Zhang Yu, Qin Fei, Liu Bo, Qi Xuan, Zhao Yingying, Zhang Dan
Institute of Education, Tsinghua University, Beijing, China.
Department of Psychology, School of Social Sciences, Tsinghua University, Beijing, China.
Front Hum Neurosci. 2018 Nov 12;12:457. doi: 10.3389/fnhum.2018.00457. eCollection 2018.
The rapid development of wearable bio-sensing techniques has made it possible to continuously record neurophysiological signals in naturalistic scenarios such as the classroom. The present study aims to explore the neurophysiological correlates of middle-school students' academic performance. The electrodermal signals (EDAs) and heart rates (HRs) were collected via wristband from 100 Grade seven students during their daily Chinese and math classes for 10 days in 2 weeks. Significant correlations were found between the academic performance as reflected by the students' final exam scores and the EDA responses. Further regression analyses revealed significant prediction of the academic performance mainly by the transient EDA responses ( = 0.083, < 0.05, with Chinese classes only; = 0.030, < 0.05, with both Chinese and math classes included). By combining the self-report data about session-based general statuses and the neurophysiological data, the explained powers of the regression models were further improved ( = 0.095, < 0.05, with Chinese classes only; = 0.057, < 0.05, with both Chinese and math classes included), and the neurophysiological data were shown to have independent contributions to the regression models. In addition, the regression models became non-significant by exchanging the academic performances of the Chinese and math classes as the dependent variables, suggesting at least partly distinct neurophysiological responses for the two types of classes. Our findings provide evidences supporting the feasibility of predicting educational outputs by wearable neurophysiological recordings.
可穿戴生物传感技术的快速发展使得在诸如教室等自然场景中连续记录神经生理信号成为可能。本研究旨在探索中学生学业成绩的神经生理相关性。在两周内的10天里，通过腕带从100名七年级学生日常的语文和数学课上收集了皮肤电信号（EDA）和心率（HR）。发现学生期末考试成绩所反映的学业成绩与EDA反应之间存在显著相关性。进一步的回归分析表明，主要是短暂的EDA反应对学业成绩有显著预测作用（仅语文课时，β = 0.083，p < 0.05；包括语文和数学课时，β = 0.030，p < 0.05）。通过结合关于基于课程的一般状态的自我报告数据和神经生理数据，回归模型的解释力进一步提高（仅语文课时，R² = 0.095，p < 0.05；包括语文和数学课时，R² = 0.057，p < 0.05），并且神经生理数据对回归模型有独立贡献。此外，将语文和数学课的学业成绩作为因变量进行交换后，回归模型变得不显著，这表明这两种类型的课程至少部分存在不同的神经生理反应。我们的研究结果为通过可穿戴神经生理记录预测教育产出的可行性提供了证据支持。
