Research on the feature representation of motor imagery electroencephalogram signal based on individual adaptation_Journal of Biomedical Engineering

Authors：

 PAN Lizheng ^1,2 , DING Yi ¹ , WANG Shunchao ¹ , SONG Aiguo ²

1. School of Mechanical Engineering and Rail Transit, Changzhou University, Changzhou, Jiangsu 213164, P.R. China;
2. Provincial Key Laboratory of Remote Measurement and Control Technology, Southeast University, Nanjing 210096, P.R. China;

Corresponding?author：

PAN Lizheng, Email: panlz@cczu.edu.cn

Keywords：

Motor imagery electroencephalogram; Individual adaptation; Channel selection; Feature representation; Brain-computer interface

DOI：

10.7507/1001-5515.202112023

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Aiming at the problem of low recognition accuracy of motor imagery electroencephalogram signal due to individual differences of subjects, an individual adaptive feature representation method of motor imagery electroencephalogram signal is proposed in this paper. Firstly, based on the individual differences and signal characteristics in different frequency bands, an adaptive channel selection method based on expansive relevant features with label F (ReliefF) was proposed. By extracting five time-frequency domain observation features of each frequency band signal, ReliefF algorithm was employed to evaluate the effectiveness of the frequency band signal in each channel, and then the corresponding signal channel was selected for each frequency band. Secondly, a feature representation method of common space pattern (CSP) based on fast correlation-based filter (FCBF) was proposed (CSP-FCBF). The features of electroencephalogram signal were extracted by CSP, and the best feature sets were obtained by using FCBF to optimize the features, so as to realize the effective state representation of motor imagery electroencephalogram signal. Finally, support vector machine (SVM) was adopted as a classifier to realize identification. Experimental results show that the proposed method in this research can effectively represent the states of motor imagery electroencephalogram signal, with an average identification accuracy of (83.0±5.5)% for four types of states, which is 6.6% higher than the traditional CSP feature representation method. The research results obtained in the feature representation of motor imagery electroencephalogram signal lay the foundation for the realization of adaptive electroencephalogram signal decoding and its application.

Citation： PAN Lizheng, DING Yi, WANG Shunchao, SONG Aiguo. Research on the feature representation of motor imagery electroencephalogram signal based on individual adaptation. Journal of Biomedical Engineering, 2022, 39(6): 1173-1180, 1188. doi: 10.7507/1001-5515.202112023 Copy

1.	Wolpaw J R, Birbaumer N, Mcfarland D J, et al. Brain-computer interfaces for communication and control. Clin Neurophysiol, 2002, 113(6): 767-791.
2.	Herweg A, Gutzeit J, Kleih S, et al. Wheelchair control by elderly participants in a virtual environment with a brain-computer interface (BCI) and tactile stimulation. Biol Psychol, 2016, 121: 117-124.
3.	Saravanakumar D, Reddy M R. A high performance hybrid SSVEP based BCI speller system. Adv Eng Inform, 2019, 42: 100994.
4.	Schloegl A, Lee F, Bischof H, et al. Characterization of four-class motor imagery EEG data for the BCI-competition 2005. J Neural Eng, 2005, 2(4): 14-22.
5.	Hill N J, Lal T N, Schroeder M, et al. Classifying event-related desynchronization in EEG, ECoG and MEG signals// The 28th Annual Symposium of the Gernan Association for Pattern Recognition, Berlin: Springer Berlin Heidelberg, 2006, 4174: 404-413.
6.	Singh A, Hussain A A, Lal S, et al. A comprehensive review on critical issues and possible solutions of motor imagery based electroencephalography brain-computer interface. Sensors, 2021, 21(6): 2173.
7.	Chu Yaqi, Zhao Xingang, Zou Yijun, et al. Decoding multiclass motor imagery EEG from the same upper limb by combining riemannian geometry features and partial least squares regression. J Neural Eng, 2020, 17(4): 046029.
8.	Das A K, Suresh S. An effect-size based channel selection algorithm for mental task classification in brain computer interface// The IEEE international conference on systems, man, and cybernetics, Hongkong: IEEE, 2015: 3140-3145.
9.	Qi F F, Wu W, Yu Z L, et al. Spatio temporal-filtering-based channel selection for single-trial EEG classification. IEEE T Cybernetics, 2021, 51(2): 558-567.
10.	Park Y, Chung W. Selective feature generation method based on time domain parameters and correlation coefficients for filter-bank- CSP BCI systems. Sensors, 2019, 19(17): 3769.
11.	付榮榮, 田永勝, 鮑甜怡. 基于稀疏共空間模式和Fisher判別的單次運動想象腦電信號識別方法. 生物醫學工程學雜志, 2019, 36(6): 911-915, 923.
12.	駱金晨, 姜月, 胡秀枋, 等. 基于多特征融合的多分類運動想象腦電信號識別研究. 生物信息學, 2020, 18(3): 176-185.
13.	郜東瑞, 周暉, 馮李逍, 等. 基于特征融合和粒子群優化算法的運動想象腦電信號識別方法. 電子科技大學學報, 2021, 50(3): 467-475.
14.	汲繼躍, 佘青山, 張啟中, 等. 最優區域共空間模式的運動想象腦電信號分類方法. 傳感技術學報, 2020, 33(1): 34-39.
15.	Goldberger A L, Amaral L A N, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet-components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): 215-220.
16.	Schalk G, Mcfarland D J, Hinterberger T, et al. BCI2000: a general-purpose, brain-computer interface (BCI) system. IEEE T Bio-Med Eng, 2004, 51(6): 1034-1043.
17.	Varsehi H, Firoozabadi S M P. An EEG channel selection method for motor imagery based brain-computer interface and neurofeedback using Granger causality. Neural Networks, 2021, 133: 193-206.
18.	Lun Xiangmin, Yu Zhenglin, Chen Tao, et al. A simplified CNN classification method for MI-EEG via the electrode pairs signals. Front Hum Neurosci, 2020, 14: 338.
19.	Hou Y M, Zhou L, Jia S Y, et al. A novel approach of decoding EEG four-class motor imagery tasks via scout ESI and CNN. J Neural Eng, 2020, 17(1): 016048.
20.	徐欣, 王娜. 四類運動想象腦電信號的特征提取與分類. 南京郵電大學學報: 自然科學版, 2017, 37(6): 18-22.
21.	馬滿振, 郭理彬, 蘇奎峰. 基于多類運動想象任務的EEG信號分類研究. 計算機測量與控制, 2017, 25(10): 232-239.
22.	Robnik-Sikonja M, Kononenko I. Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn, 2003, 53(1-2): 23-69.
23.	張小內, 翟文鵬, 侯惠讓, 等. 基于ReliefF-Pearson的嗅覺腦電通道選擇. 電子信息學報, 2021, 43(7): 2032-2037.
24.	Mishuhina V, Jiang Xudong. Feature weighting and regularization of common spatial patterns in EEG-based motor imagery BCI. IEEE Signal Proc Let, 2018, 25(6): 783-787.
25.	褚亞奇, 朱波, 趙新剛, 等. 基于時空特征學習卷積神經網絡的運動想象腦電解碼方法. 生物醫學工程學雜志, 2021, 38(1): 1-9.
26.	Fu Rongrong, Han Mengmeng, Tian Yongsheng, et al. Improvement motor imagery EEG classification based on sparse common spatial pattern and regularized discriminant analysis. J Neurosci Meth, 2020, 343: 108833.
27.	Luo Jing, Gao Xing, Zhu Xiaobei, et al. Motor imagery EEG classification based on ensemble support vector learning. Comput Meth Prog Bio, 2020, 193: 105464.
28.	Tolic M, Jovic F. Classification of wavelet transformed EEG signals with neural network for imagined mental and motor tasks. Kinesiology, 2013, 45(1) :130-138.
29.	Kim Y, Ryu J, Kim K K, et al. Motor imagery classification using mu and beta rhythms of EEG with strong uncorrelating transform based complex common spatial patterns. Comput Intel Neurosc. 2016, 2016: 1489692.
30.	Dose H, Moller J S, Lversen H K, et al. An end-to-end deep learning approach to MI-EEG signal classification for BCIs. Expert Syst Appl, 2018, 114: 532-542.

1. Wolpaw J R, Birbaumer N, Mcfarland D J, et al. Brain-computer interfaces for communication and control. Clin Neurophysiol, 2002, 113(6): 767-791.
2. Herweg A, Gutzeit J, Kleih S, et al. Wheelchair control by elderly participants in a virtual environment with a brain-computer interface (BCI) and tactile stimulation. Biol Psychol, 2016, 121: 117-124.
3. Saravanakumar D, Reddy M R. A high performance hybrid SSVEP based BCI speller system. Adv Eng Inform, 2019, 42: 100994.
4. Schloegl A, Lee F, Bischof H, et al. Characterization of four-class motor imagery EEG data for the BCI-competition 2005. J Neural Eng, 2005, 2(4): 14-22.
5. Hill N J, Lal T N, Schroeder M, et al. Classifying event-related desynchronization in EEG, ECoG and MEG signals// The 28th Annual Symposium of the Gernan Association for Pattern Recognition, Berlin: Springer Berlin Heidelberg, 2006, 4174: 404-413.
6. Singh A, Hussain A A, Lal S, et al. A comprehensive review on critical issues and possible solutions of motor imagery based electroencephalography brain-computer interface. Sensors, 2021, 21(6): 2173.
7. Chu Yaqi, Zhao Xingang, Zou Yijun, et al. Decoding multiclass motor imagery EEG from the same upper limb by combining riemannian geometry features and partial least squares regression. J Neural Eng, 2020, 17(4): 046029.
8. Das A K, Suresh S. An effect-size based channel selection algorithm for mental task classification in brain computer interface// The IEEE international conference on systems, man, and cybernetics, Hongkong: IEEE, 2015: 3140-3145.
9. Qi F F, Wu W, Yu Z L, et al. Spatio temporal-filtering-based channel selection for single-trial EEG classification. IEEE T Cybernetics, 2021, 51(2): 558-567.
10. Park Y, Chung W. Selective feature generation method based on time domain parameters and correlation coefficients for filter-bank- CSP BCI systems. Sensors, 2019, 19(17): 3769.
11. 付榮榮, 田永勝, 鮑甜怡. 基于稀疏共空間模式和Fisher判別的單次運動想象腦電信號識別方法. 生物醫學工程學雜志, 2019, 36(6): 911-915, 923.
12. 駱金晨, 姜月, 胡秀枋, 等. 基于多特征融合的多分類運動想象腦電信號識別研究. 生物信息學, 2020, 18(3): 176-185.
13. 郜東瑞, 周暉, 馮李逍, 等. 基于特征融合和粒子群優化算法的運動想象腦電信號識別方法. 電子科技大學學報, 2021, 50(3): 467-475.
14. 汲繼躍, 佘青山, 張啟中, 等. 最優區域共空間模式的運動想象腦電信號分類方法. 傳感技術學報, 2020, 33(1): 34-39.
15. Goldberger A L, Amaral L A N, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet-components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): 215-220.
16. Schalk G, Mcfarland D J, Hinterberger T, et al. BCI2000: a general-purpose, brain-computer interface (BCI) system. IEEE T Bio-Med Eng, 2004, 51(6): 1034-1043.
17. Varsehi H, Firoozabadi S M P. An EEG channel selection method for motor imagery based brain-computer interface and neurofeedback using Granger causality. Neural Networks, 2021, 133: 193-206.
18. Lun Xiangmin, Yu Zhenglin, Chen Tao, et al. A simplified CNN classification method for MI-EEG via the electrode pairs signals. Front Hum Neurosci, 2020, 14: 338.
19. Hou Y M, Zhou L, Jia S Y, et al. A novel approach of decoding EEG four-class motor imagery tasks via scout ESI and CNN. J Neural Eng, 2020, 17(1): 016048.
20. 徐欣, 王娜. 四類運動想象腦電信號的特征提取與分類. 南京郵電大學學報: 自然科學版, 2017, 37(6): 18-22.
21. 馬滿振, 郭理彬, 蘇奎峰. 基于多類運動想象任務的EEG信號分類研究. 計算機測量與控制, 2017, 25(10): 232-239.
22. Robnik-Sikonja M, Kononenko I. Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn, 2003, 53(1-2): 23-69.
23. 張小內, 翟文鵬, 侯惠讓, 等. 基于ReliefF-Pearson的嗅覺腦電通道選擇. 電子信息學報, 2021, 43(7): 2032-2037.
24. Mishuhina V, Jiang Xudong. Feature weighting and regularization of common spatial patterns in EEG-based motor imagery BCI. IEEE Signal Proc Let, 2018, 25(6): 783-787.
25. 褚亞奇, 朱波, 趙新剛, 等. 基于時空特征學習卷積神經網絡的運動想象腦電解碼方法. 生物醫學工程學雜志, 2021, 38(1): 1-9.
26. Fu Rongrong, Han Mengmeng, Tian Yongsheng, et al. Improvement motor imagery EEG classification based on sparse common spatial pattern and regularized discriminant analysis. J Neurosci Meth, 2020, 343: 108833.
27. Luo Jing, Gao Xing, Zhu Xiaobei, et al. Motor imagery EEG classification based on ensemble support vector learning. Comput Meth Prog Bio, 2020, 193: 105464.
28. Tolic M, Jovic F. Classification of wavelet transformed EEG signals with neural network for imagined mental and motor tasks. Kinesiology, 2013, 45(1) :130-138.
29. Kim Y, Ryu J, Kim K K, et al. Motor imagery classification using mu and beta rhythms of EEG with strong uncorrelating transform based complex common spatial patterns. Comput Intel Neurosc. 2016, 2016: 1489692.
30. Dose H, Moller J S, Lversen H K, et al. An end-to-end deep learning approach to MI-EEG signal classification for BCIs. Expert Syst Appl, 2018, 114: 532-542.

Journal of Biomedical Engineering

Research on the feature representation of motor imagery electroencephalogram signal based on individual adaptation

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content