摘要
为了实时识别异常驾驶状态,实现驾驶疲劳的提前预报,在驾驶模拟舱中采用脑电仪采集驾驶员脑电数据。采用功率谱估计分析正常阶段和疲劳过渡阶段的脑电数据,计算不同频段波能量分布情况,结果表明delta和alpha波在两种状态下变化显著,因此跟踪监测delta和alpha波能量变化能够实现驾驶疲劳的早期预报。为此,利用径向基神经网络构建预报系统,检验delta波的预报效果,同时提取delta波能量谱的全部极大值并通过多义线拟合,有效地提高预报性能。
In order to recognize abnormal driving state and realize driving fatigue early warning,the EEG data for a driver was recorded by an EEG apparatus in the Auto Sim,and analyzed between the awake and fatigue transitional phases by power spectrum estimation,the power distribution with frequency bands between two phases was given.The result shows delta and alpha activities are possible to predict driver fatigue early.So the prediction system was created by radical basis network to test the prediction effect of the delta activity and extracted all the maximums and used spline fitting in order to improve prediction performance.
出处
《人类工效学》
CSSCI
2009年第4期25-29,共5页
Chinese Journal of Ergonomics
基金
08科研基地-北京市教委科技创新平台-驾驶失误机理及对策研究(JJ004011200803)
关键词
驾驶疲劳预报
脑电
功率谱
径向基神经网络
driving fatigue prediction
EEG
power spectrum
radical basis network
