基于共空域频谱模式的少通道运动想象分类

doi:10.3969/j.issn.0258-8021. 2013. 05.07

摘要
图/表
参考文献
相关文章 (6)

全文: PDF (783 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对少通道脑电数据采集如2～3通道的情况下，利用每个通道信号的2～10个延时来扩展EEG信号的通道数，然后再利用共空域模式CSP算法进行特征抽取。针对每个通道信号的延时选取问题，提出利用非参数化估计互信息熵的方法来选择最佳个数的延时因子。应用多个时延的共空域频谱模式（CSSP）算法，对2008年BCI竞赛数据集IIb中的9个受试者以及实验室采集的13个受试者的想象运动数据集分析，结果表明可以使两个数据集的平均Kappa系数分别达到0.6与0.34。该方法可以依据8～30 Hz内频段的区分度自动优化权重系数，从而提高少通道数目下想象运动的分类正确率。

	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
	孟建军盛鑫军^* 姚林朱向阳

关键词 ：脑机接口, 共空域频谱模式, 特征选择, 信息熵

Abstract：Targeting to the deficient recording condition with 2～3 channels, a novel method, multiple timedelayed common spatial spectral pattern (CSSP), was proposed in this paper. In this approach, 2～10 timedelayed Electroencephalogram (EEG) signals for each channel were used to expand the number of EEG channels and then common spatial pattern (CSP) was used to extract the features. Mutual information criterion was applied to choose the optimal number of timedelayed signals. The proposed method was tested by the IIb datasets of 9 subjects in BCI Competition 2008 and datasets of 13 subjects in our experiments. The average Kappa coefficients for the two datasets are 0.6 and 0.34, respectively. This method automatically weights the importance of frequency in 8～30 Hz and enhances the classification accuracy in the case of deficient recording consequently.

Key words： braincomputer interface (BCI) common spatial spectral pattern (CSSP) feature selection mutual information

基金资助:国家重点基础研究发展计划（973计划）（2011CB013305）；上海市科委重点项目（11JC140600）；国家重点实验室基金重点项目（MSVZD201204）

引用本文:

孟建军盛鑫军^* 姚林朱向阳. 基于共空域频谱模式的少通道运动想象分类[J]. 中国生物医学工程学报, 2013, 32(5): 553-561.
MENG Jian Jun SHENG Xin Jun^* YAO Lin ZHU Xiang Yang. Common Spatial Spectral Pattern for Motor Imagery Tasks in Small Channel Configuration. journal1, 2013, 32(5): 553-561.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2013. 05.07 或 http://cjbme.csbme.org/CN/Y2013/V32/I5/553

［1］Krusienski D, GrosseWentrup M, Galan F, et al. Critical issues in stateofart braincomputer interface signal processing ［J］. Journal of Neural Engineering, 2011, 8(2): 025002.
［2］高上凯. 浅谈脑-机接口的发展现状与挑战［J］. 中国生物医学工程学报, 2007, 26 (6)：801-803.
［3］尧德中，刘铁军，雷旭，等. 基于脑电的脑-机接口：关键技术和应用前景［J］. 电子科技大学学报, 2009, 38(5)：550-554.
［4］Pfurtscheller G, Neuper C. Eventrelated synchronization of mu rhythm in the EEG over the cortical hand area in man ［J］. Neuroscience Letters, 1994, 174(1):93–96.
［5］Ramoser H, MullerGerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement ［J］. IEEE Transactions on Rehabilitation Engineering, 2000, 8(4):441–446.
［6］Lemm S, Blankertz B, Curio G, et al. Spatiospectral filters for improving the classification of single trial EEG ［J］. IEEE Transactions on Biomedical Engineering, 2005, 52(9):1541-1548.
［7］Wang Haixian, Tang Qin, Zheng Wenming. L1-normbased common spatial patterns ［J］. IEEE Transactions on Biomedical Engineering, 2012, 〖STHZ〗59(3): 653-662.
［8］Lotte F, Guan C. Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms ［J］, IEEE Transactions on Biomedical Engineering, 2011, 58(2): 355-362.
［9］Broomhead D, King G. Extracting qualitative dynamics from experimental data ［J］. Physica D, 1986, 20(2):217-236.
［10］Fukunaga K. Introduction to Statistical Pattern Recognition ［M］. Academic Press, 1990:31-35.
［11］Blankertz B, Tomioka R, Lemm S, et al. Optimizing spatial filters for Robust EEG singletrial analysis ［J］. IEEE Signal Processing Magazine, 2008, 25(1):41–56.
［12］Dornhege G, Blankertz B, Krauledat B, et al. Combined optimization of spatial and temproral filters for improving braincomputer interfacing ［J］. IEEE Transactions on Biomedical Engineering, 2006, 53(11):2274-2281.
［13］Ang K, Chin Z, Zhang H, et al. Mutual informationbased selection of optimal spatialtemporal patterns for singletrial EEGbased BCIs ［J］. Pattern Recognition, 2012, 45(6) : 2137- 2144.
［14］Zhang H, Chin Z, Ang K, et al. Optimum spatiospectral filtering network for braincomputer interface ［J］. IEEE Transactions on Neural Networks, 2011, 22(1): 52-63.［15］Duda R, Hart P, Stork D, Pattern classification ［M］// Maximumlikelihood and Bayesian Parameter Estimation. New York: John Wiley & Sons, 2001:117-124.
［16］BCI Competition IV. ［EB/OL］ http:// http://www.bbci.de/competition/iv/desc_2b.pdf, 2008-04-16/2013-01-27.
［17］Meng Jianjun, Huang Gan, Zhang Dingguo, et al. Optimizing spatial spectral patterns jointly with channel configuration for braincomputer interface ［J］. Neurocomputing, 2013, 104: 115-126.