ICA for Detecting Artifacts in a Few Channel BCI

  • Izabela Rejer
  • Paweł GórskiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9375)


Eye blinking, body parts movements, power line, and many other internal and external artifacts deteriorate the quality of EEG signal and the whole BCI system. There are some methods for removing artifacts or at least reducing their influence on the BCI system, however, they do not work efficiently when only few channels are used in the system and an automatic artifact elimination is required. The paper presents our approach to deal with artifacts in such a case by adding artificially generated signals to the set of originally recorded signals and to perform Independent Component Analysis on such an enlarged signal set. Our initial experiment, reported in this paper, shows that such an approach results in a better classification precision than when Independent Component Analysis is performed directly on the original signals set.


Brain computer interface BCI EEG Preprocessing ICA Independent Component Analysis Artifact removal 


  1. 1.
    Vigario, R.N.: Extraction of ocular artifacts from EEG using independent component analysis. Electroencephalogr. Clin. Neurophysiol. 103(3), 395–404 (1997)CrossRefGoogle Scholar
  2. 2.
    Wallstrom, G.L., Kass, R.E., Miller, A., Cohn, J.F., Fox, N.A.: Automatic correction of ocular artifacts in the EEG: a comparison of regression-based and component-based methods. Int. J. Psychophysiol. 53(2), 105–119 (2004)CrossRefGoogle Scholar
  3. 3.
    Guerrero-Mosquera, C., Vazquez, A.N.: Automatic removal of ocular artifacts from eeg data using adaptive filtering and independent component analysis. In: 17th European Signal Processing Conference (EUSIPCO 2009). Glasgow, Scotland (August 24–28 2009)Google Scholar
  4. 4.
    Rejer, I., Gorski P.: Benefits of ICA in the case of a few channel EEG. In: 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society of the IEEE Engineering in Medicine and Biology Society in MiCo, Milano (still in-print) (August 25–29 2015)Google Scholar
  5. 5.
    Shlens, J.: A tutorial on principal component analysis derivation. Accessed May 2015
  6. 6.
    Switzer P., Green A.: Min/max autocorrelation factors for multivariate spatial imagery. In: Technical report 6, Department of Statistics, Stanford University (1984)Google Scholar
  7. 7.
    Ramoser, H., Muller-Gerking, J., Pfurtscheller, G.: Optimal spatial filtering of single trial EEG during imagined handmovement. IEEE Trans. Rehabil. Eng. 8(4), 441–446 (2000)CrossRefGoogle Scholar
  8. 8.
    Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. 13(4–5), 411–430 (2000)CrossRefGoogle Scholar
  9. 9.
    Jung, T.P., Humphries, C., Lee, T.W., Makeig, S., McKeown, M.J., Iragui, V., Sejnowski, T.J.: Extended ICA removes artifacts from electroencephalographic recordings. Adv. Neural Inf. Process. Syst. 10, 894–900 (1998)Google Scholar
  10. 10.
    Delorme, A., Palmer, J., Onton, J., Oostenveld, R., Makeig, S.: Independent EEG sources are dipolar. PloS ONE 7(2), e30135 (2012)CrossRefGoogle Scholar
  11. 11.
    Data set III, II BCI Competition, motor imaginary.
  12. 12.
    Oja, E., Yuan, Z.: The FastICA algorithm revisited: convergence analysis. IEEE Trans. Neural Netw. 17(6), 1370–1381 (2006)CrossRefGoogle Scholar
  13. 13.
    Raudys, S.J., Jain, A.K.: Small sample size effects in statistical pattern recognition: recommendations for practitioners. IEEE Trans. Pattern Anal. Mach. Intell. 13(3), 252–264 (1991)CrossRefGoogle Scholar
  14. 14.
    Tibshirani, R.: Regression shrinkage and selection via the lasso. J. Roy. Stat. Soc. Ser. B (Methodol.) 58(1), 267–288 (1996)MathSciNetzbMATHGoogle Scholar
  15. 15.
    Fung, G.M., Mangasarian, O.L., Shavlik, J.W.: Knowledge-based support vector machine classifiers. Adv. Neural Inf. Process. Syst. 15, 537–544 (2002)Google Scholar
  16. 16.
    Pfurtschellera, G., Lopes da Silvab, F.H.: Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin. Neurophysiol. 110, 1842–1857 (1999)CrossRefGoogle Scholar
  17. 17.
    McFarland, D.J., Miner, L.A., Vaughan, T.M., Wolpaw, J.R.: Mu and Beta rhythm topographies during motor imagery and actual movements. Brain Topogr. 12(3), 177–186 (2000)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Faculty of Computer Science and Information TechnologyWest Pomeranian University of Technology SzczecinSzczecinPoland

Personalised recommendations