基于脑电特征的酒后驾车事故倾向预估建模

摘要/Abstract

摘要：

摘要：为建立酒后驾车的事故倾向预估模型，测量了18位驾驶员不同程度饮酒后的脑电信号和交通事故倾向指标，并分别根据左额叶区脑电的长时周期度和瞬时复杂度计算规范化脑电δ波功率增益和脑电模糊熵.引进一种混合型SigmaPi模糊神经网络，研究网络权值训练方法，构建脑电特征参数和事故倾向指标之间的预估模型.实验结果表明：模型估计值与实际值吻合较好，具有一致增减特性，在驾驶员饮酒量小于50%主观最大饮酒量时误差很小，在饮酒量大于50%主观最大饮酒量时误差随饮酒量增大有所增加.

关键词: 酒后驾车, 交通事故倾向, 脑电图, &delta, 波功率增益, 模糊熵

Abstract:

Abstract： This paper introduces the establishment of a predicting model for normalized traffic accident proneness (NAP) after drinking. Eighteen drivers’ EEGs and traffic accident proneness were measured respectively in different drunken states. Considering the instant complexity and longterm periodicity of EEGs measured from the left frontal lobe, the power gain of δ wave and fuzzy entropy of EEG were invented and calculated. A hybrid SigmaPi neural network was introduced and studied to help building the predict model for NAP from the aspects of both power gain of δ wave and fuzzy entropy of EEG. Experiments proved that the predicted values of NAP accord with the actual values, with a consistent increase and decrease characteristic. When the amount of the alcohol drunk is less than 50% of the subjective maximum alcohol to drink, the errors were very small, but when the amount of the alcohol drunk is more than 50%, the errors became bigger along with the increase volume of alcohol to drink.

Key words: drunk driving, traffic accident proneness, electroencephalogram (EEG), power gain of &delta, wave, fuzzy entropy

中图分类号:

U 491.2

钟铭恩1，吴平东2，彭军强3，洪汉池1. 基于脑电特征的酒后驾车事故倾向预估建模[J]. 上海交通大学学报（自然版）, 2015, 49(02): 287-292.

ZHONG Mingen1,WU Pingdong2，PENG Junqiang3,HONG Hanchi1. A Prediction Model for Traffic Accident Proneness Caused by Drunk Driving via Numerical Characteristics of Drivers’ EEGs[J]. Journal of Shanghai Jiaotong University, 2015, 49(02): 287-292.

参考文献

［1］World Health Organization. Global status report on road safety: Time for action［M］. Geneva: WHO Press, 2009.

［2］World Health Organization. Global status report on road safety: Supporting a decade of action［M］. Geneva: WHO Press. 2013.

［3］顾雯雯,俞敏,丛黎明. 酒后驾车现状与危害及预防控制研究进展［J］. 中国预防医学杂志, 2010, 11(08):854857.

GU Wenwen, YU Min, CHONG Liming. Review of present situation, harm and prevention control about drunk driving［J］. China Preventive Medicine, 2010, 11(08):854857.

［4］钟铭恩, 吴平东, 彭军强, 等．基于血液酒精浓度和脑电特征的酒后驾车事故倾向对比研究［J］. 中国生物医学工程学报, 2013,32(3):378383.

ZHONG Mingen, WU Pingdong, PENG Junqiang, et al. Comparative study of traffic accident proneness for drunk driving via blood alcohol concentration and EEG［J］. Chinese Journal of Biomedical Engineering, 2013, 32(3):378383.

［5］Murata K, Fujita E, Kojima S, et al. Noninvasive biological sensor system for detection of drunk driving［J］. IEEE Transactions on Information Technology in Biomedicine, 2011, 15(1):1925.

［6］Sakairi M, Suzuki D, Nishimura A, et al. Simultaneous detection of breath and alcohol using breathalcohol sensor for prevention of drunk driving［J］. IEICE Electronics Express, 2010, 7(6):467472.

［7］Koukiou G, Panagopoulos G, Anastassopoulos V. Drunk person identification using thermal infrared images［C］∥Processing of the 16th International Conference on Digital Signal. Santorini, Greecea: IEEE Press, 2009: 46.

［8］Bear M F, Connors B W, Paradiso M A. Neuroscience: Exploring the Brain 3rd edition［M］. USA: Lippincott Williams & Wilkins Press, 2007.

［9］Papadelis S C, Chen Z, Papadeli C K. Monitoring sleepiness with onboard electrophysiological recordings for preventing sleepdeprived traffic accidents［J］. Clinical Neurophysiology, 2007, 118(09):19061922．

［10］邹阳, 苗夺谦, 王登. 醉酒者和正常人脑电的样本熵研究［J］. 中国生物医学工程学报, 2010, 29(06): 939942.

ZOU Yang, MIAO Duoqian, WANG Deng. Research on sample entropy of alcoholic and normal people［J］. Chinese Journal of Biomedical Engineering, 2010, 29(06): 939942.

［11］范金锋, 邵晨曦, 王剑, 等. 醉酒者脑电和正常脑电非线性特性的比较评估［J］. 中国生物医学工程学报, 2008, 27(01):1828.

FAN Jinfeng, SHAO Chenxi, WANG Jian, et al. A comparative evaluation of nonlinear characteristics of EEG for alcoholic and normal people［J］. Chinese Journal of Biomedical Engineering, 2008, 27(01):1828.

［12］Wu D, Chen Z H, Feng R F, et al. Study on human brain after consuming alcohol based on EEG signal［C］∥Proceedings of the 3rd International Conference on Computer Science and Information Technology. Bangalore India: IEEE Press, 2010: 406409.

［13］Yazdani A, Setarehdan S K. Classification of EEG signals correlated with alcohol abusers［C］∥Proceedings of the 9th International Symposium on Signal Processing and Its Application. Sharjah: IEEE Press, 2007: 14.

［14］Kousarrizi M R N, Ghanbari A A, Gharaviri A, et al. Classification of alcoholics and nonalcoholics via EEG using SVM and neural networks［C］∥Proceedings of the 3rd International Conference on Bioinformatics and Biomedical Engineering. Beijing: IEEE Press, 2009: 14.

［15］钟铭恩, 方遒, 洪汉池, 等. 驾驶员脑电模糊熵与酒后驾车交通事故倾向相关性研究［J］. 中国安全科学学报, 2013,23(8):5964.

ZHONG Mingen, FANG Qiu, HONG Hanchi. A correlation study between fuzzy entropy of drivers’EEGs and traffic accident proneness for drunk driving［J］. China Safety Science Journal, 2013,23(8):5964.

［16］李纯明, 陈天平. SigmaPi 神经网络中的逼近问题［J］. 科学通报, 1996, 41(8): 683684.

LI Chunming, CHEN Tianping. Approximation problem in SigmaPi neural network［J］. Chinese Science Bulletin, 1996, 41(8): 683684.

[1]	李明爱1,2,3，许冬芹1. 综述：运动想像脑机接口中的迁移学习[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 37-59.
[2]	杨平1，盛杰1，王禹程2，李柱永1，金之俭1，洪智勇1. YBa2Cu3O7δ超导带材非均匀性对失超传播特性的影响[J]. 上海交通大学学报（自然版）, 2017, 51(9): 1090-1096.
[3]	何蕾, 姚雷. 2种复方精油的成分分析及对缓解焦虑情绪的效果评价[J]. 上海交通大学学报(农业科学版), 2016, 34(1): 52-56.
[4]	钟铭恩, 洪汉池, 吴平东, 方遒. 基于Uchida-Kraepelin心理测试的酒后驾车交通事故倾向测量[J]. 上海交通大学学报, 2016, 50(03): 413-418.
[5]	吴澄a, 陈迪a, 胡锐军a, 陈景东a, 陈翔a, 王晓韡b, 吕宝粮b, c. 柔性衬底MEMS技术制备脑电图干电极阵列研究[J]. 上海交通大学学报（自然版）, 2011, 45(07): 1035-1040.