Skip to main content

Multiple classifier system for EEG signal classification with application to brain–computer interfaces

Abstract

In this paper, we demonstrate the use of a multiple classifier system for classification of electroencephalogram (EEG) signals. The main purpose of this paper is to apply several approaches to classify motor imageries originating from the brain in a more robust manner. For this study, dataset II from BCI competition III was used. To extract features from the brain signal, discrete wavelet transform decomposition was used. Then, several classic classifiers were implemented to be utilized in the multiple classifier system, which outperforms the reported results of other proposed methods on the dataset. Also, a variety of classifier combination methods along with genetic algorithm feature selection were evaluated and compared in order to diminish classification error. Our results suggest that an ensemble system can be employed to boost EEG classification accuracy.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Lebedev MA, Nicolelis MAL (2006) Brain-machine interfaces:past, present and future. TRENDS Neurosci 29(9):536–546

    Google Scholar 

  2. 2.

    Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM (2002) Brain-computer interfaces for communication and control. Clin. Neurophysiol 113(6):767–791

    Article  Google Scholar 

  3. 3.

    Bell CJ, Shenoy P, Chalodhorn R, Rao RP (2008) Control of a humanoid robot by a noninvasive Brain-Computer Interface in humans. Neural Eng 5:214–220

    Google Scholar 

  4. 4.

    Bayliss JD, Ballard DH (2000) A virtual reality testbed for Brain-Computer Interface research. Rehabil Eng 8(2):188–190

    Google Scholar 

  5. 5.

    Galán F, Nuttin M, Lew E, Ferrez PW, Vanacker G, Philips J, Millán Jdel RA (2008) Brain-actuated wheelchair: asynchronous and non-invasive brain-computer interfaces for continuous control of robots. Clin Neurophysiol 119:2159–2169

  6. 6.

    Hashimoto1 Y, Ushiba J, Kimura A, Liu M, Tomita Y (2010) change in brain activity through virtual reality-based brain-machine communication in a chronic tetraplegic subject with muscular dystrophy. BMC Neurosci 11(117). doi:10.1186/1471-2202-11-117

  7. 7.

    Pfurtscheller G, Scherer R (2010) Brain-computer interfaces used for virtual reality control. In: ICABB-Venice

  8. 8.

    Reuderink B, Poel M (2008) Robustness of the common spatial patterns algorithm in the BCI-pipeline. Technical report, HMI, University of Twente. Available at http://doc.utwente.nl/64884/

  9. 9.

    Niedermeyer E, Da Silva F (2005) Electroencephalography: basic principles, clinical applications, and related fields. Doody’s all reviewed collection. Lippincott Williams & Wilkins, Philadelphia, PA

  10. 10.

    Millán JdR, Rupp R, Müller-Putz GR, Murray-Smith R, Giugliemma C, Tangermann M, Vidaurre C, Cincotti F, Kübler A, Leeb R, Neuper C, Müller K-R, Mattia D (2010) Combining brain-computer interfaces and assistive technologies: state-of-the-art and challenges. Frontiers Neurosci 4(9):161

    Google Scholar 

  11. 11.

    Keng Ang K, Guan C, Geok Chua S, Ti Ang B, Kuah C, Wang C, Soon Phua C, Yang Chin Z, Zhang H (2009) A clinical study of motor imagery-based brain-computer interface for upper limb robotic rehabilitation. In: International conference of the IEEE engineering in medicine and biology society, Minneapolis, MN

  12. 12.

    Wang Y, Jao S (2005) Common spatial pattern method for channel selection in motor imagery based brain computer interface. IEEE 1(1):5392–5395

    Google Scholar 

  13. 13.

    Leuthardt EC, Schalk G, Wolpaw JR, Ojemann JG, Moran DW (2004) A brain-computer interface using electrocorticographic signals in humans. J Neural Eng 1:63–71

    Google Scholar 

  14. 14.

    McFarland TMVDJ, Miner LA, Wolpaw JR (2000) Mu and beta rhythm topographies during motor imagery and actual movements. Brain Topogr 12(3):177–186

    Google Scholar 

  15. 15.

    Pfurtscheller G, Neuper C, Guger C, Harkam W, Ramoser H, Schlogl A, Obermaier B, Pregenzer M (2000) Current trends in graz brain-computer interface (BCI) research. Rehabil Eng 8:216–225

    Google Scholar 

  16. 16.

    Pfurtscheller G, Neuper C (1997) Motor imagery activates primary sen-sorimotor areas. Neurosci Lett 239:65–68

    Article  Google Scholar 

  17. 17.

    Pfurtscheller G, Neuper C, Flotzinger D, Pregenzer M (1997) EEG-based discrimination between imagination of right and left hand movement. Electroenc Clin Neurophys 103(5):1–10

    Google Scholar 

  18. 18.

    Hoffmann U, Vesin J-M, Ebrahimi T, Diserens K (2008) An efficient p300-based brain-computer interface for disabled subjects. J Neurosci Methods 167:115–125

    Article  Google Scholar 

  19. 19.

    Neupera C, Mullerb G, Kublerc A, Birbaumerc N, Pfurtschellera G (2003) Clinical application of an EEG-based brain-computer interface: a case study in a patient with severe motor impairment. Clin Neurophysiol 114:399–409

    Article  Google Scholar 

  20. 20.

    Obermaier B, Neuper C, Guger C, Pfurtscheller G (2001) Information transfer rate in a five-classes brain-computer interface. Neural Syst Rehabil Eng 9(9):283–288

    Google Scholar 

  21. 21.

    Zhang H, Guan C, Wang C (2008) Asynchronous p300-based brain-computer interfaces: a computational approach with statistical models. Biomed Eng 55(6):1754–1763

    Google Scholar 

  22. 22.

    Adelia H, Zhoub Z, Dadmehr N (2003) Analysis of EEG records in an epileptic patient using wavelet transform. Neurosci Methods 123(2):69–87

    Article  Google Scholar 

  23. 23.

    Cvetkovic D, Derya beyli E, Cosic I (2008) Wavelet transform feature extraction from human ppg, ECG, and EEG signal responses to elf pemf exposures: a pilot study. Elsevier Digit Signal Process 18:861–874

    Article  Google Scholar 

  24. 24.

    Übeyli ED (2009) Combined neural network model employing wavelet coefficients for EEG signals classification. Elsevier Digit Signal Process 19:297–308

    Article  Google Scholar 

  25. 25.

    Subasi A (2007) EEG signal classification using wavelet feature extraction and a mixture of expert model. Elsevier Expert Syst Appl 32:1084–1093

    Article  Google Scholar 

  26. 26.

    http://www.bbci.de/competition/ii/results/ (2003) Results webpage for BCI competition II

  27. 27.

    Mller-Gerking HRJ (2000) Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans Rehabil Eng 1(1):441–446

    Google Scholar 

  28. 28.

    Javadi M, Ebrahimpour R, Sajedin A, Faridi S, Zakernejad S (2011) Improving ECG classification accuracy using an ensemble of neural network modules. Plos One 6(10):e24386. doi:10.1371/journal.pone.0024386

  29. 29.

    Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21–45

    Article  Google Scholar 

  30. 30.

    Ghaderi R (2000) Arranging simple neural networks to solve complex classification problems. University of Surrey, Guildford

    Google Scholar 

  31. 31.

    Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms. Wiley-Interscience, New York

    Book  Google Scholar 

  32. 32.

    Esmaeili M (2007) Classifiers fusion for EEG signals processing in human-computer interface systems. In: Proceedings of the 22nd national conference on Artificial intelligence, vol 2. AAAI Press, Menlo Park, CA, pp. 1856–1857

  33. 33.

    Ebrahimpour R, Esmkhani A, Faridi S (2010) Farsi handwritten digit recognition based on mixture of rbf experts. IEICE Electron Express 7(14):1014–1019

    Article  Google Scholar 

  34. 34.

    Ebrahimpour R, Kabir E, Yousefi MR (2008) Teacher-directed learning in view-independent face recognition with mixture of experts using single-view eigenspaces. J Franklin Inst 345(2):87–101

    Article  MATH  Google Scholar 

  35. 35.

    http://www.bbci.de/competition/ii/ (2003) Dataset III provided by Institute for Biomedical Engineering, Graz University of Technology

  36. 36.

    Friedman JH, Fayyad U (1997) On bias, variance, 0/1-loss, and the curse-of-dimensionality. Data Min Knowl Disc 1:55–77

    Article  Google Scholar 

  37. 37.

    Haykin S (1998) Neural networks. 2nd edn. Prentice Hall, Englewood Cliffs NJ

    Google Scholar 

  38. 38.

    Richard DGS, Duda O, Hart PE (2000) Pattern classification, 2nd edn. Wiley, New York

    Google Scholar 

  39. 39.

    Zheng Z (1998) Naive bayesian classifier committees. In: Ndellec C, Rouveirol C (eds) Machine learning: ECML-98, vol. 1398 of lecture notes in computer science. Springer, Heidelberg, pp 196–207. doi:10.1007/BFb0026690

  40. 40.

    Gunn S (1998) Support vector machines for classification and regression,” technical report, University of Southampton, Faculty of Engineering, Science and Mathematics School of Electronics and Computer Science

  41. 41.

    Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2:121–167

    Article  Google Scholar 

  42. 42.

    Jain RPWDJMAK (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Machine Intell 22(1):4–37

    Article  Google Scholar 

  43. 43.

    Quinlan JR (1996) Bagging, boosting, and c4.5. AAAI/IAAI 1:725–730

  44. 44.

    Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139

    MathSciNet  Article  MATH  Google Scholar 

  45. 45.

    Huang YS, Suen CY (1993) The behavior-knowledge space method for combination of multiple classifiers. Comput Vision Pattern Recogn 6:347–352

    Google Scholar 

  46. 46.

    Kuncheva L, Bezdek J, Duin R (2001) Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recogn 34(2):299–314

    Article  MATH  Google Scholar 

  47. 47.

    Tsymbal PCA, Pechenizkiy M (2005) Sequential genetic search for ensemble feature selection. In: IJCAI05, 19th international joint conference on artificial intelligence, pp 877–882

  48. 48.

    Kuncheva L (1993) Genetic algorithm for feature selection for parallel classifiers. Inf Process Lett 46:163–168

    Article  MATH  Google Scholar 

Download references

Acknowledgments

The authors would like to thank the Graz University of Technology, Institute for Biomedical Engineering for providing the data. This work was supported by Shahid Rajaee Teacher Training University.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Reza Ebrahimpour.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Ahangi, A., Karamnejad, M., Mohammadi, N. et al. Multiple classifier system for EEG signal classification with application to brain–computer interfaces. Neural Comput & Applic 23, 1319–1327 (2013). https://doi.org/10.1007/s00521-012-1074-3

Download citation

Keywords

  • EEG classification
  • Motor imagery
  • Wavelet feature extraction
  • Feature selection
  • Multiple classifier system (MCS)