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

doi:10.3969/j.issn.0258-8021. 2014. 04.013

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1864 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对疲劳驾驶识别中脑电特征选择和分类模型，提出采用粗糙集理论的离散化算法对通道和脑电信号特征量进行选择，选用支持向量机作为疲劳驾驶识别模型，并将疲劳误判风险作为支持向量机模型参数进行模型优化。针对5名受试者的实验结果表明，与主分量方法相比，粗糙集离散化算法选取的特征量较少，以0.8为相容度阈值，在208个候选特征中选择的特征数为2～4个，不同被试者选取的特征不同且对建立支持向量机识别模型有影响；疲劳误判风险控制参数可以达到调节支持向量机识别模型误判风险。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	谢宏^*周笑丽夏斌杨文璐姚

关键词 ：脑电信号, 功率谱, 疲劳, 粗糙集, 支持向量机

Key words： EEG power spectrum fatigue rough set support vector machine (SVM)

基金资助:交通部基础研究项目（20103188）；上海海事大学基金（20110015）

引用本文:

谢宏^*周笑丽夏斌杨文璐姚. 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.
XIE Hong^* ZHOU Xiao Li XIA Bin YANG Wen Lu YAO Nan. Research on Selection Algorithm of EEG Signal Features and SVM Based Model for Driver’s Fatigue Recognition. journal1, 2014, 33(4): 482-486.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2014. 04.013 或 http://cjbme.csbme.org/CN/Y2014/V33/I4/482

［1］李都厚, 刘群, 袁伟, 等. 疲劳驾驶与交通事故关系［J］. 交通运输工程学报, 2010, 10(2): 104-109.
［2］傅佳伟, 石立臣, 吕宝粮. 基于EEG的警觉度分析与估计研究综述［J］. 中国生物医学工程学报, 2009, 28(4): 589-596.
［3］Lin CT, Chang CJ, Lin BS, et al. A realtime wireless braincomputer interface system for drowsiness detection ［J］. IEEE Transactions on Biomedical Circuits and Systems, 2010, 4(4): 214-222.
［4］毛科俊, 刘小明, 赵晓华, 等. 基于脑电信号的驾驶疲劳预报关键参数选取［J］. 北京工业大学学报, 2010, 36(7): 966-970.
［5］胡淑燕, 郑钢铁. 基于EEG频谱特征的驾驶员疲劳监测研究［J］. 中国安全生产科学技术, 2010, 6(3): 90-94.
［6］Khushaba RN, Kodagoda S, Lal S, et al. Driver drowsiness classification using fuzzy waveletpacket based feature extraction algorithm ［J］. IEEE Transactions on Biomedical Engineering, 2011, 58(1): 121-131.
［7］Lin CT, Ko LW, Chung IF, et al. Adaptive EEGbased alertness estimation system by using ICAbased fuzzy neural networks ［J］. IEEE Transactions on Circuits and Systems I: Regular Papers, 2006, 53(11): 2469-2476.
［8］Duann JR, Chen PC, Ko LW, et al. Detecting frontal EEG activities with forehead electrodes ［J］. Lecture Notes in Computer Science, 2009, 5638: 373-379. 
［9］Peiris MTR, Jones RD, Davidson PR, et al. Detecting behavioral microsleeps from EEG power spectra ［C］// Proceedings of the 28th IEEE EMBS Annual International Conference. New York City: IEEE, 2006:5723-5726.
［10］Chuang CH, Lai PC, Ko LW, et al. Driver’s cognitive state classification toward brain computer interface via using a generalized and supervised technology ［C］// The 2010 International Joint Conference on Neural Networks (IJCNN). Barcelona: IEEE, 2010:1-7.
［11］Cao Lei, Li Jie, Sun Yaoru, et al. EEGbased vigilance analysis by using fisher score and PCA algorithm ［C］// 2010 IEEE International Conference on Progress in Informatics and Computing (PIC). Shanghai: IEEE, 2010, 1: 175-179.
［12］Shi Lichen, Lu Baoliang. Dynamic clustering for vigilance analysis based on EEG ［C］// 30th Annual International Conference of the IEEE, EMBS 2008: 54-57.
［13］Shi Lichen, Lu Baoliang. OffLine and onLine vigilance estimation based on linear dynamical system and manifold learning ［C］// Proceeding of 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Buenos Aires: IEEE, 2010:6587-6590.
［14］Pan Jun, Ren Qingsheng, Lu Hongtao. Vigilance analysis based on fractal features of EEG signals ［C］// International Symposium on Computer, Communication, Control and Automation. Tainan: IEEE, 2010: 446-449.
［15］Ouyang Tian, Lu Hongtao. Vigilance analysis based on continuous wavelet transform of EEG signals ［C］// International Conference on Biomedical Engineering and Computer Science (ICBECS). Wuhan: IEEE, 2010: 1-4.
［16］王国胤. Rough集理论与知识获取［M］. 西安：西安交通大学出版社, 2001.
［17］谢宏, 程浩忠, 牛东晓. 基于信息熵的粗糙集连续属性离散化算法［J］. 计算机学报, 2005, 28(9):1570-1574.