AI Education Based on Evaluating Concentration of Students in Class
Yuan Zhang, Changzhen Qiu, Ningze Zhong, Xieyang Su, Xuanrui Zhang, Fuquan Huang, Luping Wang, Liang Wang · 2021
Attention is an indispensable part of the learning process. Currently, teachers in most of the schools judge student’ concentration only by their eyes subjectively. But this approach not only distracts teachers from the lesson but also difficult to obtain feedback on the result after class. In this paper, we introduce a method based on machine vision to evaluate students’ concentration. We apply the YOLO algorithm on facial movement detection to predict whether students are engaged in class. It not only helps to differentiate instruction for students but also helps teachers to optimize their lessons. The experiments demonstrate that the method can achieve the assessment of students’ concentration within a small-size classroom.