基于盲源分离的运动想象脑电信号特征提取方法的研究

张立国; 张玉曼; 金梅; 于国辉

doi:10.3969/j.issn.1000-1158.2015.05.19

PDF(13135 KB)

计量学报 ›› 2015, Vol. 36 ›› Issue (5) : 535-539. DOI: 10.3969/j.issn.1000-1158.2015.05.19

基于盲源分离的运动想象脑电信号特征提取方法的研究

张立国¹,张玉曼¹,金梅¹,于国辉²

作者信息 +

A Research on the Method of Motor Imagery EEG Feature Extraction Based on Blind Source Separation

ZHANG Li-guo¹,ZHANG Yu-man¹,JIN Mei¹,YU Guo-hui²

Author information +

文章历史 +

摘要

运动想象脑电信号被广泛应用于脑机接口系统中。针对如何准确有效地提取运动想象脑电信号特征的问题,通过分析运动想象脑电信号时域、频域和头皮空间域的特征,提出了以小波变换为预处理,并利用二阶盲辨识算法和信息论特征提取算法相结合获取的空间滤波器,从时域、频域和头皮空间域对运动想象脑电信号进行特征提取的方法。实验结果表明,采用时域、频域和空间域提取特征的方法性能有明显提高,并且将二阶盲辨识算法和信息论特征提取算法相结合获取的空间滤波器能够反映更真实的大脑源活动。

Abstract

Motor imagery has been widely used in EEG based brain-computer interface systems. In order to extract feature of the motor imagery EEG accurately and efficiently, the feature of the motor imagery EEG in time, frequency and spatial domain is analysed. Then an approach is put forward that extract feature of the motor imagery EEG from time, frequency and spatial domain, with preprocessing of wavelet transforming and using spatial filter obtained from SOBI and ITFE. Experimental results verify that the proposed method has an obvious improvement in feature extraction compared with the other methods, and the spatial filter obtained from SOBI and ITFE can reflect veridical brains activity.

导出引用

张立国,张玉曼,金梅,于国辉. 基于盲源分离的运动想象脑电信号特征提取方法的研究[J]. 计量学报. 2015, 36(5): 535-539 https://doi.org/10.3969/j.issn.1000-1158.2015.05.19

ZHANG Li-guo,ZHANG Yu-man,JIN Mei,YU Guo-hui. A Research on the Method of Motor Imagery EEG Feature Extraction Based on Blind Source Separation[J]. Acta Metrologica Sinica. 2015, 36(5): 535-539 https://doi.org/10.3969/j.issn.1000-1158.2015.05.19

参考文献

［1］赵丽, 郭旭宏. 基于运动想象的脑电信号功率谱估计［J］. 电子测量技术, 2012, 35(6): 81-83.
［2］Schlgl A, Lee F, Bischof H, et al. Characterization of four-class motor imagery EEG data for the BCI-competition 2005［J］. Journal of neural engineering, 2005, 2(4): L14-22.
［3］Hu Dingyin, Li Wei, Chen Xi. Feature extraction of motor imagery EEG signals based on wavelet packet decomposition［C］// IEEE.Complex Medical Engineering (CME), 2011 IEEE/ICME International Conference on., Harbin, Heilongjiang, 2011: 694-697.
［4］Park C, Looney D, Naveed ur Rehman, et al. Classification of motor imagery BCI using multivariate empirical mode decomposition［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering,2013, 21(1): 10-22.
［5］Shanz-Lin Wu, Chun-Wei Wu, Pal N R, et al. Common spatial pattern and linear discriminant analysis for motor imagery classification［C］//IEEE.2013 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB),Singapore,2013: 146-151.
［6］李丽君, 熊冬生, 吴效明. 基于四类运动想象任务的脑电信号识别［J］. 中国组织工程研究与临床康复, 2011, 15(48):9003-9006.
［7］Torkkola K. Feature extraction by non parametric mutual information maximization［J］. The Journal of Machine Learning Research, 2003, 3: 1415-1438.