Biomedical Engineering Graduate Program, College of Engineering, American University of Sharjah, Sharjah P.O. Box 26666, United Arab Emirates.
Department of Rehabilitation and Movement Sciences, Rutgers University, Newark, NJ 07107, USA.
Sensors (Basel). 2024 Aug 20;24(16):5373. doi: 10.3390/s24165373.
Assessments of stress can be performed using physiological signals, such as electroencephalograms (EEGs) and galvanic skin response (GSR). Commercialized systems that are used to detect stress with EEGs require a controlled environment with many channels, which prohibits their daily use. Fortunately, there is a rise in the utilization of wearable devices for stress monitoring, offering more flexibility. In this paper, we developed a wearable monitoring system that integrates both EEGs and GSR. The novelty of our proposed device is that it only requires one channel to acquire both physiological signals. Through sensor fusion, we achieved an improved accuracy, lower cost, and improved ease of use. We tested the proposed system experimentally on twenty human subjects. We estimated the power spectrum of the EEG signals and utilized five machine learning classifiers to differentiate between two levels of mental stress. Furthermore, we investigated the optimum electrode location on the scalp when using only one channel. Our results demonstrate the system's capability to classify two levels of mental stress with a maximum accuracy of 70.3% when using EEGs alone and 84.6% when using fused EEG and GSR data. This paper shows that stress detection is reliable using only one channel on the prefrontal and ventrolateral prefrontal regions of the brain.
压力评估可以通过生理信号来进行，例如脑电图（EEG）和皮肤电反应（GSR）。商业化的 EEG 检测系统需要在一个有多个通道的受控环境中运行，这限制了它们的日常使用。幸运的是，用于压力监测的可穿戴设备的使用正在增加，这提供了更大的灵活性。在本文中，我们开发了一种集成 EEG 和 GSR 的可穿戴监测系统。我们提出的设备的新颖之处在于，它只需要一个通道即可同时获取两种生理信号。通过传感器融合，我们实现了更高的准确性、更低的成本和更好的易用性。我们在二十名人类受试者身上进行了实验测试。我们估计了 EEG 信号的功率谱，并使用五种机器学习分类器来区分两种不同程度的精神压力。此外，我们还研究了当仅使用一个通道时头皮上的最佳电极位置。我们的结果表明，该系统仅使用大脑前额叶和腹外侧前额叶区域的一个通道，就能够以最高 70.3%的准确率对两种程度的精神压力进行分类，而使用融合后的 EEG 和 GSR 数据时，准确率则高达 84.6%。本文表明，仅使用一个通道就可以在前额叶和腹外侧前额叶区域可靠地检测压力。
