Exam Cheating Detection in Closed Room Using YOLOv8 Algorithm
DOI:
https://doi.org/10.55537/cosie.v4i2.1100Keywords:
Exam Cheating, Monitoring, Closed Room, YOLOv8Abstract
One of the challenges in monitoring exams in the classroom or closed room is the limited eye of the tire supervisor if he/she continues to monitor for a long time. Therefore, many behaviors of students cheating over the escape. One solution to overcome this problem is to implement an smart monitoring system that capable of detecting student exam cheating. A number of studies on smart monitoring systems have been conducted. However, the studies have not archieved optimal accuracy in identifying exam cheating. Therefore, this study provides a method to detect exam cheating in a closed room. The method used to detect the object is YOLO version 8 (Yolov8). Before training using the YOLOv8 method, hyperparameter tuning was made to generate best model performance. The test results have shown that the Yolov8s model has created the best performance with the precision, recall, IoU-Score and mAP50 values of 0.952, 0.966, 0.8977 and 0.984. Testing in the working environment shows that the Yolov8s model can detect exam cheating in real time at a frame rate of 28 fps. Although it has achieved quite optimal performance. However, the performance of this exam cheating monitoring system can still be improved. Furthermore, this study has limitations, specifically that it can only detect cheating in the place where the dataset was collected.
Downloads
References
[1] M. P. Pangestu, S. Wiyono, and D. I. Af’idah, “Platform Ujian Online Berbasis Pendeteksi Gerakan Kecurangan Menggunakan Kamera,” Infomatek, vol. 26, no. 1, pp. 55–62, 2024, doi: 10.23969/infomatek.v26i1.11208.
[2] F. A. Hariz, I. N. Yulita, and I. Suryana, “Human Activity Recognition Berdasarkan Tangkapan Webcam Menggunakan Metode Convolutional Neural Network (CNN) Dengan Arsitektur MobileNet,” J. Ilm. Teknol. Sist. Inf., vol. 3, no. 4, pp. 103–115, 2022, doi: 10.30630/jitsi.3.4.97.
[3] T. Nur, Huzaeni, and M. Khadafi, “Implementasi Metode Object Detection Dengan Algoritma Yolo (You Only Look Once) Untuk,” J. Teknol. Rekayasa Inf. dan Komput., vol. 6, no. 2, pp. 28–33, 2023.
[4] F. Bimantoro, I. G. Pasek, S. Wijaya, and M. R. Aohana, “Pendeteksian Kecurangan Ujian Melalui CCTV Menggunakan Algoritma YOLOv5,” in Prosiding Seminar Nasional Teknologi dan Sains Tahun 2024, 2024, vol. 3, pp. 109–117.
[5] Z. Wan, X. Li, B. Xia, and Z. Luo, “Recognition of Cheating Behavior in Examination Room Based on Deep Learning,” Proc. - 2021 Int. Conf. Comput. Eng. Appl. ICCEA 2021, pp. 204–208, 2021, doi: 10.1109/ICCEA53728.2021.00048.
[6] A. Zaffar, M. Jawad, and M. Shabbir, “A Novel CNN-RNN Model for E-Cheating Detection Based on Video Surveillance,” UW J. C. Sci., vol. 5, no. 1, pp. 1–13, 2023, [Online]. Available: https://uwjcs.org.pk/index.php/ojs/article/view/64.
[7] N. Tran, M. Nguyen, T. Le, T. Huynh, T. Nguyen, and T. Nguyen, “Exploring the potential of skeleton and machine learning in classroom cheating detection,” Indones. J. Electr. Eng. Comput. Sci., vol. 32, no. 3, pp. 1533–1544, 2023, doi: 10.11591/IJEECS.V32.I3.PP1533-1544.
[8] R. S. Wijaya, A. Wibisana, and E. R. Jamzuri, “Comparative Study of YOLOv5 , YOLOv7 and YOLOv8 for Robust Outdoor Detection,” J. Appl. Electr. Eng., vol. 8, no. 1, pp. 37–43, 2024.
[9] N. Affes, J. Ktari, N. Ben Amor, T. Frikha, and H. Hamam, “Comparison of YOLOV5, YOLOV6, YOLOV7 and YOLOV8 for Intelligent Video Surveillance,” J. Inf. Assur. Secur., vol. 18, no. 5, p. 147, 2023.
[10] M. Sohan, T. Sai Ram, and C. V. Rami Reddy, “A Review on YOLOv8 and Its Advancements,” 2024, pp. 529–545.
[11] H. Li, J. Huang, Z. Gu, D. He, J. Huang, and C. Wang, “Positioning of mango picking point using an improved YOLOv8 architecture with object detection and instance segmentation,” Biosyst. Eng., vol. 247, no. April, pp. 202–220, 2024, doi: 10.1016/j.biosystemseng.2024.09.015.
[12] P. Kaur, B. S. Khehra, and E. B. S. Mavi, “Data Augmentation for Object Detection: A Review,” in Midwest Symposium on Circuits and Systems (MWSCAS), 2021, pp. 537–543, doi: 10.1109/MWSCAS47672.2021.9531849.
[13] Suvarna Patil, Soham Waghule, Siddhesh Waje, Prasad Pawar, and Shreyash Domb, “Efficient Object Detection with YOLO: A Comprehensive Guide,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 4, no. 5, pp. 519–531, 2024, doi: 10.48175/ijarsct-18483.
[14] L. Ramos, E. Casas, E. Bendek, C. Romero, and F. Rivas-Echeverría, “Hyperparameter optimization of YOLOv8 for smoke and wildfire detection: Implications for agricultural and environmental safety,” Artif. Intell. Agric., vol. 12, pp. 109–126, 2024, doi: https://doi.org/10.1016/j.aiia.2024.05.003.
[15] Z. S. Hidayat, Y. A. Wijaya, and R. Kurniawan, “Optimizing YOLOv8 for Autonomous Driving: Batch Size for Best Mean Average Precision (mAP),” J. Tek. Inform., vol. 5, no. 4, pp. 1147–1153, 2024, doi: https://doi.org/10.52436/1.jutif.2024.5.4.1626.
[16] Z. Lin, S. Zhang, Y. Zhou, H. Wang, and S. Wang, “Learning rate burst for superior SGDM and AdamW integration,” J. Intell. Fuzzy Syst., vol. Preprint, pp. 1–11, 2024, doi: 10.3233/JIFS-239157.
[17] Rashmi, U. Ghose, and M. Gupta, “Comparative Design Analysis of Optimized Learning Rate for Convolutional Neural Network,” Lecture Notes on Data Engineering and Communications Technologies. Springer Singapore, Singapore, pp. 339–352, 2021.
[18] A. Jayasimhan and P. Pabitha, “A comparison between CPU and GPU for image classification using Convolutional Neural Networks,” in International Conference on Communication, Computing and Internet of Things (IC3IoT), 2022, pp. 1–4, doi: 10.1109/IC3IOT53935.2022.9767990.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Afandi Nur Aziz Thohari, Muttabik Fathul Lathief, Liliek Triyono, Kuwat Santoso
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
