Brain Connectivity Laboratory, Department of Neuroscience and Neurorehabilitation, IRCCS San Raffaele Roma, Rome, Italy.
Department of Theoretical and Applied Sciences, eCampus University, Novedrate, Italy.
Pflugers Arch. 2024 Oct;476(10):1539-1554. doi: 10.1007/s00424-024-02988-z. Epub 2024 Jul 16.
Understanding the neural responses to indoor characteristics like temperature and light is crucial for comprehending how the physical environment influences the human brain. Our study introduces an innovative approach using entropy analysis, specifically, approximate entropy (ApEn), applied to electroencephalographic (EEG) signals to investigate neural responses to temperature and light variations in indoor environments. By strategically placing electrodes over specific brain regions linked to temperature and light processing, we show how ApEn can be influenced by indoor factors. We also integrate heart indices from a multi-sensor bracelet to create a machine learning classifier for temperature conditions. Results showed that in anterior frontal and temporoparietal areas, neutral temperature conditions yield higher ApEn values. The anterior frontal area showed a trend of gradually decreasing ApEn values from neutral to warm conditions, with cold being in an intermediate position. There was a significant interaction between light and site factors, only evident in the temporoparietal region. Here, the neutral light condition had higher ApEn values compared to blue and red light conditions. Positive correlations between anterior frontal ApEn and thermal comfort scores suggest a link between entropy and perceived thermal comfort. Our quadratic SVM classifier, incorporating entropy and heart features, demonstrates strong performance (until 90% in terms of AUC, accuracy, sensitivity, and specificity) in classifying temperature sensations. This study offers insights into neural responses to indoor factors and presents a novel approach for temperature classification using EEG entropy and heart features.
理解室内特征（如温度和光照）对神经的反应对于理解物理环境如何影响人类大脑至关重要。我们的研究采用了一种创新的方法，使用熵分析，特别是近似熵（ApEn），应用于脑电图（EEG）信号，来研究室内环境中温度和光照变化对神经的反应。通过在与温度和光照处理相关的特定大脑区域放置电极，我们展示了 ApEn 如何受到室内因素的影响。我们还整合了来自多传感器手环的心率指数，创建了一个用于温度条件的机器学习分类器。结果表明，在前额和顶颞区域，中性温度条件下的 ApEn 值较高。在前额区域，ApEn 值从中性到温暖条件逐渐降低，而寒冷条件处于中间位置。光和部位因素之间存在显著的相互作用，仅在前颞区域明显。在这个区域，中性光条件下的 ApEn 值高于蓝光和红光条件。前额 ApEn 与热舒适评分之间存在正相关，表明熵与感知热舒适之间存在联系。我们的二次支持向量机分类器，结合了熵和心率特征，在分类温度感觉方面表现出很强的性能（AUC、准确性、敏感性和特异性达到 90%）。这项研究深入了解了室内因素对神经的反应，并提出了一种使用 EEG 熵和心率特征进行温度分类的新方法。
