cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
ELINVO (Electronics, Informatics, and Vocational Education)
Published by Universitas Negeri Yogyakarta
ISSN : 25806424     EISSN : 24772399     DOI : 10.21831
Core Subject : Science, Education, Engineering,
Computer Science & IT Education Electrical & Electronics Engineering
ELINVO (Electronics, Informatics and Vocational Education) is a peer-reviewed journal that publishes high-quality scientific articles in Indonesian language or English in the form of research results (the main priority) and or review studies in the field of electronics and informatics both in terms of their technological and educational development.
Arjuna Subject : Teknik (semua kategori) - Teknik Listrik dan Elektro
Articles 247 Documents
 21   22   23   24   25 
Optimizing YOLO Models for Enhanced Road Damage Detection: A Performance Comparison of YOLOv5 and YOLOv8 Indrihapsari, Yuniar; Wijaya, Danang; Ardy, Satya Adhiyaksa; Siswanto, Ikhwan Inzaghi; Ardiansyah, Dhista Dwi Nur; Ardianto, Widya
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.88919

Abstract

Accurate road damage detection is vital for ensuring road safety and infrastructure maintenance. This study evaluates and compares the performance of four YOLO models—YOLOv5-S, YOLOv5-M, YOLOv8-S, and YOLOv8-M—for detecting road damage types such as Alligator Cracks, Longitudinal Cracks, Transverse Cracks, Potholes, and Lateral Cracks. The models were trained on a combined dataset from GRDDC 2020 and the Ministry of Public Works and Housing (PUPR) Republic of Indonesia, addressing challenges like class imbalance and diverse road conditions. Results show that YOLOv8-M achieved the highest mAP@0.5 (0.412), excelling in precision and recall for prominent damage types, making it the most reliable for high-accuracy applications. YOLOv5-M balanced precision and recall, while YOLOv5-S prioritized recall, making it suitable for detecting widespread damage. However, all models struggled with less prominent types, such as Lateral Cracks, due to class imbalance. Misclassifications were common, with the "Background" class absorbing predictions from other categories. This study highlights the strengths and limitations of each model, offering insights into improving road damage detection through better feature extraction, expanded datasets, and optimized architectures. These findings provide a foundation for deploying automated deep learning-based road damage detection systems to enhance infrastructure management.
Integrating Psychological Stress Indicators with Academic Data for Student Dropout Prediction: A Decision Tree and Expert System Approach Gunawan, Indra; Widyassari, Adhika Pramita
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.89031

Abstract

Student attrition remains a major problem in higher education. Although academic variables are well-established moderators, psychological wellness, especially stress, is an important but often ignored moderator. The purpose of this study is to construct prediction models for students at risk of dropping out by combining academic and psychological information. One major challenge in this field is the class imbalance of student records, which results in a significant drop in the dropout rate compared to the general population. Therefore, in this study, we employ a Decision Tree algorithm and use a Forward Chaining inference engine along with the Synthetic Minority Over-sampling Technique (SMOTE) to solve it. We employed a data set of 122 students at one institution, with psychological stress scores generated from a standardised questionnaire according to well-known symptom domains. The accuracy for the model with only a Decision Tree was 95.83%. For the stress score, integration with the FC-based attribute increased performance to 96.67%; however, this model exhibited only marginal improvement over the final model due to its very low accuracy when compared to that of SMOTE. This ensemble model performed the best with an accuracy of 97.50% and an AUC of 96.35%. This progression demonstrates that even though the introduction of psychological information is beneficial, an approach to balance data and ensure a robust prediction system is required. This article is a proof-of-concept analysis which creates an opportunity for universities to establish proactive, early-warning-driven models; yet there is a requirement for future validation studies on larger and more diversified samples.
IoT-Based Predictive Maintenance for AC Motors in Water Treatment Plants Using Multi-Sensor Data and LSTM Networks with GAN Augmentation Frayudha, Angga Debby; Widikda, Aris Puja
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.89410

Abstract

AC motors are critical assets in water treatment plants because they operate continuously to drive key processes. Reactive or schedule-based maintenance can miss early degradation and increase the risk of unplanned downtime. This study presents a field implementation of an Internet of Things (IoT)-based predictive maintenance system in a WTP. The system integrates vibration, temperature, and rotational speed (RPM) sensors with a cloud-based IoT pipeline for real-time data acquisition. Operational data were collected for 30 days from a single motor unit and analyzed using Random Forest and Long Short-Term Memory models. To address limited abnormal-event data, Generative Adversarial Network (GAN)-based augmentation was applied during training. The results show that LSTM performed more consistently than Random Forest; after augmentation, the F1-score improved from 0.92 to 0.95. The monitoring data also captured warning-level changes during operation, including vibration up to 3.9 mm/s, temperature up to 95 °C, and rotational speed dropping to around 1420 RPM, which may indicate abnormal operating conditions requiring inspection. Given the single-unit scope and short duration, the findings are reported as an initial implementation case study. Nevertheless, the work demonstrates the feasibility of a low-cost IoT-based monitoring and prediction framework to support maintenance decisions in WTP operations.
Development of An IoT-Based Heart Rate Monitoring System Using Android Application Dimyati , Achmad; Inayah, Inayatul; Sa'odah , Lis; Yusuf , M.
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.89724

Abstract

Real-time heart rate monitoring plays an important role in early detection of cardiovascular anomalies. However, many existing IoT-based solutions still lack seamless integration of real-time sensing, cloud synchronization, and mobile visualization. This study develops and evaluates an IoT-based heart rate monitoring system using a pulse sensor, Arduino Uno, NodeMCU ESP8266, Firebase real-time database, and an Android application. Experimental testing involving six participants and 60 measurement samples demonstrates that the system achieves a high accuracy of 98.63% compared to a standard fingertip oximeter, with an average error rate of 1.37%, indicating reliable and stable performance. The system supports continuous data acquisition, real-time cloud storage, and mobile access, enabling users to view live and historical heart rate trends through the Android interface. The main contributions of this research include an end-to-end integrated IoT architecture for continuous monitoring, empirical validation of accuracy using a medical-grade comparator, and the provision of time-stamped cloud-based heart rate data for remote health monitoring. These findings confirm the feasibility and significance of IoT–mobile integration as an accessible solution for continuous cardiovascular monitoring.
A Text-Based Analysis of SDGs Goal 4 Representation in Informatics and Computer Science Syllabi Ilmiana, Indah Rahma; Biddinika, Muhammad Kunta; Herman
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.89955

Abstract

Higher education curricula play an important role in supporting the achievement of Sustainable Development Goals (SDGs), particularly SDGs Goal 4: Quality Education, through the development of relevant and sustainable learning. The purpose of this study is to look at the connections between the SDGs Goal 4 targets and the computer science and informatics curricula at universities on the island of Java. 552 course syllabi from current APTIKOM member universities are examined in this study using a text-based document analysis design. The analysis focuses on three frequently accessible syllabus components: course name, course description, and learning outcomes. The Term Frequency-Inverse Document Frequency (TF-IDF) approach was used to represent the textual data after it had been pre-processed and mapped using SDGs keywords to create initial labels. Support Vector Machine (SVM) was used as the comparison model and K-Nearest Neighbors (KNN) as the baseline model for the classification procedure. The results showed a strong relationship between most curricula and Target 4.4, which stresses the development of technical and digital skills. In terms of performance, the KNN model achieved an accuracy of 83%, while the SVM model showed a higher accuracy of 86% with more consistent performance on high-dimensional data and imbalanced class distributions. In conclusion, the syllabus analysis methodology based on keyword mapping and machine learning can be used as a systematic exploratory framework for identifying the relationship between higher education curriculum and SDGs.
A System Identification of Diabetes Based on Ensemble Method: Bagging, Random Forest, and Extreme Gradient Boosting de Deus Guterres, Jonas; Arifin, Fatchul
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.89649

Abstract

Diabetes is a prevalent chronic illness that is recognized worldwide, with an estimated prevalence in adults ranging from 42% to 170% globally. To reduce the likelihood of developing diabetes, it is vital for individuals at an increased risk to understand the importance of embracing healthy lifestyles and managing their consumption of foods that can potentially raise insulin levels in the body. Therefore, it is crucial to detect early pre-symptoms to minimize the incidence of individuals being afflicted by this condition without their awareness. Machine learning has emerged as a contemporary tool that aids in the prediction of various diseases, including diabetes, by analyzing patient data. Despite numerous research attempts using various machine learning techniques, achieving high accuracy in predicting diabetes has remained challenging. Therefore, this study implemented an ensemble approach that combined bagging, random forest, and Extreme Gradient Boost (XGBoost) algorithms to enhance the predictive performance for diabetes. This approach involved evaluating selected features based on their highest correlation and incorporating all available features in the analysis. Based on the results, the bagging technique demonstrated the highest accuracy of 0.83 in predicting model 6. Following closely behind was the random forest algorithm, which achieved an accuracy of 0.82, and XGBoost with an accuracy of 0.81.
Implementation of Vision Transformer (ViT) Method in Identifying Orchid Genus Based on Flower Images Vatresia, Arie; Cahyani, Seprina Dwi; Susanto, Agus; Romeida, Atra
Elinvo (Electronics, Informatics, and Vocational Education) Vol. 10 No. 2 (2025): November 2025 (In-Press)
Publisher : Department of Electronic and Informatic Engineering Education, Faculty of Engineering, UNY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21831/elinvo.v10i2.90056

Abstract

There are about 15,000 to 20,000 orchid species around the world, spread across more than 900 genera. They come in many different shapes, sizes, and colors. This wide range of species makes it hard to tell them apart, especially for people who aren't experts. Bengkulu is one of the provinces on the island of Sumatra. It is known for its historical and cultural heritage as well as its rich biodiversity, especially its native plants like orchids. However, it is still hard to tell what they are. The identification process can be made better by using the breakthrough in artificial intelligence of the transformer. The goal of this study is to create an Android app that can use the Vision Transformer (ViT) architecture to identify five types of orchids: Bulbophyllum, Cymbidium, Dendrobium, Phalaenopsis, and Vanda. We used open-source libraries to collect data, which included 1,500 images that went through preprocessing steps. The experimental results show that the ViT-Base16 model with 25 epochs did the best job, getting an accuracy of 0.98 on the test dataset. However, it was hard to classify the genus Dendrobium in all trials because it had a lot of different shapes. The application testing gave good results, with scores of 81.13 for ease of use, 82.5 for accuracy, and 83.06 for usefulness. These results indicate that the application successfully aids in the identification of orchid genera, serving as a useful resource for both educational and practical applications

Page 25 of 25 | Total Record : 247

 21   22   23   24   25 

Filter by Year

2015 2025


Reset
Filter By Issues
All Issue Vol. 10 No. 2 (2025): November 2025 (In-Press) Vol. 10 No. 1 (2025): May 2025 Vol. 9 No. 2 (2024): November 2024 Vol. 9 No. 1 (2024): Mei 2024 Vol. 8 No. 2 (2023): November 2023 Vol. 8 No. 1 (2023): Mei 2023 Vol 7, No 2 (2022): November 2022 Vol 7, No 1 (2022): Mei 2022 Vol. 7 No. 1 (2022): Mei 2022 Vol 6, No 2 (2021): November 2021 Vol. 6 No. 2 (2021): November 2021 Vol. 6 No. 1 (2021): Mei 2021 Vol 6, No 1 (2021): Mei 2021 Vol. 5 No. 2 (2020): November 2020 Vol. 5 No. 1 (2020): Mei 2020 Vol 4, No 2 (2019): November 2019 Vol. 4 No. 2 (2019): November 2019 Vol. 4 No. 1 (2019): May 2019 Vol 4, No 1 (2019): May 2019 Vol. 3 No. 2 (2018): November 2018 Vol 3, No 1 (2018): May 2018 Vol. 3 No. 1 (2018): May 2018 Vol 3, No 1 (2018): May 2018 Vol. 2 No. 2 (2017): November 2017 Vol. 2 No. 1 (2017): May 2017 Vol 2, No 1 (2017): May 2017 Vol 2, No 1 (2017): May 2017 Vol. 1 No. 3 (2016): November 2016 (Consist of 7 Articles) Vol 1, No 3 (2016): November 2016 (Consist of 7 Articles) Vol. 1 No. 2 (2016): May 2016 (Consist of 7 Articles) Vol 1, No 2 (2016): May 2016 (Consist of 7 Articles) Vol. 1 No. 1 (2015): November 2015 (Consist of 9 Articles) Vol 1, No 1 (2015): Oktober More Issue