期刊文献+

基于脑电波分析技术的安全驾驶实验研究 被引量:4

Experimental Study on Safe Driving Based on Electroencephalography
下载PDF
导出
摘要 为了研究饮酒对驾驶过程中脑电波的影响,在由急弯、紧急停车港、障碍区和直线路段组成的虚拟场景中,利用脑电仪实时采集汽车驾驶员的脑电信号,建立脑电波分析指标体系,进行快速傅立叶变换后,计算δ波、θ波、α波、中间快波、β波以及γ波的平均功率,进而计算各频段波功率占总频段波功率的比例,比较组合指标(α+θ)/β在饮酒前后的差异,并运用成对t检验分析各项指标.结果表明,饮酒对θ、α和γ脑电波有显著影响,t检验结果小于0.01;对其余脑电波没有显著影响,t检验结果大于0.05.在3个显著变化的指标中,仅γ脑电波饮酒前、后的差值随着酒精浓度的下降逐渐减小,酒精浓度小于40.5 mg/100 ml后,差值为1.12%. In order to study the effects of alcohol drinking on electroencephalography(EEG) during driving,a system of indicators for EEG analysis were set up based on the real-time EEG data of drivers collected by a neuroscan EEG system under virtual scenes made of sharp curves,emergency stop belts,obstacle zones and straight line segments.After fast Fourier transform,the mean powers of delta wave(δ),theta wave(θ),alpha wave(α),middle fast wave,beta wave(β),and gama wave(γ) were calculated,and the proportion of the power in each frequency range to the whole frequency range was obtained.Then,the differences of the combined indicator(α+θ)/β were compared between drunk driving and non-drunk driving,and all the indicators were analyzed by the paired sample t-test.The results show that alcohol drinking affects significantly the theta wave,alpha wave,and gama wave,with t-test values being less than 0.01;but does not affect significantly the rest of EEGs,with t-test values being more than 0.05.Among the three parameters affected significantly,only the difference of gama wave before and after drinking reduces gradually with the blood alcohol concentration(BAC) decreasing.When the BAC dropped to 40.5 mg/100 ml,the difference of gama wave was 1.12%.
作者 欧居尚
出处 《西南交通大学学报》 EI CSCD 北大核心 2011年第4期695-700,共6页 Journal of Southwest Jiaotong University
基金 北京市教委科技创新平台资助项目(JJ004011200803) 四川省教育厅科研基金资助项目(10zc017)
关键词 交通安全 酒后驾驶 脑电波 虚拟场景 统计方法 traffic safety drunk driving electroencephalography virtual scenes statistical methods
  • 相关文献

参考文献11

二级参考文献36

共引文献65

同被引文献20

  • 1谢娜,张先国,张红霞,孔斌,袁萍,邓振华,黄思兴.酒后驾车道路交通事故流行病学研究[J].法律与医学杂志,2004,11(4):296-299. 被引量:13
  • 2李程雄,丁月华,文贵华.SVM-KNN组合改进算法在专利文本分类中的应用[J].计算机工程与应用,2006,42(20):193-195. 被引量:23
  • 3Michael Grafe,沈庆.德国工业中VR/AR技术应用现状和趋势[J].中国制造业信息化(应用版),2006(8):46-49. 被引量:6
  • 4陈炎,胡江碧,荣建,刘小明.脑电技术在驾驶行为分析中的应用[J].道路交通与安全,2006,6(9):15-17. 被引量:13
  • 5Minoru Sakairi, Suzuki Daisuke,Nishimura Ayako, et al. Simultaneous detection of breath-alcohol sensor for prevention of drunk driving[J]. IEICE Electronics Express,2010,7(6):467-472.
  • 6Huang J Y. The intelligent identification and control systems of vehicles drunk driving[J]. Advanced Materials Research, 2014, 926-930: 1459-1462.
  • 7Kokji Murata, Etsunori Fujita, Shigeyuki Kojima. Noninvasive biological sensor system for detection of drunk driving[J]. IEEE Transactions on Information Technology in Biomedicine,2011, 15(1): 19-25.
  • 8WU Y C, XIA Y,XIE P, et al. The design of an automotive anti- drunk driving system to guarantee the uniqueness of driver[C]. Proceedings- 2009 International Conference on Information Engineering and Computer Science, ICIECS 2009.
  • 9CHANG C C, LIN C J. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology. 2011, 2(3): 1-27.
  • 10Fabrizio Sebastiani. Machine learning in automated text categorization[J]. ACM Computing Surveys, 2002, 34(1): 1-47.

引证文献4

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部