基于睡眠剥夺模型的脑力疲劳检测方法研究

Research on Mental Fatigue Detecting Method Based on Sleep Deprivation Models

脑力疲劳是影响人类健康和安全的重要因素,通过脑电信号实现脑力疲劳的动态检测对于疲劳预防和提高工作绩效具有重要意义。本课题通过30h睡眠剥夺实验诱发脑力疲劳,同时采集脑电信号,每6h分析相对功率、功率比值、重心频率(CGF)、基准相对功率等脑电特征参数,采用回归分析方法建立脑力疲劳的预测模型,并进行导联优化。结果显示预测模型的线性拟合R2可达0.932,经过导联优化后在仅采用4导联脑电特征的情况下R2仍可达到0.811,满足日常应用中脑力疲劳的预测精度要求。

Mental fatigue is an important factor of human health and safety. It is important to achieve dynamic mental fatigue detection by using electroencephalogram （EEG） signals for fatigue prevention and job performance improvement. We in our study induced subjects＇ mental fatigue with 30 h sleep deprivation （SD） in the experiment. We extracted EEG features, including relative power, power ratio, center of gravity frequency （CGF）, and basic relative power ratio. Then we built mental fatigue prediction model by using regression analysis. And we conducted lead optimization for prediction model. Result showed that R2 of prediction model could reach to 0. 932. After lead optimization, 4 leads were used to build prediction model, in which R2 could reach to 0. 811. It can meet the daily application accuracy of mental fatigue prediction.