Title: Data mining method for monitoring students' distance learning behaviour based on decision tree

Authors: Ketong Liu; Wenjing Ma; Andi Gao

Addresses: Centre for Modern Educational Technology, Hebei Institute of Mechanical and Electrical Technology, Xingtai, Hebei, China ' Information Engineering Department, Hebei Institute of Mechanical and Electrical Technology, Xingtai, Hebei, China ' Information Engineering Department, Hebei Institute of Mechanical and Electrical Technology, Xingtai, Hebei, China

Abstract: Because the traditional data mining methods for monitoring students' distance learning behaviours have low mining accuracy and recall, a data mining method for monitoring students' distance learning behaviours based on decision trees is proposed. First, the collected surveillance video image is compressed by OpenCV technology, and then transmitted to the client through UDP transmission mode. Then, the frequency domain enhancement method is used to enhance the processing of the surveillance image. The attention-based hybrid encoder decoder model is used to extract the sequence characteristics of students' remote learning behaviour from the enhanced surveillance image. Finally, the improved C4.5 algorithm is used to construct a decision tree, realise data mining for monitoring students' remote learning behaviour. The experimental results show that the mining accuracy and mining recall rate of this method reach more than 99%, which can accurately mine the monitoring data of students' distance learning behaviour.

Keywords: decision tree; learning behaviour; monitoring data; C4.5 algorithm; hybrid encoder decoder model.

DOI: 10.1504/IJDMB.2022.130343

International Journal of Data Mining and Bioinformatics, 2022 Vol.27 No.1/2/3, pp.73 - 91

Received: 19 Sep 2022
Accepted: 15 Dec 2022
Published online: 17 Apr 2023 *

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