An attention grading of students’ attention in online learning under different light environments

Abstract

With the rapid development of Internet technology and the influence of irresistible factors, online learning plays an increasingly prominent role in the field of education. For this study, students were recruited to participate two stages of online learning experiments. Twelve college students underwent EEG continuous recording by a portable device during a 6-hour experiment when the indoor lighting environment was set 300 lx, 4100 K (Stage 1) and when the indoor lighting environment was under five lighting setups (300 lx, 3000 K; 300 lx, 4000 K; 300 lx, 6500 K; 500 lx, 4000 K; 1000 lx, 4000 K; Stage 2). The EEG collected in the first stage was used to develop the attention grading model (AGM). In the second stage, EEGs were collected under different lighting environments and classified according to the model to analyze the students’ attention. The results show that the AGM can accurately classify students’ EEG signals into three levels, and the classification accuracy was up to 93.17%. Under the selected lighting conditions, the most suitable combination of lighting environments for online learning is 500 lx and 4100 K, which can promote concentration in a relatively short time and the concentration state lasts for a long time.