Eko Prasetyo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Eko Prasetyo has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Chien-Erh Weng
Department of Computer and Communication Engineering, National Kaohsiung University of Science and Technology, Yanchao, Kaohsiung, Taiwan
2 shared publications - Hsing-Chung Chen
Asia University
2 shared publications - Karisma Trinanda Putra
Universitas Muhammadiyah Yogyakarta
2 shared publications - Prayitno
Politeknik Negeri Semarang
2 shared publications - Shian-Shyong Tseng
Asia University
2 shared publications Sri Suning Kusumawardani
Universitas Gadjah Mada Department of Electrical and Information Engineering
2 shared publications
Latest Publications
- 9 July 2026
- Published by Emerald Publishing in Journal of Applied Research in Higher Education
- p. 1-12
Zoom fatigue and social anxiety disorder among university students: the mediating role of emotion regulation in East Kalimantan, Indonesia
Purpose: Intensive online learning during the pandemic has increased the use of video conferencing platforms such as Zoom. Excessive use of these platforms can lead to burnout that negatively impacts the psychological well-being of students. This study examines the effect of Zoom fatigue on emotion regulation and social anxiety disorder in students in East Kalimantan. Design/methodology/approach: This study used a quantitative approach with a survey method involving 720 students from various universities in East Kalimantan. The data were collected through validated questionnaires, which measured levels of Zoom fatigue, emotion regulation, and social anxiety. The data were analyzed using partial least squares structural equation modeling (PLS-SEM) with SmartPLS software to examine the relationships between variables and the mediating role of emotion regulation. Findings: The results showed that Zoom fatigue significantly affected emotion regulation, which subsequently had an impact on increased in social anxiety. However, Zoom fatigue had both direct and indirect effects on social anxiety disorder, although the direct effect was stronger than the indirect effect through emotion regulation. This suggests that emotion regulation plays a key mediator in the relationship between Zoom fatigue and social anxiety disorder. Research limitations/implications: The implications of this study highlight the need for educational institutions to develop online learning policies that explicitly integrate student psychological well-being, including the balanced use of digital technologies and evidence-based emotion-regulation strategies to mitigate the impact of Zoom fatigue. However, several limitations must be acknowledged, particularly the constraints of the survey design, which restrict the depth of psychological insight that can be captured. Future research should incorporate additional variables such as social support, coping mechanisms, and individual digital engagement experiences to provide a more comprehensive understanding of the mechanisms underlying the observed relationships. Originality/value: This study makes a new contribution to the academic literature by exploring the relationship between Zoom-induced fatigue, emotion regulation, and social anxiety disorder in the cultural context and educational environment in East Kalimantan. Furthermore, this study highlights the challenges of online learning for students in regions that have been under-discussed in previous studies.
- 9 July 2026
- Published by Emerald Publishing in Journal of Applied Research in Higher Education
- p. 1-12
Zoom fatigue and social anxiety disorder among university students: the mediating role of emotion regulation in East Kalimantan, Indonesia
Purpose: Intensive online learning during the pandemic has increased the use of video conferencing platforms such as Zoom. Excessive use of these platforms can lead to burnout that negatively impacts the psychological well-being of students. This study examines the effect of Zoom fatigue on emotion regulation and social anxiety disorder in students in East Kalimantan. Design/methodology/approach: This study used a quantitative approach with a survey method involving 720 students from various universities in East Kalimantan. The data were collected through validated questionnaires, which measured levels of Zoom fatigue, emotion regulation, and social anxiety. The data were analyzed using partial least squares structural equation modeling (PLS-SEM) with SmartPLS software to examine the relationships between variables and the mediating role of emotion regulation. Findings: The results showed that Zoom fatigue significantly affected emotion regulation, which subsequently had an impact on increased in social anxiety. However, Zoom fatigue had both direct and indirect effects on social anxiety disorder, although the direct effect was stronger than the indirect effect through emotion regulation. This suggests that emotion regulation plays a key mediator in the relationship between Zoom fatigue and social anxiety disorder. Research limitations/implications: The implications of this study highlight the need for educational institutions to develop online learning policies that explicitly integrate student psychological well-being, including the balanced use of digital technologies and evidence-based emotion-regulation strategies to mitigate the impact of Zoom fatigue. However, several limitations must be acknowledged, particularly the constraints of the survey design, which restrict the depth of psychological insight that can be captured. Future research should incorporate additional variables such as social support, coping mechanisms, and individual digital engagement experiences to provide a more comprehensive understanding of the mechanisms underlying the observed relationships. Originality/value: This study makes a new contribution to the academic literature by exploring the relationship between Zoom-induced fatigue, emotion regulation, and social anxiety disorder in the cultural context and educational environment in East Kalimantan. Furthermore, this study highlights the challenges of online learning for students in regions that have been under-discussed in previous studies.
- Open Access
- 12 September 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 107 (1) , 86
N-Gram and Full-Text Search Algorithm Testing for Pattern Recognition in a Chatbot Engine
The development of chatbots to access database services and information systems has triggered a lot of research on frameworks for service development, including the development of ISONER (Information System On Internet Messenger). This framework consists of multiple phases including pattern recognition, query processing, and response generation. In its implementation, the framework develops pattern recognition services that are currently based on Natural Language Processing (NLP). Improved pattern recognition algorithms enhance the system’s ability to accurately interpret user intent. The pattern recognition used in this research utilizes built-in plugins from MySQL, namely N-gram and Full-Text Search, which can be run directly on the MySQL engine to reduce latency and do not require another programming language. The FTS and fourgram algorithms gave the best results when applied on 100 test data points, with a threshold of 0.91, accuracy of 91%, precision of 99%, and recall of 92%; the average computation time was 19 s for 100 test data points and 2 min 49 s for 1000 data points tested simultaneously.
- 12 September 2025
- Published by MDPI AG in Engineering Proceedings
- Vol. 107 (1) , 86
Open AccessN-Gram and Full-Text Search Algorithm Testing for Pattern Recognition in a Chatbot Engine
The development of chatbots to access database services and information systems has triggered a lot of research on frameworks for service development, including the development of ISONER (Information System On Internet Messenger). This framework consists of multiple phases including pattern recognition, query processing, and response generation. In its implementation, the framework develops pattern recognition services that are currently based on Natural Language Processing (NLP). Improved pattern recognition algorithms enhance the system’s ability to accurately interpret user intent. The pattern recognition used in this research utilizes built-in plugins from MySQL, namely N-gram and Full-Text Search, which can be run directly on the MySQL engine to reduce latency and do not require another programming language. The FTS and fourgram algorithms gave the best results when applied on 100 test data points, with a threshold of 0.91, accuracy of 91%, precision of 99%, and recall of 92%; the average computation time was 19 s for 100 test data points and 2 min 49 s for 1000 data points tested simultaneously.
- Open Access
- 22 May 2024
- Published by Universitas Muhammadiyah Yogyakarta in Emerging Information Science and Technology
- Vol. 5 (1)
Bandwidth Management using Per Connection Queue and Queue Tree: A Case Study on a High School Network
This research aims to enhance the efficiency of bandwidth utilization at MTs Muhammadiyah Tawangsari using the PCQ and Queue Tree bandwidth management methods on a MikroTik router. Through this approach, an analysis of bandwidth requirements, network topology design, and implementation were conducted. Post-implementation measurement results show a remarkable improvement in average user download speeds: 17.3 Mbps in administration rooms, 10 Mbps in classrooms, and 18.8 Mbps in faculty rooms. These results indicate a significant improvement in tailored bandwidth distribution that meets the specific needs of each network area and ensures that all users receive equal bandwidth usage. This leads to more evenly distributed and efficient network performance.
- 22 May 2024
- Published by Universitas Muhammadiyah Yogyakarta in Emerging Information Science and Technology
- Vol. 5 (1)
Open AccessBandwidth Management using Per Connection Queue and Queue Tree: A Case Study on a High School Network
This research aims to enhance the efficiency of bandwidth utilization at MTs Muhammadiyah Tawangsari using the PCQ and Queue Tree bandwidth management methods on a MikroTik router. Through this approach, an analysis of bandwidth requirements, network topology design, and implementation were conducted. Post-implementation measurement results show a remarkable improvement in average user download speeds: 17.3 Mbps in administration rooms, 10 Mbps in classrooms, and 18.8 Mbps in faculty rooms. These results indicate a significant improvement in tailored bandwidth distribution that meets the specific needs of each network area and ensures that all users receive equal bandwidth usage. This leads to more evenly distributed and efficient network performance.
- Open Access
- 15 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 20839-20851
Generating Multi-Issued Session Key by Using Semi Quantum Key Distribution With Time-Constraint
Information security refers to protect the information from unauthorized access or modification. Quantum Key Distribution (QKD) is a way to generate a key preventing those malicious activities. One of QKD protocol, namely Semi-quantum key distribution (SQKD) protocol, is designed to allow two users to establish a secure secret key when either of them is limited to performing certain “classical” operations. It is proven to be secure from any type of attack. However, it will be a problem in the multi-session communication since the SQKD activities follow the number of the session. In this paper, we propose two modified SQKDs with time-constraint approach. Time-constraint is beneficial in QKD activity since it could generate session key between two parties within a certain time-constraint. By setting the number of session key and its time-constraint before QKD activities, many scheduled communications would be prepared well. Furthermore, BAN Logic analysis is applied to analyze the goal of the protocol, the considered assumptions, wasted phase, and the demand for data encryption. Finally, the performance analysis of the protocols is presented, and it shows a better performance compared with other certain QKDs.
- 15 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 20839-20851
Open AccessGenerating Multi-Issued Session Key by Using Semi Quantum Key Distribution With Time-Constraint
Information security refers to protect the information from unauthorized access or modification. Quantum Key Distribution (QKD) is a way to generate a key preventing those malicious activities. One of QKD protocol, namely Semi-quantum key distribution (SQKD) protocol, is designed to allow two users to establish a secure secret key when either of them is limited to performing certain “classical” operations. It is proven to be secure from any type of attack. However, it will be a problem in the multi-session communication since the SQKD activities follow the number of the session. In this paper, we propose two modified SQKDs with time-constraint approach. Time-constraint is beneficial in QKD activity since it could generate session key between two parties within a certain time-constraint. By setting the number of session key and its time-constraint before QKD activities, many scheduled communications would be prepared well. Furthermore, BAN Logic analysis is applied to analyze the goal of the protocol, the considered assumptions, wasted phase, and the demand for data encryption. Finally, the performance analysis of the protocols is presented, and it shows a better performance compared with other certain QKDs.
- Open Access
- 11 February 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (4) , 1885
Week-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence
Early prediction of students’ learning performance and analysis of student behavior in a virtual learning environment (VLE) are crucial to minimize the high failure rate in online courses during the COVID-19 pandemic. Nevertheless, traditional machine learning models fail to predict student performance in the early weeks due to the lack of students’ activities’ data in a week-wise timely manner (i.e., spatiotemporal feature issues). Furthermore, the imbalanced data distribution in the VLE impacts the prediction model performance. Thus, there are severe challenges in handling spatiotemporal features, imbalanced data sets, and a lack of explainability for enhancing the confidence of the prediction system. Therefore, an intelligent framework for explainable student performance prediction (ESPP) is proposed in this study in order to provide the interpretability of the prediction results. First, this framework utilized a time-series weekly student activity data set and dealt with the VLE imbalanced data distribution using a hybrid data sampling method. Then, a combination of convolutional neural network (CNN) and long short-term memory (LSTM) was employed to extract the spatiotemporal features and develop the early prediction deep learning (DL) model. Finally, the DL model was explained by visualizing and analyzing typical predictions, students’ activities’ maps, and feature importance. The numerical results of cross-validation showed that the proposed new DL model (i.e., the combined CNN-LSTM and ConvLSTM), in the early prediction cases, performed better than the baseline models of LSTM, support vector machine (SVM), and logistic regression (LR) models.
- 11 February 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (4) , 1885
Open AccessWeek-Wise Student Performance Early Prediction in Virtual Learning Environment Using a Deep Explainable Artificial Intelligence
Early prediction of students’ learning performance and analysis of student behavior in a virtual learning environment (VLE) are crucial to minimize the high failure rate in online courses during the COVID-19 pandemic. Nevertheless, traditional machine learning models fail to predict student performance in the early weeks due to the lack of students’ activities’ data in a week-wise timely manner (i.e., spatiotemporal feature issues). Furthermore, the imbalanced data distribution in the VLE impacts the prediction model performance. Thus, there are severe challenges in handling spatiotemporal features, imbalanced data sets, and a lack of explainability for enhancing the confidence of the prediction system. Therefore, an intelligent framework for explainable student performance prediction (ESPP) is proposed in this study in order to provide the interpretability of the prediction results. First, this framework utilized a time-series weekly student activity data set and dealt with the VLE imbalanced data distribution using a hybrid data sampling method. Then, a combination of convolutional neural network (CNN) and long short-term memory (LSTM) was employed to extract the spatiotemporal features and develop the early prediction deep learning (DL) model. Finally, the DL model was explained by visualizing and analyzing typical predictions, students’ activities’ maps, and feature importance. The numerical results of cross-validation showed that the proposed new DL model (i.e., the combined CNN-LSTM and ConvLSTM), in the early prediction cases, performed better than the baseline models of LSTM, support vector machine (SVM), and logistic regression (LR) models.
- 24 June 2021
- Published by Springer Nature
- p. 330-340
Learning Performance Prediction with Imbalanced Virtual Learning Environment Students’ Interactions Data
- 24 June 2021
- Published by Springer Nature
- p. 330-340
Learning Performance Prediction with Imbalanced Virtual Learning Environment Students’ Interactions Data
- Open Access
Visualization and Travel Time Extraction System for the Statistics of TDCS Travel using MapReduce Framework
Recently, extracting some information as a knowledge from big data is very challenging activity. The size of data is very huge and it requires some special techniques and adequate processing hardware. It is also applied in vehicles transportation data at Taiwan National Freeway from the Traffic Data Collection System (TDCS). The results of this extraction will be very useful if it can be used by the community. So that the delivery of information extracted from large data that is easily understood becomes a necessary thing. Presentation of results using images / visuals will make it easier for people to interpret the information provided. In this project, an interactive visualization of the results of extracting statistical information is attempted to be provided. The results can be used by users to support the decision making of road users in determining the appropriate time when going through the road pieces around the Taichung City. This visualization of the statistics will help people who want to predict the travel time around Taichung City.
Open AccessVisualization and Travel Time Extraction System for the Statistics of TDCS Travel using MapReduce Framework
Recently, extracting some information as a knowledge from big data is very challenging activity. The size of data is very huge and it requires some special techniques and adequate processing hardware. It is also applied in vehicles transportation data at Taiwan National Freeway from the Traffic Data Collection System (TDCS). The results of this extraction will be very useful if it can be used by the community. So that the delivery of information extracted from large data that is easily understood becomes a necessary thing. Presentation of results using images / visuals will make it easier for people to interpret the information provided. In this project, an interactive visualization of the results of extracting statistical information is attempted to be provided. The results can be used by users to support the decision making of road users in determining the appropriate time when going through the road pieces around the Taichung City. This visualization of the statistics will help people who want to predict the travel time around Taichung City.
- Open Access
- 1 January 2018
- Published by Universitas Muhammadiyah Yogyakarta in Semesta Teknika
- Vol. 21 (1) , 60-64
Penerapan Metode Clustering dengan Algoritma K-Means pada Pengelompokkan Data Calon Mahasiswa Baru di Universitas Muhammadiyah Yogyakarta (Studi Kasus: Fakultas Kedokteran dan Ilmu Kesehatan, dan Fakultas Ilmu Sosial dan Ilmu Politik)
The increasing new prospective students in a University to make the stack more and more data, departing from it then conducted a search for new knowledge with data mining. Grouping data for prospective new students will be made by the method Clustering and used the algorithm k-means. In this penmaru there are 5 data attributes are used i.e., hometown, gender, status to qualify for selection, driveways, and majors. This analysis is performed using WEKA software and the source data taken from admissions data (penmaru) in the form of a data warehouse. Class from the use of this method is the attribute of the majors. Iteration performed as many as 3 times and the number of a cluster at the Faculty of medicine and health sciences, i.e. 4 clusters, Faculty of social and political science 3 clusters. Method Clustering can be applied to the classification of data for prospective new students. Another thing that can be analyzed from the results of the grouping candidate data, promotion strategies from each Department to increase the quantity and quality.
- 1 January 2018
- Published by Universitas Muhammadiyah Yogyakarta in Semesta Teknika
- Vol. 21 (1) , 60-64
Open AccessPenerapan Metode Clustering dengan Algoritma K-Means pada Pengelompokkan Data Calon Mahasiswa Baru di Universitas Muhammadiyah Yogyakarta (Studi Kasus: Fakultas Kedokteran dan Ilmu Kesehatan, dan Fakultas Ilmu Sosial dan Ilmu Politik)
The increasing new prospective students in a University to make the stack more and more data, departing from it then conducted a search for new knowledge with data mining. Grouping data for prospective new students will be made by the method Clustering and used the algorithm k-means. In this penmaru there are 5 data attributes are used i.e., hometown, gender, status to qualify for selection, driveways, and majors. This analysis is performed using WEKA software and the source data taken from admissions data (penmaru) in the form of a data warehouse. Class from the use of this method is the attribute of the majors. Iteration performed as many as 3 times and the number of a cluster at the Faculty of medicine and health sciences, i.e. 4 clusters, Faculty of social and political science 3 clusters. Method Clustering can be applied to the classification of data for prospective new students. Another thing that can be analyzed from the results of the grouping candidate data, promotion strategies from each Department to increase the quantity and quality.