Advertisement

Multi-class EEG classification of motor imagery signal by finding optimal time segments and features using SNR-based mutual information

  • Mahmoud MahmoudiEmail author
  • Mousa Shamsi
Scientific Paper
  • 78 Downloads

Abstract

The electroencephalogram signals are used to distinguish different motor imagery tasks in brain–computer interfaces. In most studies, in order to classify the EEG signals recorded in a cue-guided BCI paradigm, time segments for feature extraction after the onset of the visual cue were selected manually. In addition, in these studies the authors have selected a single identical time segment for different subjects. The present study emphasized on the inter-individual variability and difference between different motor imagery tasks as the potential source of erroneous results and used mutual information and the subject specific time interval to overcome this problem. More specifically, a new method was proposed to automatically find the best subject specific time intervals for the classification of four-class motor imagery tasks by using MI between the BCI input and output. Moreover, the signal-to-noise ratio was used to calculate the MI values, while the MI values were used as feature selection criteria to select the discriminative features. The time segments and the best discriminative features were found by using training data and used to assess the evaluation data. Furthermore, the CSP algorithm was used to extract signal features. The dataset 2A of BCI competition IV used in this study consisted of four different motor imagery signals, which were obtained from nine different subjects. One Vs One decomposition scheme was used to deal with the multi-class nature of the problem. The MI values showed that the obtained time segments not only varied between different subjects but also varied between different classifiers of different pair of classes. Finally, the results suggested that the proposed method was efficient in classifying multi-class motor imagery signals as compared to other classification strategies proposed by the other studies.

Keywords

Brain–computer interface Electroencephalogram Signal to noise ratio Mutual information One-Vs-One scheme 

Notes

Compliance with ethical standards

Funding

This study received no specific grant from any funding agency.

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

References

  1. 1.
    Teng F, Chen Y, Choong AM, Gustafson S, Reichley C, Lawhead P, Waddell D (2011) Square or sine: finding a waveform with high success rate of eliciting ssvep. Comput Intell Neurosci 2011:2CrossRefGoogle Scholar
  2. 2.
    Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM (2002) Braincomputer interfaces for communication and control. Clin Neurophys 113(6):767–791CrossRefGoogle Scholar
  3. 3.
    Wessel M (2006) Pioneering research into brain computer interfaces. Delft University of TechnologyGoogle Scholar
  4. 4.
    Castermans T, Duvinage M, Cheron G, Dutoit T (2013) Towards effective non-invasive brain-computer interfaces dedicated to gait rehabilitation systems. Brain Sci 4(1):1–48CrossRefGoogle Scholar
  5. 5.
    Ali Y (2014) Brain computer interface: principles, recent advances and clinical challenges. Orient J Comput Sci Technol 7(3):425–42Google Scholar
  6. 6.
    Adams IL, Steenbergen B, Lust JM, Smits-Engelsman BC (2016) Motor imagery training for children with developmental coordination disorderstudy protocol for a randomized controlled trial. BMC Neurol 16(1):5CrossRefGoogle Scholar
  7. 7.
    Pfurtscheller G (2001) Functional brain imaging based on ERD/ERS. Vis Res 41(10):1257–1260CrossRefGoogle Scholar
  8. 8.
    Bhardwaj S, Jadhav P, Adapa B, Acharyya A, Naik G R (2015) Online and automated reliable system design to remove blink and muscle artefact in EEG. In: Engineering in Medicine and Biology Society (EMBC), 2015 37th annual international conference of the IEEE , pp 6784–6787. IEEEGoogle Scholar
  9. 9.
    Jadhav PN, Shanamugan D, Chourasia A, Ghole AR, Acharyya AA, Naik G (2014) Automated detection and correction of eye blink and muscular artefacts in EEG signal for analysis of autism spectrum disorder. In: Engineering in Medicine and Biology Society (EMBC), 2014 36th annual international conference of the IEEE, pp 1881–1884. IEEEGoogle Scholar
  10. 10.
    Chiappa S, Barber D (2006) EEG classification using generative independent component analysis. Neurocomputing 69(7–9):769–777CrossRefGoogle Scholar
  11. 11.
    Winkler I, Haufe S, Tangermann M (2011) Automatic classification of artifactual ICA-components for artifact removal in EEG signals. Behav Brain Funct 7(1):30CrossRefGoogle Scholar
  12. 12.
    Naik GR, Kumar DK (2011) An overview of independent component analysis and its applications. Informatica 35(1):63–81Google Scholar
  13. 13.
    Feis RA, Smith SM, Filippini N, Douaud G, Dopper EG, Heise V, Trachtenberg AJ, van Swieten JC, van Buchem MA, Rombouts SA, Mackay CE (2015) ICA-based artifact removal diminishes scan site differences in multi-center resting-state fMRI. Front Neurosci 9:395CrossRefGoogle Scholar
  14. 14.
    Kemiha M, Kacha A (2017) Complex blind source separation. Circuits Syst Signal Process 36(11):4670–4687CrossRefGoogle Scholar
  15. 15.
    Li XL, Adali T (2010) Independent component analysis by entropy bound minimization. IEEE Trans Signal Process 58(10):5151–5164CrossRefGoogle Scholar
  16. 16.
    Hess AS, Hess JR (2018) Principal component analysis. Transfusion.  https://doi.org/10.1111/trf.14639 CrossRefPubMedGoogle Scholar
  17. 17.
    Subasi A, Gursoy MI (2010) EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl 37(12):8659–8666CrossRefGoogle Scholar
  18. 18.
    Bascil MS, Tesneli AY, Temurtas F (2016) Spectral feature extraction of EEG signals and pattern recognition during mental tasks of 2-D cursor movements for BCI using SVM and ANN. Australas Phys Eng Sci Med 39(3):665–676CrossRefGoogle Scholar
  19. 19.
    Faust O, Acharya UR, Adeli H, Adeli A (2015) Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis. Seizure 26:56–64CrossRefGoogle Scholar
  20. 20.
    Zhang Y, Liu B, Ji X, Huang D (2017) Classification of EEG signals based on autoregressive model and wavelet packet decomposition. Neural Process Lett 45(2):365–378CrossRefGoogle Scholar
  21. 21.
    Flandrin P, Rilling G, Goncalves P (2004) Empirical mode decomposition as a filter bank. IEEE Signal Process Lett 11(2):112–114CrossRefGoogle Scholar
  22. 22.
    Fang Y, Chen M, Zheng X (2015) Extracting features from phase space of EEG signals in brain-computer interfaces. Neurocomputing 151:1477–1485CrossRefGoogle Scholar
  23. 23.
    Kevric J, Subasi A (2017) Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system. Biomed Signal Process Control 31:398–406CrossRefGoogle Scholar
  24. 24.
    Lotte F, Congedo M, Lcuyer A, Lamarche F, Arnaldi B (2007) A review of classification algorithms for EEG-based brain computer interfaces. J Neural Eng 4(2):R1CrossRefGoogle Scholar
  25. 25.
    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117CrossRefGoogle Scholar
  26. 26.
    Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127CrossRefGoogle Scholar
  27. 27.
    Kanai R, Rees G (2011) The structural basis of inter-individual differences in human behaviour and cognition. Nat Rev Neurosci 12(4):231CrossRefGoogle Scholar
  28. 28.
    Ramon C, Freeman WJ, Holmes M, Ishimaru A, Haueisen J, Schimpf PH, Rezvanian E (2009) Similarities between simulated spatial spectra of scalp EEG, MEG and structural MRI. Brain Topogr 22(3):191–196CrossRefGoogle Scholar
  29. 29.
    Yi W, Qiu S, Qi H, Zhang L, Wan B, Ming D (2013) EEG feature comparison and classification of simple and compound limb motor imagery. J Neuroengi Rehabil 10(1):106CrossRefGoogle Scholar
  30. 30.
    Barachant A, Bonnet S, Congedo M, Jutten C (2012) Multiclass braincomputer interface classification by Riemannian geometry. IEEE Trans Biomed Eng 59(4):920–928CrossRefGoogle Scholar
  31. 31.
    Tang Z, Li C, Sun S (2017) Single-trial EEG classification of motor imagery using deep convolutional neural networks. Opt-Int J Light Electron Opt 130:11–18CrossRefGoogle Scholar
  32. 32.
    Kam TE, Suk HI, Lee SW (2013) Non-homogeneous spatial filter optimization for electroencephalogram (EEG)-based motor imagery classification. Neurocomputing 108:58–68CrossRefGoogle Scholar
  33. 33.
    Ang KK, Chin ZY, Wang C, Guan C, Zhang H (2012) Filter bank common spatial pattern algorithm on BCI competition IV datasets 2A and 2b. Fronti Neurosci 6:39Google Scholar
  34. 34.
    Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33(3):1065–1076CrossRefGoogle Scholar
  35. 35.
    Ang KK, Chin ZY, Zhang H, Guan C (2012) Mutual information-based selection of optimal spatialtemporal patterns for single-trial EEG-based BCIs. Pattern Recognit 45(6):2137–2144CrossRefGoogle Scholar
  36. 36.
    Schlögl A, Neuper C, Pfurtscheller G (2002) Estimating the mutual information of an EEG-based brain-computer interface. Biomedizinische Technik/Biomed Eng 47(1–2):3–8CrossRefGoogle Scholar
  37. 37.
    BCI Competition II (2003) http://www.bbci.de/competition/ii/
  38. 38.
    Gaur P, Pachori RB, Wang H, Prasad G (2018) A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry. Expert Syst Appl 95:201–211CrossRefGoogle Scholar
  39. 39.
    Wang J, Feng Z, Lu N, Luo J (2018) Toward optimal feature and time segment selection by divergence method for EEG signals classification. Comput Biol Med 97:161–170CrossRefGoogle Scholar
  40. 40.
    Alimardani F, Boostani R, Blankertz B (2017) Weighted spatial based geometric scheme as an efficient algorithm for analyzing single-trial EEGS to improve cue-based BCI classification. Neural Netw 92:69–76CrossRefGoogle Scholar
  41. 41.
    Sun L, Feng Z, Chen B, Lu N (2018) A contralateral channel guided model for EEG based motor imagery classification. Biomed Signal Process Control 41:1–9CrossRefGoogle Scholar
  42. 42.
    Wei Z, Wei Q (2016) The backtracking search optimization algorithm for frequency band and time segment selection in motor imagery-based braincomputer interfaces. J Integr Neurosci 15(03):347–364CrossRefGoogle Scholar
  43. 43.
    Luo J, Feng Z, Zhang J, Lu N (2016) Dynamic frequency feature selection based approach for classification of motor imageries. Comput Biol Med 75:45–53CrossRefGoogle Scholar
  44. 44.
    Koles ZJ, Lazar MS, Zhou SZ (1990) Spatial patterns underlying population differences in the background EEG. Brain Topogr 2(4):275–284CrossRefGoogle Scholar
  45. 45.
    BCI Competition IV (2008) http://www.bbci.de/competition/iv/
  46. 46.
    Brunner C, Leeb R, Mller-Putz G, Schlögl A, Pfurtscheller G (2008) BCI Competition 2008Graz data set A. Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces), Graz University of Technology, Graz, pp 136–142Google Scholar
  47. 47.
    Guger C, Ramoser H, Pfurtscheller G (2000) Real-time EEG analysis with subject-specific spatial patterns for a brain–computer interface (BCI). IEEE Trans Rehabil Eng 8(4):447–456CrossRefGoogle Scholar
  48. 48.
    Ramoser H, Muller-Gerking J, Pfurtscheller G (2000) Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans Rehabil Eng 8(4):441–446CrossRefGoogle Scholar
  49. 49.
    Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2011) An overview of ensemble methods for binary classifiers in multi-class problems: experimental study on one-vs-one and one-vs-all schemes. Pattern Recogn 44(8):1761–1776CrossRefGoogle Scholar
  50. 50.
    Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20(1):37–46CrossRefGoogle Scholar
  51. 51.
    Hsu WY (2011) Continuous EEG signal analysis for asynchronous BCI application. Int J Neural Syst 21(04):335–350CrossRefGoogle Scholar

Copyright information

© Australasian College of Physical Scientists and Engineers in Medicine 2018

Authors and Affiliations

  1. 1.Faculty of Biomedical EngineeringSahand University of TechnologyTabrizIran

Personalised recommendations