Lin Chin-Teng, Chuang Chun-Hsiang, Huang Chih-Sheng, Tsai Shu-Fang, Lu Shao-Wei, Chen Yen-Hsuan, Ko Li-Wei
IEEE Trans Biomed Circuits Syst. 2014 Apr;8(2):165-76. doi: 10.1109/TBCAS.2014.2316224. Epub 2014 May 19.
Brain activity associated with attention sustained on the task of safe driving has received considerable attention recently in many neurophysiological studies. Those investigations have also accurately estimated shifts in drivers' levels of arousal, fatigue, and vigilance, as evidenced by variations in their task performance, by evaluating electroencephalographic (EEG) changes. However, monitoring the neurophysiological activities of automobile drivers poses a major measurement challenge when using a laboratory-oriented biosensor technology. This work presents a novel dry EEG sensor based mobile wireless EEG system (referred to herein as Mindo) to monitor in real time a driver's vigilance status in order to link the fluctuation of driving performance with changes in brain activities. The proposed Mindo system incorporates the use of a wireless and wearable EEG device to record EEG signals from hairy regions of the driver conveniently. Additionally, the proposed system can process EEG recordings and translate them into the vigilance level. The study compares the system performance between different regression models. Moreover, the proposed system is implemented using JAVA programming language as a mobile application for online analysis. A case study involving 15 study participants assigned a 90 min sustained-attention driving task in an immersive virtual driving environment demonstrates the reliability of the proposed system. Consistent with previous studies, power spectral analysis results confirm that the EEG activities correlate well with the variations in vigilance. Furthermore, the proposed system demonstrated the feasibility of predicting the driver's vigilance in real time.
最近，在许多神经生理学研究中，与安全驾驶任务中持续注意力相关的大脑活动受到了相当大的关注。这些研究还通过评估脑电图（EEG）变化，根据驾驶员任务表现的变化，准确估计了他们的唤醒水平、疲劳程度和警觉性的变化。然而，当使用面向实验室的生物传感器技术时，监测汽车驾驶员的神经生理活动面临着重大的测量挑战。这项工作提出了一种基于新型干式EEG传感器的移动无线EEG系统（本文中称为Mindo），以实时监测驾驶员的警觉状态，从而将驾驶性能的波动与大脑活动的变化联系起来。所提出的Mindo系统采用了无线可穿戴EEG设备，以便方便地记录驾驶员头皮区域的EEG信号。此外，该系统可以处理EEG记录并将其转化为警觉水平。该研究比较了不同回归模型之间的系统性能。此外，所提出的系统使用Java编程语言作为移动应用程序来进行在线分析。一项涉及15名研究参与者的案例研究，他们在沉浸式虚拟驾驶环境中执行了90分钟的持续注意力驾驶任务，证明了所提出系统的可靠性。与先前的研究一致，功率谱分析结果证实EEG活动与警觉性变化密切相关。此外，所提出的系统证明了实时预测驾驶员警觉性的可行性。
