APPLICATION OF MACHINE LEARNING IN IMAGE RECOGNITION  TO DETECT SOME ABNORMALITIES IN THE EXAMINATION ROOMS

Nguyen Tien Dat; Nguyen Truong Phuc; Pham Minh Chuan

Nguyen Tien Dat Faculty of Information Technology, Hung Yen University of Technology and Education
Nguyen Truong Phuc Faculty of Information Technology, Hung Yen University of Technology and Education
Pham Minh Chuan Faculty of Information Technology, Hung Yen University of Technology and Education

Keywords: Anomaly detection, machine learning, deep learning, Yolo, Recurrent Neural Network (RNN), OpenPose

Abstract

The phenomenon of academic dishonesty during examinations constitutes a grave concern, exerting adverse implications on the educational standard. Despite an extensive body of research addressing this issue, the practical application of machine learning technology remains significantly constrained. Consequently, the imperative to deploy machine learning mechanisms for the identification and mitigation of irregularities and fraudulent activities becomes paramount. This study endeavors to employ sophisticated deep learning models, including Yolov3 (You Only Look Once), OpenPose, RNN, among others, for the purpose of discerning behavioral patterns exhibited by examination candidates. Empirical findings reveal a commendable model accuracy, approximately reaching 83 %. This research investigation serves as a foundational framework for the development of an automated anomaly detection system within educational settings. Such a system is poised to alleviate the burden on examination supervisors, optimize examination room management, and ultimately enhance the overall educational quality.

References

Kamalov, F., Sulieman, H., & Santandreu Calonge, D., Machine learning based approach to exam cheating detection. Plos one, 2021, 16(8), e0254340.

Wan, Z., Li, X., Xia, B., & Luo, Z., Recognition of Cheating Behavior in Examination Room Based on Deep Learning. In 2021 International Conference on Computer Engineering and Application(ICCEA). IEEE, 2021, June, pp. 204-208.

Tiong, L. C. O., & Lee, H. J., E-cheating prevention measures: detection of cheating at online examinations using deep learning approach--a case study, 2021. arXiv preprint arXiv:2101.09841.

Jia, M., Gabrys, B., & Musial, K., A Network Science perspective of Graph Convolutional Networks: A survey. IEEE Access, 2023.

Albawi, S., Mohammed, T. A., & Al-Zawi, S., Understanding of a convolutional neural network. In 2017 international conference on engineering and technology (ICET), Ieee, 2017, August, pp. 1-6.

Schmidt, R. M., Recurrent neural networks (rnns): A gentle introduction and overview, 2019. arXiv preprint arXiv:1912.05911.

Hedegaard, L., & Iosifidis, A., Continual 3D convolutional neural networks for real-time processing of videos. In European Conference on Computer Vision, 2022, October, pp. 369-385. Cham: Springer Nature Switzerland.

Wang, Z., Lu, H., Jin, J., & Hu, K., Human Action Recognition Based on Improved Two-Stream Convolution Network. Applied Sciences, 2022, 12(12), 5784.

Caesar, H., Uijlings, J., & Ferrari, V., Coco-stuff: Thing and stuff classes in context. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 1209-1218.

Fang, H. S., Li, J., Tang, H., Xu, C., Zhu, H., Xiu, Y., ... & Lu, C., Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.

Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., ... & Zitnick, C. L., Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, Springer International Publishing, pp. 740-755.

Kynkäänniemi, T., Karras, T., Laine, S., Lehtinen, J., & Aila, T., Improved precision and recall metric for assessing generative models. Advances in Neural Information Processing Systems, 32, 2019.

Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S., Generalized intersection over union: A metric and a loss for bounding box regression. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 658-666.

Terven, J., Córdova-Esparza, D. M., & Romero-González, J. A., A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 2023, 5(4), pp. 1680-1716.

Fan, Q., Brown, L., & Smith, J., A closer look at Faster R-CNN for vehicle detection. In 2016 IEEE intelligent vehicles symposium (IV), IEEE, 2016, June, pp. 124-129.

He, K., Gkioxari, G., Dollár, P., & Girshick, R., Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961-2969.