Recognition of motor imagery electroencephalogram based on flicker noise spectroscopy and weighted filter bank common spatial pattern_Journal of Biomedical Engineering

Authors：

 FEI Keling ¹ , CAI Xiaoxian ¹ , CHEN Shunzhi ¹ , PAN Lizheng ¹ , WANG Wei ²

1. School of Mechanical Engineering and Rail Transit, Changzhou University, Changzhou, Jiangsu 213164, P.R. China;
2. School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, P.R. China;

Corresponding author：

FEI Keling, Email: feikeling@cczu.edu.cn

Keywords：

Flicker noise spectroscopy; Common spatial pattern; Feature selection; Electroencephalogram signal recognition; Brain-computer interface

DOI：

10.7507/1001-5515.202302020

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Due to the high complexity and subject variability of motor imagery electroencephalogram, its decoding is limited by the inadequate accuracy of traditional recognition models. To resolve this problem, a recognition model for motor imagery electroencephalogram based on flicker noise spectrum (FNS) and weighted filter bank common spatial pattern (wFBCSP) was proposed. First, the FNS method was used to analyze the motor imagery electroencephalogram. Using the second derivative moment as structure function, the ensued precursor time series were generated by using a sliding window strategy, so that hidden dynamic information of transition phase could be captured. Then, based on the characteristic of signal frequency band, the feature of the transition phase precursor time series and reaction phase series were extracted by wFBCSP, generating features representing relevant transition and reaction phase. To make the selected features adapt to subject variability and realize better generalization, algorithm of minimum redundancy maximum relevance was further used to select features. Finally, support vector machine as the classifier was used for the classification. In the motor imagery electroencephalogram recognition, the method proposed in this study yielded an average accuracy of 86.34%, which is higher than the comparison methods. Thus, our proposed method provides a new idea for decoding motor imagery electroencephalogram.

Citation： FEI Keling, CAI Xiaoxian, CHEN Shunzhi, PAN Lizheng, WANG Wei. Recognition of motor imagery electroencephalogram based on flicker noise spectroscopy and weighted filter bank common spatial pattern. Journal of Biomedical Engineering, 2023, 40(6): 1126-1134. doi: 10.7507/1001-5515.202302020 Copy

1.	Clerc M. Brain computer interfaces, principles and practise. Biomed Eng Online, 2013, 12: 22.
2.	Xu S, Zhu L, Kong W, et al. A novel classification method for EEG-based motor imagery with narrow band spatial filters and deep convolutional neural network. Cogn Neurodyn, 2022, 16(2): 379-389.
3.	Martens S M, Leiva J M. A generative model approach for decoding in the visual event-related potential-based brain-computer interface speller. J Neural Eng, 2010, 7(2): 26003.
4.	Saravanakumar D, Reddy M R. A high performance hybrid SSVEP based BCI speller system. Advanced Engineering Informatics, 2019, 42: 100994.
5.	Schlögl 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): L14.
6.	Rong Yuying, Wu Xiaojun, Zhang Yumei. Classification of motor imagery electroencephalography signals using continuous small convolutional neural network. Int J Imaging Syst Technol, 2020, 30(3): 653-659.
7.	田贵鑫, 陈俊杰, 丁鹏, 等. 脑机接口中运动想象的执行与能力的评估和提高方法. 生物医学工程学杂志, 2021, 38(3): 434-446.
8.	Pfurtscheller G, Neuper C, Ramoser H, et al. Visually guided motor imagery activates sensorimotor areas in humans. Neurosci Lett, 1999, 269(3): 153-156.
9.	Pfurtscheller G, Neuper C, Schlögl A, et al. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans Rehabil Eng, 1998, 6(3): 316-325.
10.	Aggarwal S, Chugh N. Signal processing techniques for motor imagery brain computer interface: a review. Array, 2019, 1-2: 100003.
11.	Amin H U, Malik A S, Ahmad R F, et al. Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques. Australas Phys Eng Sci Med, 2015, 38(1): 139-149.
12.	Subasi A. Selection of optimal AR spectral estimation method for EEG signals using Cramer-Rao bound. Comput Biol Med, 2007, 37(2): 183-194.
13.	Ang K K, Chin Z Y, Wang C, et al. Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci, 2012, 6: 39.
14.	Khan M E, Dutt D N. An expectation-maximization algorithm based Kalman smoother approach for event-related desynchronization (ERD) estimation from EEG. IEEE Trans Biol Med Eng, 2007, 54(7): 1191-1198.
15.	孟明, 尹旭, 高云园, 等. 运动想象脑电的块选择共空间模式特征提取. 控制理论与应用, 2021, 38(3): 301-308.
16.	Huang Y, Jin J, Xu R, et al. Multi-view optimization of time-frequency common spatial patterns for brain-computer interfaces. J Neurosci Methods, 2022, 365: 109378.
17.	孙会文, 伏云发, 熊馨, 等. 基于HHT运动想象脑电模式识别研究. 自动化学报, 2015, 41(9): 1686-1692.
18.	谷学静, 位占锋, 刘海望, 等. 基于小波包和串并行CNN的脑电信号分类. 微电子学与计算机, 2021, 38(6): 60-65.
19.	唐贤伦, 李伟, 马伟昌, 等. 基于条件经验模式分解和串并行CNN的脑电信号识别. 电子与信息学报, 2020, 42(4): 1041-1048.
20.	Dose H, Møller J S, Iversen H K, et al. An end-to-end deep learning approach to MI-EEG signal classification for BCIs. Expert Systems with Applications, 2018, 114: 532-542.
21.	张玮, 赵永虹, 邱桃荣. 基于注意力机制和深度学习的运动想象脑电信号分类方法. 南京大学学报(自然科学), 2022, 58(1): 29-37.
22.	Broniec A. The FNS-based analysis of precursors and cross-correlations in EEG signal related to an imaginary motor task. Biomedical Signal Processing and Control, 2021, 64: 102315.
23.	Tangermann M, Muller K R, Aertsen A, et al. Review of the BCI competition IV. Front Neurosci, 2012, 6: 55.
24.	Blanco-Diaz C F, Antelis J M, Ruiz-Olaya A F. Comparative analysis of spectral and temporal combinations in CSP-based methods for decoding hand motor imagery tasks. J Neurosci Methods, 2022, 371: 109495.
25.	Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell, 2005, 27(8): 1226-1238.
26.	郜东瑞, 周晖, 冯李逍, 等. 基于特征融合和粒子群优化算法的运动想象脑电信号识别方法. 电子科技大学学报, 2021, 50(3): 467-475.
27.	Schölkopf B, Smola A. Learning with kernels: support vector machines, regularization, optimization, and beyond. IEEE Trans Neural Net, 2005, 16(3): 781.
28.	Brabanter K D, Karsmakers P, Ojeda F, et al. LS-SVMlab Toolbox User’s Guide version 1.8. ESAT-SISTA Technical Report, 2011: 10-146.
29.	Tang Xianlun, Zhang Na, Zhou Jialin, et al. Hidden-layer visible deep stacking network optimized by PSO for motor imagery EEG recognition. Neurocomputing, 2017, 234: 1-10.
30.	Thomas K P, Guan C, Lau C T, et al. A new discriminative common spatial pattern method for motor imagery brain computer interfaces. IEEE Trans Biomed Eng, 2009, 56: 2730-2733.
31.	Yang J, Gao S, Shen T. A two-branch CNN fusing temporal and frequency features for motor imagery EEG decoding. Entropy, 2022, 24(3): 376.
32.	Zhao H, Zheng Q, Ma K, et al. Deep representation-based domain adaptation for nonstationary EEG classification. IEEE Trans Neural Netw Learn Syst, 2021, 32(2): 535-545.

1. Clerc M. Brain computer interfaces, principles and practise. Biomed Eng Online, 2013, 12: 22.
2. Xu S, Zhu L, Kong W, et al. A novel classification method for EEG-based motor imagery with narrow band spatial filters and deep convolutional neural network. Cogn Neurodyn, 2022, 16(2): 379-389.
3. Martens S M, Leiva J M. A generative model approach for decoding in the visual event-related potential-based brain-computer interface speller. J Neural Eng, 2010, 7(2): 26003.
4. Saravanakumar D, Reddy M R. A high performance hybrid SSVEP based BCI speller system. Advanced Engineering Informatics, 2019, 42: 100994.
5. Schlögl 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): L14.
6. Rong Yuying, Wu Xiaojun, Zhang Yumei. Classification of motor imagery electroencephalography signals using continuous small convolutional neural network. Int J Imaging Syst Technol, 2020, 30(3): 653-659.
7. 田贵鑫, 陈俊杰, 丁鹏, 等. 脑机接口中运动想象的执行与能力的评估和提高方法. 生物医学工程学杂志, 2021, 38(3): 434-446.
8. Pfurtscheller G, Neuper C, Ramoser H, et al. Visually guided motor imagery activates sensorimotor areas in humans. Neurosci Lett, 1999, 269(3): 153-156.
9. Pfurtscheller G, Neuper C, Schlögl A, et al. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans Rehabil Eng, 1998, 6(3): 316-325.
10. Aggarwal S, Chugh N. Signal processing techniques for motor imagery brain computer interface: a review. Array, 2019, 1-2: 100003.
11. Amin H U, Malik A S, Ahmad R F, et al. Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques. Australas Phys Eng Sci Med, 2015, 38(1): 139-149.
12. Subasi A. Selection of optimal AR spectral estimation method for EEG signals using Cramer-Rao bound. Comput Biol Med, 2007, 37(2): 183-194.
13. Ang K K, Chin Z Y, Wang C, et al. Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci, 2012, 6: 39.
14. Khan M E, Dutt D N. An expectation-maximization algorithm based Kalman smoother approach for event-related desynchronization (ERD) estimation from EEG. IEEE Trans Biol Med Eng, 2007, 54(7): 1191-1198.
15. 孟明, 尹旭, 高云园, 等. 运动想象脑电的块选择共空间模式特征提取. 控制理论与应用, 2021, 38(3): 301-308.
16. Huang Y, Jin J, Xu R, et al. Multi-view optimization of time-frequency common spatial patterns for brain-computer interfaces. J Neurosci Methods, 2022, 365: 109378.
17. 孙会文, 伏云发, 熊馨, 等. 基于HHT运动想象脑电模式识别研究. 自动化学报, 2015, 41(9): 1686-1692.
18. 谷学静, 位占锋, 刘海望, 等. 基于小波包和串并行CNN的脑电信号分类. 微电子学与计算机, 2021, 38(6): 60-65.
19. 唐贤伦, 李伟, 马伟昌, 等. 基于条件经验模式分解和串并行CNN的脑电信号识别. 电子与信息学报, 2020, 42(4): 1041-1048.
20. Dose H, Møller J S, Iversen H K, et al. An end-to-end deep learning approach to MI-EEG signal classification for BCIs. Expert Systems with Applications, 2018, 114: 532-542.
21. 张玮, 赵永虹, 邱桃荣. 基于注意力机制和深度学习的运动想象脑电信号分类方法. 南京大学学报(自然科学), 2022, 58(1): 29-37.
22. Broniec A. The FNS-based analysis of precursors and cross-correlations in EEG signal related to an imaginary motor task. Biomedical Signal Processing and Control, 2021, 64: 102315.
23. Tangermann M, Muller K R, Aertsen A, et al. Review of the BCI competition IV. Front Neurosci, 2012, 6: 55.
24. Blanco-Diaz C F, Antelis J M, Ruiz-Olaya A F. Comparative analysis of spectral and temporal combinations in CSP-based methods for decoding hand motor imagery tasks. J Neurosci Methods, 2022, 371: 109495.
25. Peng H, Long F, Ding C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell, 2005, 27(8): 1226-1238.
26. 郜东瑞, 周晖, 冯李逍, 等. 基于特征融合和粒子群优化算法的运动想象脑电信号识别方法. 电子科技大学学报, 2021, 50(3): 467-475.
27. Schölkopf B, Smola A. Learning with kernels: support vector machines, regularization, optimization, and beyond. IEEE Trans Neural Net, 2005, 16(3): 781.
28. Brabanter K D, Karsmakers P, Ojeda F, et al. LS-SVMlab Toolbox User’s Guide version 1.8. ESAT-SISTA Technical Report, 2011: 10-146.
29. Tang Xianlun, Zhang Na, Zhou Jialin, et al. Hidden-layer visible deep stacking network optimized by PSO for motor imagery EEG recognition. Neurocomputing, 2017, 234: 1-10.
30. Thomas K P, Guan C, Lau C T, et al. A new discriminative common spatial pattern method for motor imagery brain computer interfaces. IEEE Trans Biomed Eng, 2009, 56: 2730-2733.
31. Yang J, Gao S, Shen T. A two-branch CNN fusing temporal and frequency features for motor imagery EEG decoding. Entropy, 2022, 24(3): 376.
32. Zhao H, Zheng Q, Ma K, et al. Deep representation-based domain adaptation for nonstationary EEG classification. IEEE Trans Neural Netw Learn Syst, 2021, 32(2): 535-545.

Journal of Biomedical Engineering

Recognition of motor imagery electroencephalogram based on flicker noise spectroscopy and weighted filter bank common spatial pattern

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content