Optimal channel-based sparse time-frequency blocks common spatial pattern feature extraction method for motor imagery classification

Xu Yin; Ming Meng; Qingshan She; Yunyuan Gao; Zhizeng Luo; Xu Yin; Ming Meng; Qingshan She; Yunyuan Gao; Zhizeng Luo

doi:10.3934/mbe.2021213

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 4: 4247-4263. doi: 10.3934/mbe.2021213

Previous Article Next Article

Research article

Optimal channel-based sparse time-frequency blocks common spatial pattern feature extraction method for motor imagery classification

1.
Institute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou 310018, China
2.
Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou 310018, China

Received: 21 March 2021 Accepted: 10 May 2021 Published: 17 May 2021

Common spatial pattern (CSP) as a spatial filtering method has been most widely applied to electroencephalogram (EEG) feature extraction to classify motor imagery (MI) in brain-computer interface (BCI) applications. The effectiveness of CSP is determined by the quality of interception in a specific time window and frequency band. Although numerous algorithms have been designed to optimize CSP by splitting the EEG data with a sliding time window and dividing the frequency bands with a set of band-pass filters, simultaneously. However, they did not consider the drawbacks of the rapid increase in data volume and feature dimensions brought about by this method, which would reduce the classification accuracy and calculation efficiency of the model. Therefore, we propose an optimal channel-based sparse time-frequency blocks common spatial pattern (OCSB-CSP) feature extraction method to improve the model classification accuracy and computational efficiency. Comparative experiments on two public EEG datasets show that the proposed method can quickly select significant time-frequency blocks and improve classification performance. The average classification accuracies are higher than those of other winners' methods, providing a new idea for the improvement of BCI applications.
- brain-computer interface,
- electroencephalogram,
- motor imagery,
- common spatial pattern
Citation: Xu Yin, Ming Meng, Qingshan She, Yunyuan Gao, Zhizeng Luo. Optimal channel-based sparse time-frequency blocks common spatial pattern feature extraction method for motor imagery classification[J]. Mathematical Biosciences and Engineering, 2021, 18(4): 4247-4263. doi: 10.3934/mbe.2021213

Related Papers:

Abstract

Common spatial pattern (CSP) as a spatial filtering method has been most widely applied to electroencephalogram (EEG) feature extraction to classify motor imagery (MI) in brain-computer interface (BCI) applications. The effectiveness of CSP is determined by the quality of interception in a specific time window and frequency band. Although numerous algorithms have been designed to optimize CSP by splitting the EEG data with a sliding time window and dividing the frequency bands with a set of band-pass filters, simultaneously. However, they did not consider the drawbacks of the rapid increase in data volume and feature dimensions brought about by this method, which would reduce the classification accuracy and calculation efficiency of the model. Therefore, we propose an optimal channel-based sparse time-frequency blocks common spatial pattern (OCSB-CSP) feature extraction method to improve the model classification accuracy and computational efficiency. Comparative experiments on two public EEG datasets show that the proposed method can quickly select significant time-frequency blocks and improve classification performance. The average classification accuracies are higher than those of other winners' methods, providing a new idea for the improvement of BCI applications.

References

[1]	R. Krepki, B. Blankertz, G. Curio, K. R. Müller, The Berlin Brain-Computer Interface (BBCI)-towards a new communication channel for online control in gaming applications, Multimedia Tools Appl., 33 (2007), 73-90.
[2]	D. Saravanakumar, M. R. Reddy, A high performance hybrid SSVEP based BCI speller system, Adv. Eng. Inf., 42 (2019), 100994-101003. doi: 10.1016/j.aei.2019.100994
[3]	L. Shao, L. Y. Zhang, A. N. Belkacem, Y. M. Zhang, X. Q. Chen, J. Li, et al., EEG-Controlled Wall-Crawling Cleaning Robot Using SSVEP-Based Brain-Computer Interface, J. Healthcare Eng., 2020 (2020), 1-11.
[4]	Z. Ma, Z. X. Xie, T. S. Qiu, J. Cheng, Driving event-related potential-based speller by localized posterior activities: An offline study, Math. Biosci. Eng., 17 (2020), 789-801. doi: 10.3934/mbe.2020041
[5]	S. M. M. Martens, J. M. Leiva, A generative model approach for decoding in the visual event-related potential-based brain-computer interface speller, J. Neural Eng., 7 (2010), 26003-26012. doi: 10.1088/1741-2560/7/2/026003
[6]	I. Majidov, T. Whangbo, Efficient Classification of Motor Imagery Electroencephalography Signals Using Deep Learning Methods, Sensors, 19 (2019), 1736-1748. doi: 10.3390/s19071736
[7]	Y. Y. Rong, X. J. Wu, Y. M. Zhang, Classification of motor imagery electroencephalography signals using continuous small convolutional neural network, Int. J. Imaging Syst. Technol., 30 (2020), 653-659. doi: 10.1002/ima.22405
[8]	A. Schlogl, F. Lee, H. Bischof, G. Pfurtscheller, Characterization of four-class motor imagery EEG data for the BCI-competition 2005, J. Neural Eng., 2 (2005), 14-22. doi: 10.1088/1741-2560/2/4/L02
[9]	F. Cincotti, D. Mattia, C. Babiloni, F. Carducci, S. Salinari, L. Bianchi, et al., The use of EEG modifications due to motor imagery for brain-computer interfaces, IEEE Trans. Neural Syst. Rehabil. Eng., 11 (2003), 131-133. doi: 10.1109/TNSRE.2003.814455
[10]	F. V. Alvarez, R. R. Angevin, L. S. Sauer, S. S. Ros, Audio-cued motor imagery-based brain-computer interface: Navigation through virtual and real environments, Neurocomputing, 121 (2013), 89-98. doi: 10.1016/j.neucom.2012.11.038
[11]	H. Yuan, B. He, Brain-Computer Interfaces Using Sensorimotor Rhythms: Current State and Future Perspectives, IEEE Trans. Biomed. Eng., 61 (2014), 1425-1435. doi: 10.1109/TBME.2014.2312397
[12]	A. Dietrich, R. Kanso, A Review of EEG, ERP, and Neuroimaging Studies of Creativity and Insight, Psychol. Bull., 136 (2010), 822-848.
[13]	V. Sakkalis, Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEG, Comput. Biol. Med., 41 (2011), 1110-1117. doi: 10.1016/j.compbiomed.2011.06.020
[14]	T. Aflalo, S. Kellis, C. Klaes, B. Lee, Y. Shi, K. Pejsa, et al., Decoding motor imagery from the posterior parietal cortex of a tetraplegic human, Science, 348 (2015), 906-910. doi: 10.1126/science.aaa5417
[15]	S. Hetu, M. Gregoire, A. Saimpont, M. P. Coll, F. Eugene, P. E. Michon, et al., The neural network of motor imagery: An ALE meta-analysis, Neurosci. Biobehav. Rev., 37 (2013), 930-949. doi: 10.1016/j.neubiorev.2013.03.017
[16]	H. Ramoser, J. M. Gerking, G. Pfurtscheller, Optimal spatial filtering of single trial EEG during imagined hand movement, IEEE Trans. Rehabil. Eng., 8 (2000), 441-446. doi: 10.1109/86.895946
[17]	J. Feng, E. Yin, J. Jin, R. Saab, I. Daly, X. Wang, et al., Towards correlation-based time window selection method for motor imagery BCIs, Neural Networks, 102 (2018), 87-95. doi: 10.1016/j.neunet.2018.02.011
[18]	K. Wang, M. P. Xu, Y. J. Wang, S. S. Zhang, L. Chen, D. Ming, Enhance decoding of pre-movement EEG patterns for brain-computer interfaces, J. Neural Eng., 17 (2020), 016033-016051. doi: 10.1088/1741-2552/ab598f
[19]	M. A. Li, Y. F. Wang, X. Q. Zhu, J. F. Yang, A wrapped time-frequency combined selection in the source domain, Biomed. Signal Proc. Control, 57 (2020), 101748-101757. doi: 10.1016/j.bspc.2019.101748
[20]	N. Yamawaki, C. Wilke, Z. M. Liu, B. He, An enhanced time-frequency-spatial approach for motor imagery classification, IEEE Trans. Neural Syst. Rehabil. Eng., 14 (2006), 250-254. doi: 10.1109/TNSRE.2006.875567
[21]	P. Gaur, H. Gupta, A. Chowdhury, K. McCreadie, R. B. Pachori, H. Wang, A Sliding Window Common Spatial Pattern for Enhancing Motor Imagery Classification in EEG-BCI, IEEE Trans. Instrum. Meas., 70 (2021), 1-9.
[22]	Y. Zhang, C. S. Nam, G. X. Zhou, J. Jin, X. Y. Wang, A. Cichocki, Temporally Constrained Sparse Group Spatial Patterns for Motor Imagery BCI, IEEE Trans. Cyber., 49 (2019), 3322-3332. doi: 10.1109/TCYB.2018.2841847
[23]	V. Peterson, D. Wyser, O. Lambercy, R. Spies, R. Gassert, A penalized time-frequency band feature selection and classification procedure for improved motor intention decoding in multichannel EEG, J. Neural Eng., 16 (2019), 016019-016031. doi: 10.1088/1741-2552/aaf046
[24]	P. Gaur, K. McCreadie, R. B. Pachori, H. Wang, G. Prasad, An automatic subject specific channel selection method for enhancing motor imagery classification in EEG-BCI using correlation, Biomed. Signal Proc. Control, 68 (2021). 102574-102581
[25]	J. Jin, C. Liu, I. Daly, Y. Y. Miao, S. R. Li, X. Y. Wang, et al., Bispectrum-Based Channel Selection for Motor Imagery Based Brain-Computer Interfacing, IEEE Trans. Neural Syst. Rehabil. Eng., 28 (2020), 2153-2163. doi: 10.1109/TNSRE.2020.3020975
[26]	Q. G. Wei, W. Tu, Channel Selection by Genetic Algorithms for Classifying Single-Trial ECoG during Motor Imagery, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2008. Available from: https://ieeexplore.ieee.org/abstract/document/4649230/.
[27]	F. K. Onay, C. Kose, Assessment of CSP-based two-stage channel selection approach and local transformation-based feature extraction for classification of motor imagery/movement EEG data, Biomed. Eng. Biomed. Tech., 64 (2019), 643-653.
[28]	J. Jin, Y. Y. Miao, I. Daly, C. L. BZuo, D. W. Hu, A. Cichocki, Correlation-based channel selection and regularized feature optimization for MI-based BCI, Neural Networks, 118 (2019), 262-270. doi: 10.1016/j.neunet.2019.07.008
[29]	K. R. Müller, M. Krauledat, G. Dornhege, G. Curio, B. Blankert, Machine learning techniques for brain-computer interfaces, Biomed. Tech., 49 (2004), 11-22. doi: 10.1515/BMT.2004.003
[30]	C. Vidaurre, N. Kramer, B. Blankertz, A. Schlogl, Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces, Neural Networks, 22 (2009), 1313-1319. doi: 10.1016/j.neunet.2009.07.020
[31]	K. K. Ang, Z. Y. Chin, H. H. Zhang, C. T. Guan, Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface, IEEE Int. Joint Conf. Neural Networks, 2008 (2008), 2390-2397.
[32]	K. D. Ghanbar, T. Y. Rezaii, M. A. Tinati, A. Farzamnia, Correlation-Based Regularized Common Spatial Patterns for Classification of Motor Imagery EEG Signals, 27th Iranian Conference on Electrical Engineering (ICEE), 2019. Available from: https://ieeexplore.ieee.org/abstract/document/8786490/.
[33]	Y. Zhang, G. X. Zhou, J. Jin, X. Y. Wang, A. Cichocki, Optimizing spatial patterns with sparse filter bands for motor-imagery based brain-computer interface, J. Neurosci. Methods, 255 (2015), 85-91. doi: 10.1016/j.jneumeth.2015.08.004
[34]	R. Tibshirani, Regression Shrinkage and Selection via the Lasso, J. Royal Stat. Soc. Ser. B Stat. Methodol., 58 (1996), 267-288.
[35]	R. Tibshirani, M. Saunders, S. Rosset, J. Zhu, K. Knight, Sparsity and smoothness via the fused lasso, J. Royal Stat. Soc. Ser. B Stat. Methodol., 67 (2005), 91-108. doi: 10.1111/j.1467-9868.2005.00490.x
[36]	G. Dornhege, B. Blankertz, G. Curio, K. R. Muller, Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms, IEEE Trans. Biomed. Eng., 51 (2004), 993-1002. doi: 10.1109/TBME.2004.827088
[37]	B. Blankertz, G. Dornhege, M. Krauledat, K. R. Muller, G. Curio, The non-invasive Berlin Brain-Computer Interface: Fast acquisition of effective performance in untrained subjects, Neuroimage, 37 (2007), 539-550. doi: 10.1016/j.neuroimage.2007.01.051
[38]	Y. Park, W. Chung, Frequency-Optimized Local Region Common Spatial Pattern Approach for Motor Imagery Classification, IEEE Trans. Neural Syst. Rehabil. Eng., 27 (2019), 1378-1388. doi: 10.1109/TNSRE.2019.2922713
[39]	Y. Jiao, Y. Zhang, X. Chen, E. Yin, J. Jin, X. Wang, et al., Sparse Group Representation Model for Motor Imagery EEG Classification, IEEE J. Biomed. Health Inf., 23 (2019), 631-641. doi: 10.1109/JBHI.2018.2832538
[40]	J. Jin, C. Liu, I. Daly, Y. Y. Miao, S. R. Li, X. Y. Wang, et al., Bispectrum-Based Channel Selection for Motor Imagery Based Brain-Computer Interfacing, IEEE Trans. Neural Syst. Rehabil. Eng., 28 (2020), 2153-2163. doi: 10.1109/TNSRE.2020.3020975
[41]	Y. Park, W.Chung, Optimal Channel Selection Using Correlation Coefficient for CSP Based EEG Classification, IEEE Access, 8 (2020), 111514-111521. doi: 10.1109/ACCESS.2020.3003056
[42]	B. Graimann, J. E. Huggins, S. P. Levine, G. Pfurtscheller, Visualization of significant ERD_ERS patterns in multichannel EEG and ECoG data, Clin. Neurophysiol., 113 (2002), 43-47. doi: 10.1016/S1388-2457(01)00697-6
[43]	G. Pfurtscheller, C. Neuper, C. Andrew, G. Edlinger, Foot and hand area mu rhythms, Int. J. Psychophysiology, 26 (1997), 121-135. doi: 10.1016/S0167-8760(97)00760-5

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)