Brain Topography

, Volume 23, Issue 2, pp 186–193 | Cite as

On Optimal Channel Configurations for SMR-based Brain–Computer Interfaces

  • Claudia Sannelli
  • Thorsten Dickhaus
  • Sebastian Halder
  • Eva-Maria Hammer
  • Klaus-Robert Müller
  • Benjamin Blankertz
Original Paper

Abstract

One crucial question in the design of electroencephalogram (EEG)-based brain–computer interface (BCI) experiments is the selection of EEG channels. While a setup with few channels is more convenient and requires less preparation time, a dense placement of electrodes provides more detailed information and henceforth could lead to a better classification performance. Here, we investigate this question for a specific setting: a BCI that uses the popular CSP algorithm in order to classify voluntary modulations of sensorimotor rhythms (SMR). In a first approach 13 different fixed channel configurations are compared to the full one consisting of 119 channels. The configuration with 48 channels results to be the best one, while configurations with less channels, from 32 to 8, performed not significantly worse than the best configuration in cases where only few training trials are available. In a second approach an optimal channel configuration is obtained by an iterative procedure in the spirit of stepwise variable selection with nonparametric multiple comparisons. As a surprising result, in the second approach a setting with 22 channels centered over the motor areas was selected. Thanks to the acquisition of a large data set recorded from 80 novice participants using 119 EEG channels, the results of this study can be expected to have a high degree of generalizability.

Keywords

Brain–computer interface Common spatial patterns Channel selection EEG Machine learning Variable selection 

References

  1. Al-Ani A, Al-Sukker A (2006) Effect of feature and channel selection on EEG classification. In: Engineering in medicine and biology society, 2006. EMBS ’06. 28th annual international conference of the IEEE, pp 2171–2174. doi:10.1109/IEMBS.2006.259833
  2. Blankertz B, Tomioka R, Lemm S, Kawanabe M, Müller K-R (2008) Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Proc Mag 25(1):41–56CrossRefGoogle Scholar
  3. Blankertz B, Dornhege G, Krauledat M, Müller K-R, Curio G (2007) The non-invasive Berlin brain–computer interface: fast acquisition of effective performance in untrained subjects. NeuroImage 37(2):539–550CrossRefPubMedGoogle Scholar
  4. Dornhege G, del R Millán J, Hinterberger T, McFarland D, Müller KR (eds) (2007) Toward brain–computer interfacing. MIT Press, Cambridge, MAGoogle Scholar
  5. Draper N, Smith H (1981) Applied regression analysis, 2nd edn. Wiley, New YorkGoogle Scholar
  6. Engelbrecht AP (2005) Fundamentals of computational swarm intelligence. Wiley, Chichester, UKGoogle Scholar
  7. Farquhar J, Hill NJ, Lal TN, Schölkopf B (2006) Regularised CSP for sensor selection in BCI. In: Proceedings of the 3rd international brain–computer interface workshop and training course, Graz, pp 14–15Google Scholar
  8. Friedman JH (1989) Regularized discriminant analysis. J Am Stat Assoc 84(405):165–175CrossRefGoogle Scholar
  9. Gibbons JD (1985) Nonparametric statistical inference, 2nd edn. Marcel Dekker Inc., New YorkGoogle Scholar
  10. Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1–3):389–422CrossRefGoogle Scholar
  11. Hollander M, Wolfe DA (1973) Nonparametric statistical methods. Wiley, New YorkGoogle Scholar
  12. Hocking RR (1976) The analysis and selection of variables in a linear regression. Biometrics 32:1–49CrossRefGoogle Scholar
  13. Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, New YorkCrossRefGoogle Scholar
  14. Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, New YorkGoogle Scholar
  15. Lal TN, Schröder M, Hinterberger T, Weston J, Bodgan M, Birbaumer N, Schölkopf B (2004) Support vector channel selection in BCI. IEEE Trans Bio-Med Eng 51(6):1003–1010CrossRefGoogle Scholar
  16. Lv J, Meichun L (2008) Common spatial pattern and particle swarm optimization for channel selection in BCI. In: ICICIC ’08: Proceedings of the 2008 3rd international conference on innovative computing information and control. IEEE computer society, Washington, DC, pp 457–460. doi:10.1109/ICICIC.2008.196
  17. McFarland DJ, McCane LM, David SV, Wolpaw JR (1997) Spatial filter selection for EEG-based communication. Electroencephalogr Clin Neurophysiol 103(3):386–394. doi:10.1016/S0013-4694(97)00022-2 CrossRefPubMedGoogle Scholar
  18. Naeem M, Brunner C, Pfurtscheller G (2009) Dimensionality reduction and channel selection of motor imagery electroencephalographic data. Comput Intell Neurosci 2009, Article ID 537504, 8 pp. doi:10.1155/2009/537504
  19. Popescu F, Fazli S, Badower Y, Blankertz B, Müller K-R (2007) Single trial classification of motor imagination using 6 dry EEG electrodes. PLoS ONE 2(7):e637. doi:10.1371/journal.pone.0000637 CrossRefPubMedGoogle Scholar
  20. Ramoser H, Müller-Gerking J, Pfurtsheller G (2000) Optimal Spatial Filtering of single trial EEG during imagined hand movement. IEEE Trans Rehab Eng 4(8):441-446CrossRefGoogle Scholar
  21. Vidaurre C, Krämer N, Blankertz Benjamin, Schlögl A (2009) Time domain parameters as a feature for eeg-based brain computer interfaces. Neural Networks, Special Issue 22(9):1201–1358. doi:10.1016/j.neunet.2009.07.020 Google Scholar
  22. Vidaurre C, Schlögl A (2008) Comparison of adaptive features with linear discriminant classifier for brain computer interfaces. In: Engineering in medicine and biology society, 2008. EMBS 2008. 30th annual international conference of the IEEE, pp 173–176. doi:10.1109/IEMBS.2008.4649118
  23. Wang Y, Gao X, Gao S (2005) Common spatial pattern method for channel selection in motor imagery based brain–computer interface. In: Proceedings of the 27th international IEEE EMBS conference, pp 5392–5395. doi:10.1109/IEMBS.2005.1615701

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Claudia Sannelli
    • 1
  • Thorsten Dickhaus
    • 1
  • Sebastian Halder
    • 2
  • Eva-Maria Hammer
    • 2
  • Klaus-Robert Müller
    • 1
  • Benjamin Blankertz
    • 1
    • 3
  1. 1.Machine Learning LaboratoryBerlin Institute of TechnologyBerlinGermany
  2. 2.Institute of Medical Psychology and Behavioral NeurobiologyUniversity of TübingenTübingenGermany
  3. 3.Intelligent Data Analysis Group, Fraunhofer FIRSTBerlinGermany

Personalised recommendations