Annals of Biomedical Engineering

, Volume 33, Issue 8, pp 1053–1070 | Cite as

Recognition of Motor Imagery Electroencephalography Using Independent Component Analysis and Machine Classifiers

  • Chih-I Hung
  • Po-Lei Lee
  • Yu-Te Wu
  • Li-Fen Chen
  • Tzu-Chen Yeh
  • Jen-Chuen Hsieh
Article

Abstract

Motor imagery electroencephalography (EEG), which embodies cortical potentials during mental simulation of left or right finger lifting tasks, can be used to provide neural input signals to activate a brain computer interface (BCI). The effectiveness of such an EEG-based BCI system relies on two indispensable components: distinguishable patterns of brain signals and accurate classifiers. This work aims to extract two reliable neural features, termed contralateral and ipsilateral rebound maps, by removing artifacts from motor imagery EEG based on independent component analysis (ICA), and to employ four classifiers to investigate the efficacy of rebound maps. Results demonstrate that, with the use of ICA, recognition rates for four classifiers (fisher linear discriminant (FLD), back-propagation neural network (BP-NN), radial-basis function neural network (RBF-NN), and support vector machine (SVM)) improved significantly, from 54%, 54%, 57% and 55% to 70.5%, 75.5%, 76.5% and 77.3%, respectively. In addition, the areas under the receiver operating characteristics (ROC) curve, which assess the quality of classification over a wide range of misclassification costs, also improved from .65, .60, .62, and .64 to .74, .76, .80 and .81, respectively.

Keywords

Brain computer interface (BCI) Rebound maps Fisher linear discriminant (FLD) Back-propagation neural network (BP-NN) Radial-basis function neural network (RBF-NN) Support vector machine (SVM) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Belouchrani, A., K. Abed-Meraim, J. F. Cardoso, and E. Moulines. A blind source separation technique using second-order statistics. IEEE Trans., Signal Process. (see also IEEE Trans. Acoustics, Speech,Signal Process.) 45(2):434–444, 1997.Google Scholar
  2. 2.
    Cichock, A., and S. I. Amari. Adaptive blind signal and image processing. England: Wiley, 2002.Google Scholar
  3. 3.
    Clochon, P., J. M. Fontbonne, N. Lebrun, and P. Etevenon. A new method for quantifying EEG event-related desynchronization: amplitude envelope analysis. Electroencephalogr. Clin. Neuro-Physiol.. 98:126–129, 1996.CrossRefGoogle Scholar
  4. 4.
    Cover, T. M. Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE trans. Electron. Comput. EC-14:326–334, 1965.Google Scholar
  5. 5.
    Cover, T. M., and J. A. Thomas. Elements of Information Theory. New York: Wiley, 1991.Google Scholar
  6. 6.
    Cover, T. M. Capacity Problems for Linear Machines. Washington, DC: Thompson Book, Pattern Recognition, 1988, pp. 293–289.Google Scholar
  7. 7.
    Cristianini, N., and J. Shawe-Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge: Cambridge University Press, 2000.Google Scholar
  8. 8.
    Daubechies, I. Ten Lectures on Wavelets. Philadelphia: Society for Induced and Applied Mathematics, 1992.Google Scholar
  9. 9.
    Delorme, A., and S. Makeig. EEG changes accompanying leraned regulation of 12-Hz EEG activity. IEEE Trans. Neural Syst. Rehab. Eng. 11(2):133–137, 2003.CrossRefGoogle Scholar
  10. 10.
    Ebrahimi T., J. M. Vesin, and G. Garcia. Brain-computer interface a new frontier in multimedia communication. IEEE Signal Process. Mag. 20(1):14–24, 2003.CrossRefGoogle Scholar
  11. 11.
    Guger, C., A. Schlogl, C. Neuper, D. Walterspacher, T. Strein, and G. Pfurtscheller. Rapid prototyping of an EEG-based brain-computer interface (BCI). IEEE Trans. Neural Syst. Rehab. Eng. 9(1):49–58, 2001.CrossRefGoogle Scholar
  12. 12.
    Haykin, S. Neural Network: A Comprehensive Foundation. New York: Macmillan. 1994.Google Scholar
  13. 13.
    Hung, C. I., P. L. Lee, Y. T. Wu, L. F. Chen, T. C. Yeh, and J. C. Hsieh. Single-trial quantification of EEG imagery Beta-band post-movement rebound in finger lifting task using independent component analysis (ICA). In: Proceeding of the 2003 World Congress on Medical Physics and Biomedical Engineering. Sydney, Australia, 2003.Google Scholar
  14. 14.
    Hyvarinen, A., J. Karhunen, and E. Oja. Independent Component Analysis. New York: Wiley, 2001.Google Scholar
  15. 15.
    Jung, T. P., S. Makeig, M. Westerfield, J. Townsend, E. Courchesne, and T. J. Sejnowski. Analysis and visualization of single-trial event-related potentials. Human Brain Mapping. 14:166–185, 2001.CrossRefPubMedGoogle Scholar
  16. 16.
    Jung, T. P., S. Makeig, M. J. Mckeown, A. J. Bell, T. W. Lee, and T. J. Sejnowski. Imaging Brain Dynamics Using Independent Component Analysis. Proc. IEEE 89(7):1107–1122, 2001.CrossRefGoogle Scholar
  17. 17.
    Kelly, S., D. Burke, P. de Chazal, and R. Reilly. Parametric models and spectral analysis for classification in brain-computer interfaces. In: Proceedings of the 14th International Conference on Digital Signal Processin. Greece, July 2002.Google Scholar
  18. 18.
    Lee, P. L., Y. T. Wu, L. F. Chen, Y. S. Chen, C. M. Cheng, T. C. Yeh, L. T. Ho, M. S. Chang, and J. C. Hsieh. ICA-based spatiotemporal approach for single-trial analysis of post-movement MEG beta synchronization. NeuroImage. 20:2010–2030, 2003.CrossRefPubMedGoogle Scholar
  19. 19.
    Lins, O., T. Picton, P. Berg, and M. Scherg. Ocular artifacts in EEG and event-related potentials. I: Scalp topography. Brain Topogr. 6:51–63, 1993.CrossRefPubMedGoogle Scholar
  20. 20.
    Makeig, S., S. Enghoff, T. P. Jung, and T. J. Sejnowski. A natural basis for efficient brain-actuated control. IEEE Trans. Rehab. Eng. 8(2):208–211, 2000.CrossRefGoogle Scholar
  21. 21.
    Makeig, S., A. J. Bell, T. P. Jung, and T. J. Sejnowski. Independent component analysis of electroencephalographic data. Advances in Neural Information Processing Systems 8. 145–151, 1996.Google Scholar
  22. 22.
    Muller-Gerking, J., G. Pfurtscheller, and H. Flyvbjerg. Designing optimal spatial filters for single-trial EEG classification in a movement task. Clin. Neurophysiol. 110:787–798, 1999.CrossRefPubMedGoogle Scholar
  23. 23.
    Niedermeyer, E., and F. H. Lopes da Silva. Electroencephalography : Basic Principles, Clinical Applications, and Related Fields. Baltimore, Md. : Williams & Wilkins, 1999, pp. 958–967.Google Scholar
  24. 24.
    Obermaier, B., C. Neuper, C. Guger, and G. Pfurtscheller. Information Transfer Rate in a Five-Classes Brain-Computer Interface. IEEE Trans. Rehab. Eng. 9(3):283–288, 2001.CrossRefGoogle Scholar
  25. 25.
    Parra, L., and P. Sajda. Blind source separation via generalized eigenvalue decomposition. J. Machine Learning Res. 4:1261–1269, 2003.Google Scholar
  26. 26.
    Pfurtscheller, G., and F. H. Lopes da Silva. Event-related desynchronization. Handbook of Electroencephalography and Clinical Neurophysiology, Revised Series, Vol. 6. Amsterdam: Elsevier Science, 1999, pp. 303–325.Google Scholar
  27. 27.
    Pfurtscheller, G., and A. Aranibar. Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movements. Electroencephalogr. Clin. Neurophysiol. 46:138–146, 1979.CrossRefPubMedGoogle Scholar
  28. 28.
    Pfurtscheller, G., A. Stancak Jr, and C. Neuper. Post-movement beta synchronization. A correlate of an idling motor area? Electroencephalogr. Clin. Neuro- Physiol. 98:281–293, 1996.CrossRefGoogle Scholar
  29. 29.
    Pfurtscheller, G., C. Neuper, A. Schlogl, and K. Lugger. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans. Rehab. Eng. 63:316–325, 1998.CrossRefGoogle Scholar
  30. 30.
    Pfurtscheller, G., C. Guger, G. Muller, G. Krausz, and C. Neuper. Brain oscillations control hand orthosis in a tetraplegic. Neurosci. Lett. 292:211–214, 2000.CrossRefPubMedGoogle Scholar
  31. 31.
    Pregenzer, M., and G. Pfurtscheller. Frequency component selection for an EEG-based brain to computer interface. IEEE Trans. Rehab. Eng. 7:413–419, 1999.CrossRefGoogle Scholar
  32. 32.
    Tang A. C., B. A. Pearlmutter, M. Zibulevsky, and S. A. Carter. Blind source separation of multichannel neuromagnetic responses. Neurocomput. 32–33:1115–1120, 2000.CrossRefGoogle Scholar
  33. 33.
    Vapnik, V. N. The Nature of Statistical Learning Theory, 2nd ed., New York: Springer-Verlag, 2000.Google Scholar
  34. 34.
    Wolpaw, J. R., D. J. McFarland, G.W. Neat, and C. A. Forneris. An EEG-based brain—computer interface for cursor control. Electroenceph. Clin. Neurophysiol. 78:252–259, 1991.CrossRefPubMedGoogle Scholar
  35. 35.
    Wolpaw, J. R., D. J. McFarland, and T. M. Vaughan. Brain—computer interface research at the Wadsworth Center. IEEE Trans. Rehab. Eng. 8:222–226, 2000.CrossRefGoogle Scholar
  36. 36.
    Wolpaw, J. R., N. Birbaumer, D. J. McFarlanda, G. Pfurtschellere, and T. M. Vaughan. Brain—computer interfaces for communication and control (Invited Review). Clin. Neurophysiol. 113:767–791, 2002.CrossRefPubMedGoogle Scholar
  37. 37.
    Wu, Y. T., H. Y. Chen, P. L. Lee, Y. S. Chen, L. F. Chen, and J. C. Hsieh. Classifying MEG Data of Left, Right Index Finger Movement and Resting State Using Support Vector Machine (SVM). In: Proceedings, BioMag 13th International Conference on Biomagnetism, 2002, pp. 1042–1044.Google Scholar
  38. 38.
    Wu, Y. T., P. L. Lee, L. F. Chen, T. C. Yeh, and J. C. Hsieh. Single-trial quantification of imagery beta-band Murhythm in finger lifting task using independent component analysis (ICA). In: Proceedings, BioMag 13th International Conference on Biomagnetism, 2002, pp. 1045–1047.Google Scholar
  39. 39.
    Wu, Y. T., P. L. Lee, L. F. Chen, T. C. Yeh, and J. C. Hsieh. Quantification of movement-related modulation on beta activity of single-trial magnetoencephalography measuring using independent component analysis (ICA). In: Proceedings, 1st International IEEE EMBS Conference on Neural Engineering, 2003, pp. 396–398.Google Scholar

Copyright information

© Biomedical Engineering Society 2005

Authors and Affiliations

  • Chih-I Hung
    • 1
    • 2
  • Po-Lei Lee
    • 2
  • Yu-Te Wu
    • 1
    • 2
    • 3
  • Li-Fen Chen
    • 2
    • 4
  • Tzu-Chen Yeh
    • 2
    • 5
  • Jen-Chuen Hsieh
    • 2
    • 3
    • 5
    • 6
  1. 1.Institute of Radiological SciencesNational Yang-Ming UniversityTaipeiTaiwan
  2. 2.Laboratory of Integrated Brain Research, Department of Medical Research and EducationTaipei Veterans General HospitalTaipeiTaiwan
  3. 3.Institute of Health Informatics and Decision MakingSchool of Medicine, National Yang-Ming UniversityTaipeiTaiwan
  4. 4.Center for NeuroscienceNational Yang-Ming UniversityTaipeiTaiwan
  5. 5.Faculty of MedicineSchool of Medicine, National Yang-Ming UniversityTaipeiTaiwan
  6. 6.Institute of NeuroscienceSchool of Life Science, National Yang-Ming UniversityTaipeiTaiwan

Personalised recommendations