基于ROC曲线的驾驶疲劳脑电样本熵判定阈值研究

赵晓华; 许士丽; 荣建; 张兴俭

doi:10.3969/j.issn.0258-2724.2013.01.028

基于ROC曲线的驾驶疲劳脑电样本熵判定阈值研究

doi: 10.3969/j.issn.0258-2724.2013.01.028

基金项目:

北京市教委科技创新平台项目(JJ004011200803)

北京市科研基金资助项目(8112004)

计量
- 文章访问数: 1165
- HTML全文浏览量: 62
- PDF下载量: 606
- 被引次数: 0
出版历程
- 收稿日期: 2011-06-02
- 刊出日期: 2013-02-25

Discriminating Threshold of Driving Fatigue Based on the Electroencephalography Sample Entropy by Receiver Operating Characteristic Curve Analysis

摘要

摘要: 为了获得客观而准确的驾驶疲劳判别阈值,采用驾驶模拟实验研究方法,采集驾驶员在清醒及疲劳状态下的脑电信号,对比分析不同状态下脑电信号的时域特征,选取表征信号复杂程度的样本熵作为驾驶疲劳判别指标,并利用受试者工作特性曲线(receiver operating characteristic curve, ROC)分析方法,确定基于脑电信号样本熵值的驾驶疲劳判别阈值.研究结果表明:脑电信号样本熵值处于区间(0.32,0.71)时,驾驶员处于疲劳过渡时期,可能出现疲劳特征;脑电信号样本熵值小于阈值0.605时,判定驾驶员处于驾驶疲劳状态,准确率为0.95,该值可作为基于脑电信号样本熵的驾驶疲劳判定阈值.
- 样本熵 /
- 脑电信号 /
- 最佳阈值 /
- 驾驶疲劳判别 /
- ROC曲线
Abstract: In order to acquire an objective and accurate driving fatigue threshold, electroencephalography (EEG) signals of drivers were collected from driving simulator, and the time-domain characteristics of EGG signals of drivers in sober and mental fatigue states were comparatively analyzed. Considering the different complexity of EEG signals in sober and fatigue states, the sample entropy of EEG signals were calculated to characterize the complexity of signals, and used as the index for identifying driving fatigue. Based on the obtained EGG sample entropy, the receiver operating characteristic (ROC) curve analysis was introduced to obtain the discriminating threshold of driving fatigue. The results indicate that when the EEG sample entropy value is between (0.32, 0.71), the driver is in the transitional period of fatigue, may be in a fatigue state; the sample entropy of less than 0.605 can be identified as the threshold of driving fatigue, and the accuracy is 0.95.
- sample entropy /
- EEG signal /
- discriminating threshold /
- driving fatigue /
- ROC curve

HTML全文

参考文献(12)

刘灵,邓小燕,徐颖. 汽车驾驶员驾驶疲劳监测方法与装置的研究现状[J]. 医疗卫生装备,2006,27(12): 28-30. LIU Ling, DENG Xiaoyan, XU Ying. Development of detecting techniques and devices for vehicle driver fatigue[J]. Chinese Medical Equipment Journal, 2006, 27(12): 28-30.

赵晓华,房瑞雪,毛科俊,等. 基于生理信号的驾驶疲劳声音对策有效性实验[J]. 西南交通大学学报,2010,45(3): 457-463. ZHAO Xiaohua. FANG Ruixue, MAO Kejun, et al. Test on effectiveness of sound as countermeasure against driving fatigue based on physiological signals[J]. Journal of Southwest Jiaotong University, 2010, 45(3): 457-463.

MCCARTTA T, R IBNER S A, PACK A I, et al. The scope and nature of the drowsy driving problem in New York state[J]. Accident Analysis and Prevention, 1996, 28(4): 511-517.

SAGBERG F. Road accidents caused by drivers falling asleep[J]. Accident Anal Prevent, 1999, 31(6): 639-649.

PACK A I, PACK A M, RODGMAN E, et al. Characteristics of crashes attributed to the driver having fallen asleep[J]. Accident Anal Prevent, 1995, 27(6): 769-775.

BROWN I D. Methodological issues in driver fatigue research[M]. London: Taylor & Francis, 1995: 155-166.

房瑞雪,赵晓华,荣建,等. 基于脑电信号的驾驶疲劳研究[J]. 公路交通科技,2009,26(增刊): 124-126. FANG Ruixue, ZHAO Xiaohua, RONG Jian, et al. Study on driving fatigue based on EEG signals[J]. Journal of Highway and Transportation Research and Development, 2009, 26(Sup.): 124-126.

彭军强,吴平东,殷罡,等. Hilbert-Huang变换结合近似熵在疲劳驾驶时脑电分析中的应用[J]. 公路交通科技,2008,25(6): 126-129. PENG Junqiang, WU Pingdong, YIN Gang, et al. Application of combining Hilbert-Huang transform with approximate entropy in EEG signal analyzing of fatigued driving[J]. Journal of Highway and Transportation Research and Development, 2008, 25(6): 126-129.

周建芳,罗晓曙,胡叶荣. 脑电信号的样本熵分析[J]. 广西物理,2007,28(2): 15-17. ZHOU Jianfang, LUO Xiaoshu, HU Yerong. Sample entropy analysis of EEG[J]. Journal of Guangxi Physics, 2007, 28(2): 15-17.

和卫星,陈晓平,邵珺婷. 基于样本熵的睡眠脑电分期[J]. 江苏大学学报,2009,30(5): 501-504. HE Weixing, CHEN Xiaoping, SHAO Junting. Sleep EEG staging based on sample entropy[J]. Journal of Jiangsu University, 2009, 30(5): 501-504.

陈卫中,倪宗瓒,潘晓平,等. 用ROC曲线确定最佳临界点和可疑值范围[J]. 现代预防医学,2005,32(7): 729-731. CHENG Weizhong, NI Zongzan, PAN Xiaoping, et al. Receiver operating characteristic curves to determine the optimal operating point and doubtable value interval[J]. Mordern Preventive Medicine, 2005, 32(7): 729-731.

孙长亮,何峻,肖怀铁. 基于ROC曲线的目标识别性能评估方法[J]. 雷达科学与技术,2007,5(1): 17-21. SUN Changliang, HE Jun, XIAO Huaitie. A new performance evaluation method based on ROC curve[J]. Radar Science and Technology, 2007, 5(1): 17-21.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1165
HTML全文浏览量: 62
PDF下载量: 606
被引次数: 0

基于ROC曲线的驾驶疲劳脑电样本熵判定阈值研究

doi: 10.3969/j.issn.0258-2724.2013.01.028

计量

出版历程

Discriminating Threshold of Driving Fatigue Based on the Electroencephalography Sample Entropy by Receiver Operating Characteristic Curve Analysis

计量

出版历程

目录