摘要
为实现驾驶疲劳定量检测,设计了4 h高速单调路况模拟驾驶实验,通过编制的刺激信号采集反应时间,可穿戴设备采集皮电、肌电和心率信号,然后分析各信号变化规律,依据反应时间区分疲劳状态与清醒状态,选取生理信号特征指标,利用支持向量机(SVM)检测驾驶疲劳。研究发现:反应时间的变化呈跳跃性;皮电信号样本熵在疲劳状态下低于清醒状态,而大部分肌电信号样本熵在疲劳状态下高于清醒状态;基于SVM的驾驶疲劳检测算法准确率达86.25%,能有效识别驾驶疲劳。
To realize the quantitative examination of driving fatigue, a simulated driving experiment of 4 hours high speed monotone road condition is designed.The signals in terms of GSR, EMG, and HR are respectively collected from skin, through wearable devices. Support vector machine(SVM) has been ultilise to detect the degree of driving fatigue by measuring the characteristic index of physiological signals, which is obtained by judging sober state or fatigue state from reaction time.It is found that the change of reaction time is hopping. The sample entropy of GSR in fatigue state is lower than that in the sober state, and the sample entropy of most EMG is higher in fatigue state than that in the sober state. Consequently, driving fatigue can be effectively identified based on SVM with the accuracy of 86.25%.
引文
[1] Tobias Vogelpohl,Matthias Kiihnb,Thomas Hummelb,et al.Asleep at the Automated Wheel-sleepiness and Fatigue During Highly Automated Driving[J].Accident Analysis and Prevention,2018(3):13-18.
[2] 刘光远.人体生理信号的情感计算方法[M].北京:科学出版社,2014.
[3] Karthick P A,Ramakrishnan S.Surface Electromyography Based Muscle Fatigue Progression Analysis Using Modified B Distribution Time-frequency Features[J].Biomedical Signal Processing and Control,2016,26:42-51.
[4] Patel M,Lal S K L,Kavanagh D,et al.Applying Neural Network Analysis on Heart Rate Variability Data to Assess Driver Fatigue[J].Expert Systems with Applications,2011,38(6):7235-7242.
[5] Lanata A,Valenza G,Scilingo E P.The Role of Nonlinear Dynamics in Affective Valence and Arousal Recognition[J].IEEE Transactions on Affective Computing ,2012,3(2):237-249.
[6] 蔡菁.皮肤电反应信号在情感状态识别中的研究[D].重庆:西南大学,2010.
[7] Foong R,Ang K K,Quek C,et al.An Analysis on Driver Drowsiness Based on Reaction Time and EEG Band Power[C]//Proceedings of the 37th Annual International Conference Engineering in Medicine and Biology Society.New York:IEEE,2015:2012-2023.
[8] 赵晓华,许士丽,荣建.基于ROC曲线的驾驶疲劳脑电样本嫡判定阈值研究[J].西南交通大学学报,2003,48(1):178-183.
[9] 王小川,史峰,郁磊.Matlab神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.