Three-class Motor Imagery Classification Based on Optimal Sub-band Features of Independent Components_Journal of Biomedical Engineering

Authors：

KANGShasha ¹ , ZHOUBangyan ^1,2 ,  WUXiaopei ^1,2

1. The Key Laboratory of Intelligent Computing and Signal Processing, Anhui University, Hefei 230039, China;
2. Co-Innovation Center for Information Supply & Assurance Technology, Anhui University, Hefei 230601, China;

Corresponding author：

WUXiaopei, Email: wxp2001@ahu.edu.cn

Keywords：

brain-computer interface; independent components analysis; motor imagery; spatial filter

DOI：

10.7507/1001-5515.20160037

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

In the study of the scalp electroencephalogram (EEG)-based brain-computer interface (BCI), individual differences and complex background noise are two main factors which affect the stability of BCI system. For different subjects, therefore, optimization of BCI system parameters is necessary, including the optimal designing of temporal and spatial filters parameters as well as the classifier parameters. In order to improve the accuracy of BCI system, this paper proposes a new BCI information processing method, which combines the optimization design of independent component analysis spatial filter (ICA-SF) with the multiple sub-band features of EEG signals. The four subjects' three-class motor imagery EEG (MI-EEG) data collected in different periods were analyzed with the proposed method. Experimental results revealed that, during the inner and outer cross-validation of single subject as well as the subject-to-subject validation, the proposed multiple sub-band method always had higher average classification accuracy compared to those with single-band method, and the maximum difference could achieve 6.08% and 5.15%, respectively.

Citation： KANGShasha, ZHOUBangyan, WUXiaopei. Three-class Motor Imagery Classification Based on Optimal Sub-band Features of Independent Components. Journal of Biomedical Engineering, 2016, 33(2): 208-215. doi: 10.7507/1001-5515.20160037 Copy

1.	THAKOR N V. In the spotlight:neuroengineering[J]. IEEE Rev Biomed Eng, 2013, 6:24-26.
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(6):801-803, 809.
3.	伏云发, 王越超, 李洪谊, 等.直接脑控机器人接口技术[J].自动化学报, 2012, 38(8):1229-1246.
4.	冯焕清, 江朝晖, 陈强, 等.用于BCI设计的运动想象脑电信号分析方法[C]//中国生物医学工程进展——2007中国生物医学工程联合学术年会论文集:下册, 2007.
5.	YAMAWAKI N, WILKE C, LIU Zhongming, et al. An enhanced time-frequency-spatial approach for motor imagery classification[J]. IEEE Trans Neural Syst Rehabil Eng, 2006, 14(2):250-254.
6.	BLANKERTZ B, TOMIOKA R, LEMM S, et al. Optimizing spatial filters for robust EEG single-trial analysis[J]. IEEE Signal Process Mag, 2008, 25(1):41-56.
7.	LEMM S, BLANKERTZ B, CURIO G, et al. Spatio-spectral filters for improving the classification of single trial EEG[J]. IEEE Trans Biomed Eng, 2005, 52(9):1541-1548.
8.	LEE T W, GIROLAMI M, SEJNOWSKI T J. Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources[J]. Neural Comput, 1999, 11(2):417-441.
9.	GÓRECKA J, WALERJAN P. Artifacts extraction from EEG data using the infomax approach[J]. Biocybernetics and Biomedical Engineering, 2011, 31(4):59-74.
10.	CHUANG C H, LIN Yuanpin, KO L W, et al. Automatic design for Independent component analysis based brain-computer interfacing[C]//35th Annual International Conference of the IEEE EMBS. Osaka:2013:2180-2183.
11.	WINKLER I, BRANDL S, HORN F, et al. Robust artifactual Independent component classification for BCI practitioners[J]. J Neural Eng, 2014, 11(3):035013.
12.	WANG Yijun, WANG Yute, JUNG T P. Translation of EEG spatial filters from resting to motor imagery using independent component analysis[J]. PLoS One, 2012, 7(5):e37665.
13.	GROSSE-WENTRUP M, BUSS M. Multiclass common spatial patterns and information theoretic feature extraction[J]. IEEE Trans Biomed Eng, 2008, 55(8):1991-2000.
14.	LOTTE F, GUAN Cuntai. Regularizing common spatial patterns to improve BCI designs:unified theory and new algorithms[J]. IEEE Trans Biomed Eng, 2011, 58(2):355-362.
15.	杨福生, 洪波, 唐庆玉.独立分量分析及其在生物医学工程中的应用[J].国外医学.生物医学工程分册, 2000, 23(3):129-134, 186.
16.	吴小培, 冯焕清, 周荷琴, 等.独立分量分析及其在脑电信号预处理中的应用[J].北京生物医学工程, 2001, 20(1):35-37, 46.
17.	周颖, 王涛, 冯焕清, 等.运动想象脑电的ERD/ERS分析[J].北京生物医学工程, 2004, 23(4):263-268.
18.	吕俊, 谢胜利, 章晋龙.脑-机接口中基于ERS/ERD的自适应空间滤波算法[J].电子与信息学报, 2009, 31(2):314-318.
19.	TING C M, SALLEH S H, ZAINUDDIN Z M, et al. Spectral estimation of nonstationary EEG using particle filtering with application to event-related desynchronization (ERD)[J]. IEEE Trans Biomed Eng, 2011, 58(2):321-331.
20.	伏云发, 徐保磊, 李永程, 等.基于运动相关皮层电位握力运动模式识别研究[J].自动化学报, 2014, 40(6):1045-1057.
21.	杨福生, 洪波.独立分量分析的原理与应用[M].北京:清华大学出版社, 2006.
22.	吴小培, 周蚌艳, 张磊, 等.运动想象脑-机接口中的ICA滤波器设计[J].生物物理学报, 2014, 30(7):540-554.
23.	KAI Keng-ang, CHIN Z, ZHANG Hai-hong. Filter bank common spatial pattern(FBCSP)in Brain-Computer interface[C]//IEEE International Joint Conference on Neural Networks, 2008:2390-2397.
24.	NOVI Q, GUAN Cun-tai, DAT T H, et al. Sub-band Common Spatial Pattern(SBCSP)for Brain-Computer Interface[C]//Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. Kohala Coast:2007:204-207.
25.	KAWANABE M, VIDAURRE C. Improving BCI performance by modified common spatial patterns with robustly averaged covariance matrices[J]. World Congress on Medical Physics and Biomedical Engineering, 2009:279-282.
26.	李明爱, 刘净瑜, 郝冬梅.基于改进CSP算法的运动想象脑电信号识别方法[J].中国生物医学工程学报, 2009, 28(2):161-165.
27.	LU Jun, MCFARLAND D J, WOLPAW J R. Adaptive laplacian filtering for sensorimotor rhythm-based brain-computer interfaces[J]. J Neural Eng, 2013, 10(1):016002.

1. THAKOR N V. In the spotlight:neuroengineering[J]. IEEE Rev Biomed Eng, 2013, 6:24-26.
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(6):801-803, 809.
3. 伏云发, 王越超, 李洪谊, 等.直接脑控机器人接口技术[J].自动化学报, 2012, 38(8):1229-1246.
4. 冯焕清, 江朝晖, 陈强, 等.用于BCI设计的运动想象脑电信号分析方法[C]//中国生物医学工程进展——2007中国生物医学工程联合学术年会论文集:下册, 2007.
5. YAMAWAKI N, WILKE C, LIU Zhongming, et al. An enhanced time-frequency-spatial approach for motor imagery classification[J]. IEEE Trans Neural Syst Rehabil Eng, 2006, 14(2):250-254.
6. BLANKERTZ B, TOMIOKA R, LEMM S, et al. Optimizing spatial filters for robust EEG single-trial analysis[J]. IEEE Signal Process Mag, 2008, 25(1):41-56.
7. LEMM S, BLANKERTZ B, CURIO G, et al. Spatio-spectral filters for improving the classification of single trial EEG[J]. IEEE Trans Biomed Eng, 2005, 52(9):1541-1548.
8. LEE T W, GIROLAMI M, SEJNOWSKI T J. Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources[J]. Neural Comput, 1999, 11(2):417-441.
9. GÓRECKA J, WALERJAN P. Artifacts extraction from EEG data using the infomax approach[J]. Biocybernetics and Biomedical Engineering, 2011, 31(4):59-74.
10. CHUANG C H, LIN Yuanpin, KO L W, et al. Automatic design for Independent component analysis based brain-computer interfacing[C]//35th Annual International Conference of the IEEE EMBS. Osaka:2013:2180-2183.
11. WINKLER I, BRANDL S, HORN F, et al. Robust artifactual Independent component classification for BCI practitioners[J]. J Neural Eng, 2014, 11(3):035013.
12. WANG Yijun, WANG Yute, JUNG T P. Translation of EEG spatial filters from resting to motor imagery using independent component analysis[J]. PLoS One, 2012, 7(5):e37665.
13. GROSSE-WENTRUP M, BUSS M. Multiclass common spatial patterns and information theoretic feature extraction[J]. IEEE Trans Biomed Eng, 2008, 55(8):1991-2000.
14. LOTTE F, GUAN Cuntai. Regularizing common spatial patterns to improve BCI designs:unified theory and new algorithms[J]. IEEE Trans Biomed Eng, 2011, 58(2):355-362.
15. 杨福生, 洪波, 唐庆玉.独立分量分析及其在生物医学工程中的应用[J].国外医学.生物医学工程分册, 2000, 23(3):129-134, 186.
16. 吴小培, 冯焕清, 周荷琴, 等.独立分量分析及其在脑电信号预处理中的应用[J].北京生物医学工程, 2001, 20(1):35-37, 46.
17. 周颖, 王涛, 冯焕清, 等.运动想象脑电的ERD/ERS分析[J].北京生物医学工程, 2004, 23(4):263-268.
18. 吕俊, 谢胜利, 章晋龙.脑-机接口中基于ERS/ERD的自适应空间滤波算法[J].电子与信息学报, 2009, 31(2):314-318.
19. TING C M, SALLEH S H, ZAINUDDIN Z M, et al. Spectral estimation of nonstationary EEG using particle filtering with application to event-related desynchronization (ERD)[J]. IEEE Trans Biomed Eng, 2011, 58(2):321-331.
20. 伏云发, 徐保磊, 李永程, 等.基于运动相关皮层电位握力运动模式识别研究[J].自动化学报, 2014, 40(6):1045-1057.
21. 杨福生, 洪波.独立分量分析的原理与应用[M].北京:清华大学出版社, 2006.
22. 吴小培, 周蚌艳, 张磊, 等.运动想象脑-机接口中的ICA滤波器设计[J].生物物理学报, 2014, 30(7):540-554.
23. KAI Keng-ang, CHIN Z, ZHANG Hai-hong. Filter bank common spatial pattern(FBCSP)in Brain-Computer interface[C]//IEEE International Joint Conference on Neural Networks, 2008:2390-2397.
24. NOVI Q, GUAN Cun-tai, DAT T H, et al. Sub-band Common Spatial Pattern(SBCSP)for Brain-Computer Interface[C]//Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. Kohala Coast:2007:204-207.
25. KAWANABE M, VIDAURRE C. Improving BCI performance by modified common spatial patterns with robustly averaged covariance matrices[J]. World Congress on Medical Physics and Biomedical Engineering, 2009:279-282.
26. 李明爱, 刘净瑜, 郝冬梅.基于改进CSP算法的运动想象脑电信号识别方法[J].中国生物医学工程学报, 2009, 28(2):161-165.
27. LU Jun, MCFARLAND D J, WOLPAW J R. Adaptive laplacian filtering for sensorimotor rhythm-based brain-computer interfaces[J]. J Neural Eng, 2013, 10(1):016002.

Journal of Biomedical Engineering

Three-class Motor Imagery Classification Based on Optimal Sub-band Features of Independent Components

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content