Investigation on Driver Fatigue Based on WBAN and Approximate Entropy of Multi-Physiological Signals
Wang Lin1,2*, Fu Rongrong3, Zhang Chen1, Yin Xiaowei1, Hua Chengcheng2, Wang Hong2
1Department of Mechanical Engineering, Shenyang Institute of Engineering, Shenyang 110136, China 2School of Mechanical Engineering and Automation, Northeastern University, Shenyang 110819, China 3Measurement Technology and Instrumentation Key Lab of Hebei Province, Yanshan University, Qinhuangdao 066004, Hebei, China
Abstract：Aimed to reasonably evaluate driver fatigue in driving process, three kinds of physiological signals, including electroencephalograph (EEG), electromyography (EMG) and respiration (RESP) signals of 12 subjects are recorded by wireless body area network (WBAN). Then, the approximate entropy (ApEn) of the signals are investigated during the driving process. The experimental results show that, ApEn of EEG, EMG, and RESP decrease in driving process. After about 90 min, the ApEn stays at a certain range of value, indicating the deeply driver fatigue. From principle components analysis, the contributions of the first two components are 47.33% and 40.26% (the total is more than 85%), and the weight of EEG and EMG is higher than RESP. From the statistical analysis, the values of P of ApEn of EEG and EMG are lower than 0.05, indicating EEG and EMG have better discrimination on driver fatigue. In case of the combination of EEG-EMG, there is obvious discrimination for the probability distribution of normal and fatigued state. This combination can effectively evaluate the fatigue degree during driving. Therefore, an optimized combination of physiological signals may be obtained, which is reasonable and reliable to evaluate the physiological characteristics of driver fatigue. The research results of present work can give a guidance to evaluate and relieve the driver fatigue.
王琳, 付荣荣, 张陈, 尹晓伟, 化成城, 王宏. 基于无线体域网和复合生理信号近似熵的驾驶疲劳研究[J]. 中国生物医学工程学报, 2017, 36(5): 543-549.
Wang Lin, Fu Rongrong, Zhang Chen, Yin Xiaowei, Hua Chengcheng, Wang Hong. Investigation on Driver Fatigue Based on WBAN and Approximate Entropy of Multi-Physiological Signals. Chinese Journal of Biomedical Engineering, 2017, 36(5): 543-549.
[1] Kumar M, Weippert M, Arndt D, et al. Fuzzy filtering for physiological signal analysis [J]. IEEE Transactions on Fuzzy Systems, 2010, 18(1): 208-216. [2] Ye Ning, Sun Yuge, Yang Dan. Noninvasive heart rate variability detection device for fatigue driving detection system [J]. Applied Mechanics and Materials, 2013, 246: 194-198. [3] Choi A, Woo W. Daily physiological signal monitoring system for fostering social well-being in smart spaces [J]. Cybernetics and Systems, 2010, 41(3): 262-279. [4] Kwofie S, Rahbar N. A fatigue driving stress approach to damage and life prediction under variable amplitude loading [J]. International Journal of Damage Mechanics, 2013, 22(3): 393-404. [5] 李昕,李红红,李长吾.基于复杂度熵特征融合的高压力人群情感状态评估[J].中国生物医学工程学报,2013,32(3):313-320. [6] 张启忠,席旭刚,马玉良,等.基于表面肌电信号的手腕动作模式识别[J].中国生物医学工程学报,2013,32(3):257-265. [7] 谢宏,周笑丽,夏斌,等.疲劳驾驶识别中的脑电信号特征选择算法和支持向量机模型研究[J].中国生物医学工程学报,2014,33(4):482-486. [8] Lal SKL, Craig A. A critical review of the psychophysiology of driver fatigue [J], Biological Psychology, 2001, 55: 173-194. [9] Patel M, Lal SKL, 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. [10] 付荣荣,王宏,王琳,等.基于无线体域网中多生理信号驾驶疲劳检测[J].东北大学学报(自然科学版),2014,35(6):850-853. [11] Lin Zhui, Wang Lide, Zhou Jieqiong, et al. The research on fatigue driving detection algorithm [J]. Journal of Software, 2013, 8(9): 2272-2279. [12] Zhao Shuanfeng, Xu Guanghua, Guo Wei. Parallel diagnosis model of fatigue driving based on vehicle running status [J]. Journal of Networks, 2013, 8(11): 2585-2591. [13] Yang Qiufen, Li Canjun, Li Zhenjun. Application of FTGSVM algorithm in expression recognition of fatigue driving [J]. Journal of Multimedia, 2014, 9(4): 527-533. [14] Richman JS, Moorman JR. Physiological time-series analysis using approximate entropy and sample entropy [J]. AJP Heart & Circulatory Physiology, 2000, 278(6): 2039-2049. [15] Dias NS, Carmo JP, Mendes PM, et al. Wireless instrumentation system based on dry electrodes for acquiring EEG signals [J]. Medical Engineering & Physics, 2012,34(7): 978-981. [16] Bonfort G, Evans R, Nelson B, et al. A randomized clinical trial of exercise and spinal manipulation for patients with chronic neck pain [J]. Spine, 2001, 26(7): 798-799. [17] 徐安,刘军,彭旗宇,等.动态近似熵快速算法在心率变异研究中的应用[J].同济大学学报(自然科学版),2005,33(4):520-524. [18] Takens F. Detecting strange attractors in turbulence [J]. Lecture Notes in Mathematics, 1981, 898: 366-381. [19] Foij O, Holcik J. Applying nonlinear dynamics to ECG signal processing[J]. IEEE Engineering in Medicine and Biology, 1998, 3(4): 96-110. [20] Wang Hong, Zhang Chi, Shi Tianwei, et al. Real-time EEG-based detection of fatigue driving danger for accident prediction [J]. International Journal of Neural Systems, 2015, 25(2): 155-164. [21] James CB, Robert E, Willianm F. The fuzzy c-means clustering algorithm [J]. Computers & Geosciences, 1984(10): 191-203. [22] 吴群.基于心电信号的疲劳驾驶检测方法研究[D].杭州:浙江大学,2008:45.
