Wickramasuriya Dilranjan S, Qi Chaoxian, Faghih Rose T
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:3562-3567. doi: 10.1109/EMBC.2018.8512928.
The human body responds to neurocognitive stress in multiple ways through its autonomic nervous system. Increases in heart rate, salivary cortisol and skin conductance level are often observed accompanying high levels of stress. Stress can also take on different forms including emotional, cognitive and motivational. While a precise definition for stress is lacking, a pertinent issue is to quantify the state of psychological stress manifested in the nervous system. State-space models have previously been applied to estimate an unobserved neural state (e.g. learning, consciousness) from physiological signal measurements and data collected during behavioral experiments. In this paper, we relate stress to the probability that a phasic driver impulse occurs in skin conductance signals. We apply state-space modeling to extracted binary measures to continuously track a stress level across episodes of cognitive and emotional stress as well as relaxation. Results demonstrate a promising approach for tracking stress through wearable devices.
人体通过自主神经系统以多种方式对神经认知应激做出反应。在高应激水平下，常观察到心率、唾液皮质醇和皮肤电导水平升高。应激也可以有不同形式，包括情绪、认知和动机方面的。虽然目前还缺乏对应激的确切定义，但一个相关问题是量化神经系统中表现出的心理应激状态。状态空间模型此前已被用于从生理信号测量以及行为实验收集的数据中估计未观察到的神经状态（例如学习、意识）。在本文中，我们将应激与皮肤电导信号中出现相位驱动脉冲的概率联系起来。我们将状态空间建模应用于提取的二元测量值，以在认知和情绪应激以及放松的各个阶段持续跟踪应激水平。结果表明了一种通过可穿戴设备跟踪应激的有前景的方法。
