[论文解读] EEG-based Investigation of the Impact of Classroom Design on Cognitive Performance of Students

Jesús G. Cruz-Garza, Michael Darfler+3 more|arXiv (Cornell University)|Feb 6, 2021

Color perception and design参考文献 83被引用 5

一句话总结

本研究探讨了虚拟教室设计（特别是窗户位置和房间尺寸）对学生认知表现的影响，采用脑电图（EEG）和行为测试进行分析。尽管在不同设计下的认知测试表现未发现显著差异，但双侧额叶、顶叶和枕叶区域的θ波段和α波段EEG特征在不同条件下表现出显著且分类鲁棒的差异，尤其在视觉记忆测试中表现最为明显。

ABSTRACT

This study investigated the neural dynamics associated with short-term exposure to different virtual classroom designs with different window placement and room dimension. Participants engaged in five brief cognitive tasks in each design condition including the Stroop Test, the Digit Span Test, the Benton Test, a Visual Memory Test, and an Arithmetic Test. Performance on the cognitive tests and Electroencephalogram (EEG) data were analyzed by contrasting various classroom design conditions. The cognitive-test-performance results showed no significant differences related to the architectural design features studied. We computed frequency band-power and connectivity EEG features to identify neural patterns associated to environmental conditions. A leave one out machine learning classification scheme was implemented to assess the robustness of the EEG features, with the classification accuracy evaluation of the trained model repeatedly performed against an unseen participant's data. The classification results located consistent differences in the EEG features across participants in the different classroom design conditions, with a predictive power that was significantly higher compared to a baseline classification learning outcome using scrambled data. These findings were most robust during the Visual Memory Test, and were not found during the Stroop Test and the Arithmetic Test. The most discriminative EEG features were observed in bilateral occipital, parietal, and frontal regions in the theta and alpha frequency bands. While the implications of these findings for student learning are yet to be determined, this study provides rigorous evidence that brain activity features during cognitive tasks are affected by the design elements of window placement and room dimensions.

研究动机与目标

• 考察不同教室设计要素（窗户位置和房间尺寸）对学生认知表现的神经与行为影响。
• 确定建筑特征是否会影响认知任务期间的EEG模式。
• 评估EEG特征在使用机器学习分类不同教室环境时的判别能力。
• 识别对环境设计变化最敏感的特定脑区和频段。
• 通过留一法验证评估EEG分类在不同参与者间的鲁棒性。

提出的方法

• 参与者在五种不同的虚拟教室设计中完成五项认知任务（Stroop、数字广度、Benton、视觉记忆、算术）。
• 收集并分析了θ波段（4–8 Hz）和α波段（8–12 Hz）的功率以及功能连接度量指标。
• 采用留一法交叉验证的机器学习分类框架，评估不同设计条件下EEG特征的判别能力。
• 将分类准确率与使用随机化EEG数据的基线进行比较，以评估统计显著性。
• 基于电极位置和脑源定位，将神经特征定位至双侧额叶、顶叶和枕叶区域。
• 量化并比较不同条件下认知任务的表现，以评估行为效应。

实验结果

研究问题

• RQ1 教室窗户位置和房间尺寸的变化是否显著影响认知任务表现？
• RQ2 哪些EEG频段和脑区对不同教室设计表现出最一致的神经反应？
• RQ3 能否利用机器学习可靠地通过EEG特征分类参与者所处的不同教室环境？
• RQ4 在特定认知任务期间观察到的神经差异是否比其他任务更为显著？
• RQ5 当以随机化数据作为基线时，EEG特征的分类性能与随机水平相比如何？

主要发现

• 在不同教室设计条件下，认知测试表现未发现显著差异。
• θ波段和α波段的EEG特征在不同教室设计中表现出一致且统计显著的差异，尤其在视觉记忆测试期间最为明显。
• 使用真实EEG数据时，机器学习分类器的准确率显著高于基线，表明环境条件具有鲁棒的可判别性。
• 最具判别力的EEG特征位于双侧枕叶、顶叶和额叶区域。
• 分类性能在视觉记忆测试中最高，而在Stroop测试和算术测试中最低，表明其具有任务依赖性敏感性。
• 本研究提供了证据，表明即使行为表现未变，脑活动仍会受到窗户位置和房间尺寸等建筑特征的调节。