期刊论文

Hung, Jui-Long

英文

IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES

1939-1382

2020

13

3

617-630

10.1109/TLT.2020.2988253

Manuscript received April 5, 2019; revised August 9, 2019 and March 10, 2020 and March 17, 2020; accepted April 12, 2020. Date of publication April 20, 2020; date of current version September 16, 2020. This work was supported by the National Natural Science Foundation of China under Grant 61937001 and Grant 61877027. (Corresponding author: Jui-Long Hung.) Zongkai Yang, Juan Yang, and Xu Du are with the National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China (e-mail: zkyang@mail.ccnu.edu.cn; yangjuan_hust@163.com; duxu@mail.ccnu.edu.cn).

本校为第一机构

This article proposes two innovative approaches, the one-channel learning image recognition and the three-channel learning image recognition, to convert student's course involvements into images for early warning predictive analysis. Multiple experiments with 5235 students and 576 absolute/1728 relative input variables were conducted to verify their effectiveness. The results indicate that both methods can significantly capture more at-risk students (the highest average recall rate is equal to 77.26%) than the following machine learning algorit...