by adequate access to recovery services due to psychological barriers in the form of social stigma. This situation motivated the design of the “Pulih” interface, a smartwatch-based mental health support application developed using Research and Development (R&D) methods with a Design Thinking approach. This application integrates a Bidirectional Long Short-Term Memory (Bi-LSTM) deep learning architecture to analyze users’ Heart Rate Variability (HRV) and Resting Heart Rate (RHR) biometric data in real-time. AI testing results on the WESAD physiological dataset showed stable learning curve convergence without overfitting, achieving a training accuracy of 92.0%, validation accuracy of 90.5%, precision of 90.0%, recall of 91.0%, and an F1-Score of 90.5%. Meanwhile, an evaluation of the interface’s usability via the System Usability Scale (SUS) test with 27 respondents yielded an average score of 86.79 (falling into the ‘Excellent’ and ‘Acceptable’ categories with an A+ grade). The encrypted anonymous community feature further strengthens privacy aspects. In conclusion, Pulih has proven to possess trauma-sensitive technical reliability as well as high usability as an inclusive digital solution for the mental recovery of PTSD survivors.

Page 28 of 29 | Total Record : 284

 25   26   27   28   29 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 2: August 2026 Vol. 11 No. 1: April 2026 Vol. 10 No. 3: Desember 2025 Vol. 10 No. 2: August 2025 Vol. 10 No. 1: April 2025 Vol. 9 No. 3: December 2024 Vol. 9 No. 2: August 2024 Vol. 9 No. 1: April 2024 Vol. 8 No. 3: December 2023 Vol. 8 No. 2: August 2023 Vol. 8 No. 1: April 2023 Vol. 7 No. 3: December 2022 Vol. 7 No. 2: August 2022 Vol. 7 No. 1: April 2022 Vol. 6 No. 3: December 2021 Vol. 6 No. 2: August 2021 Vol. 6 No. 1: April 2021 Vol. 5 No. 3: Desember 2020 Vol. 5 No. 2: August 2020 Vol. 5 No. 1: April 2020 Vol. 4 No. 3: Desember 2019 Vol. 4 No. 2: September 2019 Vol. 4 No. 1: June 2019 Vol. 3 No. 2: November 2018 Vol. 3 No. 1: June 2018 Vol. 2 No. 2: November 2017 Vol. 2 No. 1: June 2017 Vol. 1 No. 2: November 2016 Vol. 1 No. 1: June 2016 More Issue