Skip to main content
SpringerLink
Log in

Multi-segment Majority Voting Decision Fusion for MI EEG Brain-Computer Interfacing

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Brain-computer interfaces (BCIs) based on the electroencephalogram (EEG) generated during motor imagery (MI) have the potential to be used in brain-controlled prosthetics, neurorehabilitation and gaming. Many MI EEG classification systems segment EEG into windows for classification. However, a comprehensive analysis of decision fusion based on the segmented EEG data, within the context of different classifiers, has not been carried out. This study presents a multi-segment majority voting (MSMV) decision fusion approach in which an EEG trial is segmented using overlapping windows. Segments are labelled and a final classification label for the trial is derived through majority voting, using the common spatial pattern (CSP) features. The impact of the MSMV approach on the classification accuracy of six classifiers was investigated. The effects of window size and overlap were analysed. Results were generated using five different subsets of EEG channels, and channel subsets for static EEG analysis are also proposed. The BCI Competition III dataset IVa was used. The MSMV decision fusion approach was found to significantly improve the classification accuracy for linear discriminant analysis (LDA), support vector machine (SVM), naïve-Bayes (NB) and random forest (RF) classifiers. The classification accuracy was improved by 5.02%, 4.41%, 1.25% and 3.62% for the SVM, LDA, NB and RF classifiers, respectively. The channel analysis indicated the importance of central-parietal and central-frontal electrode regions for MI EEG classification. MSMV decision fusion improved MI EEG classification performance and could be considered for future studies, particularly in online systems that deal with buffered data.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Padfield N, Zabalza J, Zhao H, Masero V, Ren J. EEG-based brain-computer interfaces using motor-imagery: techniques and challenges. Sensors (Switzerland). 2019;19(6):1–34. https://doi.org/10.3390/s19061423.

    Article  Google Scholar 

  2. Graimann B, Allison B, Pfurtscheller G. Brain–computer interfaces: a gentle introduction. In: Graimann B, Pfurtscheller G, Allison B, editors. Brain-computer interfaces. Heidelberg: Springer; 2009. p. 1–27. https://doi.org/10.1007/978-3-642-02091-9_1.

    Chapter  Google Scholar 

  3. Tang Z, Li C, Sun S. Single-trial EEG classification of motor imagery using deep convolutional neural networks. Optik (Stuttg). 2017;130:11–8.

    Article  Google Scholar 

  4. Choi J, Kim H. Real-time decoding of EEG gait intention for controlling a lower-limb exoskeleton system. In: 7th International Winter Conference on Brain-Computer Interface (BCI), Feb. 2019. https://doi.org/10.1109/IWW-BCI.2019.8737311.

  5. Arnin J, Kahani D, Lakany H, Conway BA. Heterogeneous real-time multi-channel time-domain feature extraction using parallel sum reduction on GPU. In: 8th Graz Brain Comp. Interface Conf. 2019, Bridging Science and Application, Sept. 2019. https://doi.org/10.3217/978-3-85125-682-6-33.

  6. Rodŕiguez-Beŕmudez G, Gárcia-Laencina PJ. Automatic and adaptive classification of electroencephalographic signals for brain computer interfaces. J Med Syst. 2012;36:51–63. https://doi.org/10.1007/s10916-012-9893-4.

    Article  Google Scholar 

  7. Asensio-Cubero J, Gan JQ, Palaniappan R. A study on temporal segmentation strategies for extracting common spatial patterns for brain computer interfacing. UKCI 2011 - Proceedings of the 11th UK Workshop on Computational Intelligence. 2011.

  8. Asensio-Cubero J, Gan JQ, Palaniappan R. Extracting optimal tempo-spatial features using local discriminant bases and common spatial patterns for brain computer interfacing. Biomed Signal Process Control. 2013;8(6):772–8. https://doi.org/10.1016/j.bspc.2013.07.004.

    Article  Google Scholar 

  9. Samuel OW, Asogbon MG, Geng Y, Pirbhulal S, Mzurikwao D, Chen S, Fang P, et al. Determining the optimal window parameters for accurate and reliable decoding of multiple classes of upper limb motor imagery tasks. In: 2018 IEEE Int. Conf. Cyborg Bionic Syst. CBS, Oct. 2018. https://doi.org/10.1109/CBS.2018.8612159.

  10. Kevric J, Subasi A. Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system. Biomed Signal Process Control. 2017;31:398–406. https://doi.org/10.1016/j.bspc.2016.09.007.

    Article  Google Scholar 

  11. Ko LW, Lu Y, Chang Y. Multimodal fuzzy fusion for enhancing the motor-imagery-based brain computer interface. IEEE Comput Intell Mag. 2019;14(1):96–106. https://doi.org/10.1109/MCI.2018.2881647.

    Article  Google Scholar 

  12. Oikonomou VP, Georgiadis K, Liaros G, Nikolopoulos S, Kompatsiaris I. A comparison study on EEG signal processing techniques using motor imagery EEG data. In: IEEE Symp. Comput. Med. Syst., Jun. 2017. https://doi.org/10.1109/CBMS.2017.113.

  13. Wahid MF, Tafreshi R, Langari R. A multi-window majority voting strategy to improve hand gesture recognition accuracies using electromyography signal. IEEE Trans Neural Syst Rehabil Eng. 2019;28(2):427–36. https://doi.org/10.1109/TNSRE.2019.2961706.

    Article  Google Scholar 

  14. Baig MZ, Aslam N, Shum HPH, Zhang L. Differential evolution algorithm as a tool for optimal feature subset selection in motor imagery EEG. Expert Syst Appl. 2017;90:184–95. https://doi.org/10.1016/j.eswa.2017.07.033.

    Article  Google Scholar 

  15. Kumar S, Sharma A, Tsunoda T. An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information. BMC Bioinformatics. 2017;18:545. https://doi.org/10.1186/s12859-017-1964-6.

    Article  Google Scholar 

  16. He L, Hu Y, Li Y, Li D. Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying single-trial motor imagery EEG. Neurocomputing. 2013;121:423–33. https://doi.org/10.1016/j.neucom.2013.05.005.

    Article  Google Scholar 

  17. Shenoy HV, Vinod AP. An iterative optimization technique for robust channel selection in motor imagery based brain computer interface. In: 2014 IEEE Int. Conf. Syst. Man Cybern., Jan. 2014. https://doi.org/10.1109/SMC.2014.6974191.

  18. Li M, Ma J, Jia S. Optimal combination of channels selection based on common spatial pattern algorithm. In: IEEE Int. Conf. Mechatronics Autom. ICMA 2011, Aug. 2011. https://doi.org/10.1109/ICMA.2011.5985673.

  19. Yang Y, Bloch I, Chevallier S, Wiart J. Subject-specific channel selection using time information for motor imagery brain–computer interfaces. Cogn Comput. 2016;8(3):505–18. https://doi.org/10.1007/s12559-015-9379-z.

    Article  Google Scholar 

  20. Yang B, Hu C, Wang J, Li B, Wang W. Research on motor imagery EEG modeling based on window optimization and a few channels PSD. In: Int. Conf. Digit. Signal Process., Nov 2018. https://doi.org/10.1109/ICDSP.2018.8631698.

  21. Olias J, Martin-Clemente R, Sarmiento-Vega MA. EEG signal processing in MI-BCI applications with improved covariance matrix estimators. IEEE Trans Neural Syst Rehabil Eng. 2019;27(5):895–904. https://doi.org/10.1109/TNSRE.2019.2905894.

    Article  Google Scholar 

  22. Siuly S, Li Y, Zhang Y. Comparative study: motor area EEG and all-channels EEG. In: EEG Signal Analysis and Classification. Springer: Cham; 2016. p. 211–225. https://doi.org/10.1007/978-3-319-47653-7_11.

  23. Armstrong S, Sale MV, Cunnington R. Neural oscillations and the initiation of voluntary movement. Front Psychol. 2018;9:2509.

    Article  Google Scholar 

  24. Schutter DJ, Putman P, Hermans E, van Honk J. Parietal electroencephalogram beta asymmetry and selective attention to angry facial expressions in healthy human subjects. Neurosci Lett. 2001;314(1–2):13–6.

    Article  Google Scholar 

  25. Dornhege G, Blankertz B, Curio G, Müller KR. Boosting bit rates in non-invasive EEG single-trial classifications by feature combination and multi-class paradigms. IEEE Trans Biomed Eng. 2004;51(6):993–1002. https://doi.org/10.1109/TBME.2004.827088.

    Article  Google Scholar 

  26. O’Reilly C, Nielsen T. Automatic sleep spindle detection: benchmarking with fine temporal resolution using open science tools. Front Hum Neurosci. 2015;9:353. https://doi.org/10.3389/fnhum.2015.00353.

    Article  Google Scholar 

  27. She Q, Chen K, Ma Y, Nguyen T, Zhang Y. Sparse representation-based extreme learning machine for motor imagery EEG classification. Comput Intell Neurosci. 2018;2018:9593682. https://doi.org/10.1155/2018/9593682.

    Article  Google Scholar 

  28. Kumar S, Sharma A, Mamun K, Tsunoda T. A deep learning approach for motor imagery EEG signal classification. In: 3rd Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE), Dec. 2016. https://doi.org/10.1109/APWC-on-CSE.2016.017.

  29. Cranstoun SD, Ombao HC, von Sachs R, Guo W, Litt B. Time-frequency spectral estimation of multichannel EEG using the auto-SLEX method. IEEE Trans Biomed Eng. 2002;49(9):988–96. https://doi.org/10.1109/TBME.2002.802015.

    Article  Google Scholar 

  30. Qin D, Houchins B, Parten M E, Parker N, Homan R and Petrosian A. A comparison of techniques for the prediction of epileptic seizures. In: 8th IEEE Symposium on Computer-Based Medical Systems, Jun. 1995. https://doi.org/10.1109/CBMS.1995.465436.

  31. Wojcikiewicz W, Vidaurre C and Kawanabe M. Stationary common spatial patterns for non-stationary EEG data. Front. Comput. Neurosci. Conference Abstract: Bernstein Conf. on Computational Neuroscience, Sept. 2010. https://doi.org/10.3389/conf.fncom.2010.51.00051.

  32. Wang Q, Lin J, Yuan Y. Salient band selection for hyperspectral image classification via manifold ranking. IEEE Trans Neural Netw Learn Syst. 2016;27(6):1279–89. https://doi.org/10.1109/TNNLS.2015.2477537.

    Article  Google Scholar 

  33. Lyu D, Liu B, Geist M, Dong W, Biaz S, Wang Q. Stable and efficient policy evaluation. IEEE Trans Neural Netw Learn Syst. 2018;30(6):1831–40. https://doi.org/10.1109/TNNLS.2018.2871361.

    Article  MathSciNet  Google Scholar 

  34. Padfield N, Ren J, Murray P, Zhao H, Sparse learning of band power features with genetic channel selection for effective classification of EEG signals, Neurocomputing 463, 566-579, 2021. https://doi.org/10.1016/j.neucom.2021.08.067.

  35. Fang Z, Ren J, MacLellan C, Li H, Zhao H, Hussain A, Fortino G, A novel multi-stage residual feature fusion network for detection of COVID-19 in chest X-ray images, IEEE Transactions on Molecular, Biological and Multi-Scale Communications, in press, 2021. https://doi.org/10.1109/TMBMC.2021.3099367.

  36. Sun G, Fu H, Ren J, Zhang A, Zabalza J, Jia X, Zhao H, SpaSSA: Superpixelwise adaptive SSA for unsupervised spatial-spectral feature extraction in hyperspectral image, IEEE Transactions on Cybernetics, in press, 2021. https://doi.org/10.1109/TCYB.2021.3104100.

Download references

Funding

This work was supported in part by the Dazhi Scholarship of the Guangdong Polytechnic Normal University (GPNU), the Education Department of Guangdong Province (2019KSYS0091), the National Natural Science Foundation of China (62072122), the Scientific and Technological Planning Projects of Guangdong Province (2021A0505030074) the Scientific and Technological Planning Projects of Guangdong Province (2021A0505030074) and the University of Strathclyde Scholarship.

Author information

Authors and Affiliations

  1. Centre for Signal and Image Processing, University of Strathclyde, Glasgow, G1 1XW, UK

    Natasha Padfield & Paul Murray

  2. National Subsea Centre, Robert Gordon University, Aberdeen, UK

    Jinchang Ren

  3. School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China

    Chunmei Qing

  4. School of Computer Sciences, Guangdong Polytechnic Normal University, Guangzhou, 510665, China

    Jinchang Ren & Huimin Zhao

  5. School of Software, Northwestern Polytechnical University, Xi’an, China

    Jiangbin Zheng

Authors
  1. Natasha Padfield
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinchang Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chunmei Qing
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Paul Murray
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Huimin Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jiangbin Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jinchang Ren.

Ethics declarations

Conflict of Interest

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

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Padfield, N., Ren, J., Qing, C. et al. Multi-segment Majority Voting Decision Fusion for MI EEG Brain-Computer Interfacing. Cogn Comput 13, 1484–1495 (2021). https://doi.org/10.1007/s12559-021-09953-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-021-09953-3

Keywords

Search

Navigation