Title: Anomaly detection of learners' online learning behaviour based on educational data mining

Authors: Baoyu Huang

Addresses: School of Information Engineering, Xiamen Ocean Vocational College, Xiamen, 361100, Fujian, China

Abstract: To improve the accuracy and efficiency of anomaly detection in online learning behaviour of learners, a research on anomaly detection of online learning behaviour of learners based on data mining is proposed. Firstly, by utilising the monitoring and recording module of the online education platform, the online learning status images of learners are collected and processed for noise reduction, binarisation, and connectivity. Then, based on this, the degree of change in the centroid of the human body contour is introduced to extract features for online learning behaviour anomaly detection. Finally, the improved YOLOv3 model is applied to construct an online learning behaviour anomaly detection model for learners, achieving the function of behaviour anomaly detection. The experimental outcomes reveal that the proposed method attains a detection precision exceeding 94.7%, with a peak detection latency of 1.81 ms.

Keywords: data mining; learners; online learning behaviour; anomaly detection.

DOI: 10.1504/IJCEELL.2025.146011

International Journal of Continuing Engineering Education and Life-Long Learning, 2025 Vol.35 No.3/4, pp.203 - 216

Received: 26 Jun 2024
Accepted: 06 Nov 2024
Published online: 01 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article