Proceedings of the 2024 Brawijaya International Conference (BIC 2024)

<Previous Article In Volume
Next Article In Volume>

Enhancing Exam Cheating Detection with MobileOne: A YOLOv5 Algorithm Approach to Abnormal Behavior Recognition

Authors
Muhammad Ihsan Shiddiq1, Aliyah Kurniasih2, *
1Universitas Ary Ginanjar, Menara 165, Jakarta Selatan, Indonesia
2Universitas Ary Ginanjar, Menara 165, Jakarta Selatan, Indonesia
*Corresponding author. Email: aliyah.kurniasih@uag.ac.id
Corresponding Author
Aliyah Kurniasih
Available Online 11 November 2025.
DOI
10.2991/978-94-6463-854-7_2How to use a DOI?
Keywords
Abnormal behavior; YOLO; Backbone; MobileOne
Abstract

Cheating in educational institutions remains a persistent challenge, with current surveillance methods often limited by human capacity. This research proposes an object detection approach using the YOLOv5 algorithm to detect early signs of cheating activities, leveraging its real-time capabilities. To enhance YOLOv5’s accuracy, we explore replacing its CSPDarknet53 feature extraction backbone with MobileOne. Integrating MobileOne significantly improves YOLOv5 performance, achieving 98.1% accuracy, a 0.4% increase over the original algorithm. This enhancement surpasses YOLOv7 by 12.9%, which achieves 85.2% accuracy on the same dataset. The MobileOne-augmented model not only enhances detection precision and recall rates crucial for real-time reliability but also reduces computational complexity, making it efficient for resource-constrained deployments. This approach proves effective for early detection of cheating activities, balancing computational efficiency with high performance.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2024 Brawijaya International Conference (BIC 2024)
Series
Atlantis Advances in Applied Sciences
Publication Date
11 November 2025
ISBN
978-94-6463-854-7
ISSN
3091-4442
DOI
10.2991/978-94-6463-854-7_2How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Muhammad Ihsan Shiddiq
AU  - Aliyah Kurniasih
PY  - 2025
DA  - 2025/11/11
TI  - Enhancing Exam Cheating Detection with MobileOne: A YOLOv5 Algorithm Approach to Abnormal Behavior Recognition
BT  - Proceedings of the 2024 Brawijaya International Conference (BIC 2024)
PB  - Atlantis Press
SP  - 3
EP  - 16
SN  - 3091-4442
UR  - https://doi.org/10.2991/978-94-6463-854-7_2
DO  - 10.2991/978-94-6463-854-7_2
ID  - Shiddiq2025
ER  -