Skip to main content
Springer Nature Link
Log in

Optimizing motion imagery classification with limited channels using the common spatial pattern-based integrated algorithm

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

The extraction of effective classification features from electroencephalogram (EEG) signals in motor imagery is a popular research topic. The Common Spatial Pattern (CSP) algorithm is widely employed in this field. However, the performance of the traditional CSP method depends significantly on the choice of a specific frequency band and channel number of EEG data. Furthermore, inter-class variance among these frequency bands and the limited number of available EEG channels can adversely affect the CSP algorithm’s ability to extract meaningful features from the relevant signal frequency bands. We hypothesize that multiple Intrinsic Mode Functions (IMFS), into which the raw EEG signal is decomposed, can better capture the non-Gaussian characteristics of the signal, thus compensating for the limitations of the CSP algorithm when dealing with nonlinear and non-Gaussian distributed data with few channels. Therefore, this paper proposes a novel method that integrates Variational Mode Decomposition (VMD), Phase Space Reconstruction (PSR), and the CSP algorithm to address these issues. VMD is used to filter and enhance the quality of the collected data, PSR is employed to increase the effective data channels (data augmentation), and the subsequent CSP filtering can obtain signals with spatial features, which are decoded by Convolutional Neural Networks (CNN) for action decoding. This study utilizes self-collected EEG data to demonstrate that the new method can achieve a good classification accuracy of 82.30% on average, confirming the improved algorithm’s effectiveness and feasibility. Furthermore, this study conducted validation on the publicly available BCI Competition IV dataset 2b, demonstrating an average classification accuracy of 87.49%.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Grosse-Wentrup M, Liefhold C, Gramann K, et al. (2009) Beamforming in noninvasive brain-computer interfaces [J]. IEEE Trans Bio-Med Eng. https://doi.org/10.1109/TBME.2008.2009768

  2. Guan S, Wang J, Wang F (2020) Research on recognition of shoulder joint movement imagination based on BCI technology [C]. Proceedings of the 2nd International Conference on Artificial Intelligence and Advanced Manufacture, 163–167

  3. Elstob D, Secco E L (2016) A low cost EEG based BCI prosthetic using motor imagery [Z]. https://doi.org/10.5121/ijitcs.2016.6103

  4. Santamato A, Panza F, Filoni S et al (2010) Effect of botulinum toxin type A, motor imagery and motor observation on motor function of hemiparetic upper limb after stroke [J]. Brain Inj 24(9):1108

    Article  PubMed  Google Scholar 

  5. Zhang H, Xu L, Wang S et al (2011) Behavioral improvements and brain functional alterations by motor imagery training [J]. Brain Res 1407:38–46

    Article  CAS  PubMed  Google Scholar 

  6. Pfurtscheller G, Brunner C, SCHL?GL A, et al. (2006) Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks [J]. Neuroimage, 31(1): 153–9. https://doi.org/10.1016/j.neuroimage.2005.12.003

  7. Wang H, Zhang C, Shi T et al (2015) Real-time EEG-based detection of fatigue driving danger for accident prediction [J]. Int J Neural Syst 25(02):498–369

    Article  Google Scholar 

  8. Kumar S, Sharma A, Tsunoda T (2019) Subject-specific-frequency-band for motor imagery EEG signal recognition based on common spatial spectral pattern, F[C]. https://doi.org/10.1007/978-3-030-29911-8_55

  9. Jiao Y, Zhang Y, Chen X et al (2018) Sparse group representation model for motor imagery EEG classification [J]. IEEE J Biomed Health Inform 23(2):631–641

    Article  PubMed  Google Scholar 

  10. Tomida N, Tanaka T, Ono S et al (2014) Active data selection for motor imagery EEG classification [J]. IEEE Trans Biomed Eng 62(2):458–467

    Article  PubMed  Google Scholar 

  11. Correa M, Leber E L (2011) Noise removal from EEG signals in polisomnographic records applying adaptive filters in cascade [M]. Adapt Filt Appl

  12. Jin J, Xiao R, Daly I et al (2020) Internal feature selection method of CSP based on L1-Norm and Dempster-Shafer theory [J]. IEEE Trans Neural Netw Learn Syst 1(PP):1–12

    Google Scholar 

  13. Miao Y, Jin J, Daly I, et al. (2021) Learning common time-frequency-spatial patterns for motor imagery classification [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, PP(99): 1-. https://doi.org/10.1109/TNSRE.2021.3071140

  14. Talukdar U, Hazarika SM, Gan JQ (2020) Adaptive feature extraction in EEG-based motor imagery BCI: tracking mental fatigue [J]. J Neural Eng 17(1):016020

    Article  PubMed  Google Scholar 

  15. Zhang Y, Zhou G, Jin J, et al. (2015) Optimizing spatial patterns with sparse filter bands for motor-imagery based brain–computer interface [J]. J Neurosci Methods, 85–91. https://doi.org/10.1016/j.jneumeth.2015.08.004

  16. Jin Y, Mousavi M, Sa V (2018) Adaptive CSP with subspace alignment for subject-to-subject transfer in motor imagery brain-computer interfaces; proceedings of the 2018 6th International Conference on Brain and Computer Interface (BCI), F, [C]

  17. Zhang Y, Nam CS, Zhou G et al (2018) (2018) Temporally constrained sparse group spatial patterns for motor imagery BCI [J]. IEEE transactions on cybernetics 49(9):3322–32

    Article  PubMed  Google Scholar 

  18. Zahid SZ, Aqil M, Tufail M et al (2020) Online classification of multiple motor imagery tasks using filter bank based maximum-a-posteriori common spatial pattern filters [J]. IRBM 41(3):141–150

    Article  Google Scholar 

  19. Guan J, Duan F (2019) The improvement of motor imagery based on spectral feature and transformation on multivariate empirical mode decomposition [J]. J Phys Conf Ser 1169:012044

    Article  Google Scholar 

  20. Baig MZ, Aslam N, Shum HP (2020) Filtering techniques for channel selection in motor imagery EEG applications: a survey [J]. Artif Intell Rev 53:1207–1232

    Article  Google Scholar 

  21. Gaur P, McCreadie K, Pachori RB et al (2021) An automatic subject specific channel selection method for enhancing motor imagery classification in EEG-BCI using correlation [J]. Biomed Signal Process Control 68:102574

    Article  Google Scholar 

  22. Wang T-C, Huang Y-Y, Duann J-R (2022) Sources of independent mu components reveal different brain areas involved in motor imagery, motor execution, and movement observation [J]. Brain Res 1796:148075

    Article  CAS  PubMed  Google Scholar 

  23. Ferracuti F, Iarlori S, Mansour Z et al (2021) Comparing between different sets of preprocessing, classifiers, and channels selection techniques to optimise motor imagery pattern classification system from EEG pattern recognition [J]. Brain Sci 12(1):57

    Article  PubMed  PubMed Central  Google Scholar 

  24. Saha S K, Ali M S (2016) Data adaptive filtering approach to improve the classification accuracy of motor imagery for BCI; proceedings of the International Conference on Electrical & Computer Engineering, F, [C]

  25. Packard NH, Crutchfield JP, Farmer JD et al (1980) (1980) Geometry from a time series [J]. Physical review letters 45(9):712

    Article  Google Scholar 

  26. Takens F (2006) Detecting strange attractors in turbulence; proceedings of the Dynamical Systems and Turbulence, Warwick 1980: proceedings of a symposium held at the University of Warwick 1979/80, F, [C]. Springer

  27. Alotaiby TN, Alshebeili SA, Alotaibi FM et al (2017) Epileptic seizure prediction using CSP and LDA for scalp EEG signals [J]. Computational Intelligence and Neuroscience 2017:1240323. https://doi.org/10.1155/2017/1240323

    Article  PubMed  PubMed Central  Google Scholar 

  28. Wang Y, Shen X, Peng Z (2018) Research of EEG recognition algorithm based on motor imagery, F, [C]

  29. Li C, Zhou W, Liu G et al (2021) Seizure onset detection using empirical mode decomposition and common spatial pattern [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering 29:458–67

    Article  PubMed  Google Scholar 

  30. Brunner C, Leeb R, Müller-Putz G et al (2008) BCI competition 2008–Graz data set A [J]. Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces). Graz Univ Technol 16:1–6

    Google Scholar 

  31. Tabar YR, Halici U (2016) A novel deep learning approach for classification of EEG motor imagery signals [J]. J Neural Eng 14(1):016003

    Article  PubMed  Google Scholar 

  32. Han Y, Wang B, Luo J et al (2022) A classification method for EEG motor imagery signals based on parallel convolutional neural network [J]. Biomed Signal Process Control 71:103190

    Article  Google Scholar 

  33. Ang KK, Chin ZY, Wang C et al (2012) Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b [J]. Front Neurosci 6:39

    Article  PubMed  PubMed Central  Google Scholar 

  34. Wang Z, He B, Zhou Y et al (2022) Incorporating EEG and EMG patterns to evaluate BCI-based long-term motor training [J]. IEEE Trans Human-Mach Syst 52(4):648–657

    Article  Google Scholar 

Download references

Funding

This work was supported by the National Key Research and Development Program of China (No. 2021ZD0113204), National Natural Science Foundation of China (Nos. 62371178 and 62301197), and Zhejiang Provincial Key Research and Development Program of China (No.2024C03041), Zhejiang Provincial Natural Science Foundation of China (NO. LQ21H180005).

Author information

Authors and Affiliations

  1. School of Automation, Hangzhou Dianzi University, Hangzhou, 310018, China

    Shishi Chen, Xugang Xi, Ting Wang, Lihua Li & Zhong Lü

  2. Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, 310018, China

    Shishi Chen, Xugang Xi & Ting Wang

  3. Hangzhou Mingzhou Naokang Rehabilitation Hospital, Hangzhou, 311215, China

    Hangcheng Li

  4. Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, 322100, China

    Maofeng Wang

Authors
  1. Shishi Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xugang Xi
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Ting Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Hangcheng Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Maofeng Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Lihua Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Zhong Lü
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Shishi Chen: Methodology, Writing—original draft, Data curation.

Xugang Xi: Funding acquisition, Writing—review & editing, Resources.

Ting Wang: Funding acquisition, Writing—review & editing.

Hangcheng Li and Maofeng Wang: Formal analysis, Visualization.

Lihua Li: Validation;

Corresponding author

Correspondence to Ting Wang.

Ethics declarations

Ethics approval and consent to participate

All the experimental procedures were approved by the ethics committee of Dongyang People’s Hospital of Zhejiang Province.

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, S., Xi, X., Wang, T. et al. Optimizing motion imagery classification with limited channels using the common spatial pattern-based integrated algorithm. Med Biol Eng Comput 62, 2305–2318 (2024). https://doi.org/10.1007/s11517-024-03069-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-024-03069-0

Keywords