Automatic Artefact Removal from Event-related Potentials via Clustering



This paper outlines a method for automatic artefact removal from multichannel recordings of event-related potentials (ERPs). The proposed method is based on, firstly, separation of the ERP recordings into independent components using the method of temporal decorrelation source separation (TDSEP). Secondly, the novel lagged auto-mutual information clustering (LAMIC) algorithm is used to cluster the estimated components, together with ocular reference signals, into clusters corresponding to cerebral and non-cerebral activity. Thirdly, the components in the cluster which contains the ocular reference signals are discarded. The remaining components are then recombined to reconstruct the clean ERPs.


event-related potentials auto-mutual information clustering EEG automatic artefact removal 


  1. 1.
    R. Q. Quiroga, M. Atienza, J. L. Cantero, and M. L. A. Jongsma, “What Can We Learn from Single-trial Event-related Potentials?,” Chaos and Complexity Letters, vol. 2, no. 2, 2006, (forthcoming)Google Scholar
  2. 2.
    G. Zouridakis and D. Iyer, “Comparison between ICA and Wavelet-based Denoising of Single-trial Evoked Potentials,” in Proc. 26th Annual Intl. Conf. of the IEEE EMBS, San Fransisco, USA, 2004, pp. 87–90.Google Scholar
  3. 3.
    R. Q. Quiroga and H. Garcia, “Single-trial Event-related Potentials with Wavelet Denoising”, Clin. Neurophysiol., vol. 114, 2003, pp. 376–390.CrossRefGoogle Scholar
  4. 4.
    D. J. Doyle, “Some Comments on the Use of Wiener Filtering in the Estimation of Evoked Potentials,” Electroencephalogr. Clin. Neurophysiol., vol. 38, 1975, p. 533.CrossRefGoogle Scholar
  5. 5.
    S. Cerutti, G. Basselli, and G. Pavesi, “Single Sweep Analysis of Visual Evoked Potentials through a Model of Parametric Identification,” Biol. Cybern., vol. 56, 1987, p. 111.CrossRefGoogle Scholar
  6. 6.
    M. Fatourechi, S. G. Mason, G. E. Birch, and R. K. Ward, “A Wavelet-based Approach for the Extraction of Event Related Potentials from EEG,” in Proc. ICASSP’04, 2004. pp. II-737–II-740.Google Scholar
  7. 7.
    T.-P. Jung, S. Makeig, C. Humphries, T.-W. Lee, M. J. McKeown, V. Iragui, and T. J. Sejnowski, “Removing Electroencephalographic Artefacts by Blind Source Separation,” Psychophysiology, vol. 37, 2000, pp. 163–178.CrossRefGoogle Scholar
  8. 8.
    C. J. James and O. J. Gibson, “Temporally Constrained ICA: An Application to Artefact Rejection in Electromagnetic Brain Signal Analysis,” IEEE Trans. Biomed. Eng., vol. 50, no. 9, (September) 2003, pp. 1108–1116.CrossRefGoogle Scholar
  9. 9.
    N. Ille, P. Berg, and M. Scherg, “Artifact Correction of the Ongoing EEG Using Spatial Filters Based on Artefact and Brain Signal Topographies,” J. Clin. Neurophysiol., vol. 19, no. 2, 2002, pp. 113–124.CrossRefGoogle Scholar
  10. 10.
    V. Schetinin, “An Evolving Cascade Neural Network Technique for Cleaning Sleep Electroencephalograms,” Neural Comput. Appl., vol. 17, no. 7, 2005 pp. 1577–1601.CrossRefGoogle Scholar
  11. 11.
    C. A. Joyce, I. F. Gorodnitsky, and M. Kutas, “Automatic Removal of Eye Movement and Blink Artefacts from EEG Data Using Blind Component Separation,” Psychophysiology, vol. 41, 2003, pp. 313–325.CrossRefGoogle Scholar
  12. 12.
    D. R. Brillinger, “Second-order Moments and Mutual Information in the Analysis of Time Series,” in Recent Advances in Statistical Methods. Imperial College Press, London, 2002, pp. 64–76.Google Scholar
  13. 13.
    A. Dionísio, R. Menezes, and D. A. Mendes, “Mutual Information: A Dependence Measure for Nonlinear Time Series,” EconWPA Econometrics series, No. 0311003, 2003.Google Scholar
  14. 14.
    A. Kraskov, H. Stögbauer, and P. Grassberger, “Estimating Mutual Information,” Phys. Rev. E, vol. 69, no. 6, 2004, pp. 066138.CrossRefGoogle Scholar
  15. 15.
    N. Nicolaou and S. J. Nasuto, “Robustness of Mutual Information to Inter-subject Variability for Automatic Artefact Removal from EEG,” in Proc. 27th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), Shanghai, China, 2005.Google Scholar
  16. 16.
    A. Ziehe and K.-R. Muller, “TDSEP—An Efficient Algorithm for Blind Source Separation using Time Structure,” in Proc. ICANN98, 1998. pp. 675–680.Google Scholar
  17. 17.
    A. Hyvärinen and E. Oja, “Independent Component Analysis: A Tutorial,” in Neural Networks: ICA—Algorithms and Applications, 1999.Google Scholar
  18. 18.
    R. Mojena, “Hierarchical Grouping Methods and Stopping Rules: An Evaluation,” Comput. J., vol. 20, no. 4, 1977, pp. 359–363.CrossRefGoogle Scholar
  19. 19.
    A. Schlögl, P. Anderer, M.-J. Barbanoj, G. Dorffner, G. Gruber, G. Klösch, J. L. Lorenzo, P. Rappelsberger, and G. Pfurtscheller, “Artifacts in the Sleep EEG—A Database for the Evaluation of Automated Processing Methods,” in Proc. 3rd Int. Congress of WFSRS, Dresden, 1999. pp. 5–8.Google Scholar
  20. 20.
    H. Berger, “Uber das Electrenkephalogramm des Menchen,” Arch. Psychiatr. Nervenkr., vol. 87, 1929, pp. 527–570.CrossRefGoogle Scholar
  21. 21.
    C. Westbrook, Handbook of MRI technique, 2nd ed., Blackwell Publishing, 1999.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.CIRG, School of Systems EngineeringUniversity of ReadingReadingUK

Personalised recommendations