Medical & Biological Engineering & Computing

, Volume 47, Issue 4, pp 413–423 | Cite as

Independent component analysis: comparison of algorithms for the investigation of surface electrical brain activity

  • Matthias Klemm
  • Jens Haueisen
  • Galina Ivanova
Original Article


We compared the performance of 22 algorithms for independent component analysis with the aim to find suitable algorithms for applications in the field of surface electrical brain activity analysis. The quality of the separation is assessed with four performance measures: a correlation coefficient based index, a signal-to-interference ratio, a signal-to-distortion-ratio and the computational demand. Artificial data are used consisting of typical electroencephalogram and evoked potentials signal patterns, e.g. spikes, polyspikes, sharp waves and spindles. We evaluate different noise scenarios and the influence of pre-whitening. The comparisons reveal considerable differences between the algorithms, especially concerning the computational load. Algorithms based on the time structure of the data set seem to have advantages in separation quality especially for sine-shaped signals. Derivates of FastICA and Infomax also attain good results. Our results can serve as a reference for selecting a task-specific algorithm to analyze a large number of signal patterns occurring in the surface electrical brain activity.


Independent component analysis Electrical brain activity EEG simulations EEG processing Blind source separation 



This work was in part supported by the German Ministry of Science (03IP605) and the German Research Council (DFG Ha 2899/7-1).

Supplementary material

11517_2009_452_MOESM1_ESM.doc (88 kb)
Supplementary material 1 (DOC 88 kb)


  1. 1.
    Abdi H (2007) Encyclopedia of measurement and statistics. Sage Publications Inc., Thousand OaksGoogle Scholar
  2. 2.
    De Lucia M, Fritschy J et al (2008) A novel method for automated classification of epileptiform activity in the human electroencephalogram-based on independent component analysis. Med Biol Eng Comput 46(3):263–272. doi: 10.1007/s11517-007-0289-4 CrossRefGoogle Scholar
  3. 3.
    Delorme A, Makeig S (2004) EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134(1):9–21. doi: 10.1016/j.jneumeth.2003.10.009 CrossRefGoogle Scholar
  4. 4.
    DiPietroPaolo D, Müller H et al (2006) Noise reduction in magnetocardiography by singular value decomposition and independent component analysis. Med Biol Eng Comput 44(6):489–499. doi: 10.1007/s11517-006-0055-z CrossRefGoogle Scholar
  5. 5.
    Ebe M, Homma I (1994) Leitfaden für die EEG-Praxis. G. Fischer Verlag, StuttgartGoogle Scholar
  6. 6.
    Fisher AC, El-Deredy W et al (2007) Removal of eye movement artefacts from single channel recordings of retinal evoked potentials using synchronous dynamical embedding and independent component analysis. Med Biol Eng Comput 45(1):69–77. doi: 10.1007/s11517-006-0123-4 CrossRefGoogle Scholar
  7. 7.
    Giannakopoulos X, Karhunen J et al (1999) An experimental comparison of neural algorithms for independent component analysis and blind separation. Int J Neural Syst 9(2):99–114. doi: 10.1142/S0129065799000101 CrossRefGoogle Scholar
  8. 8.
    Glass K, Frishkoff G et al (2004) A framework for evaluating ICA methods of artifact removal from multichannel EEG. Lect Notes Comput Sci 3195/2004:1033–1040Google Scholar
  9. 9.
    Göhler W (1986) Höhere Mathematik. VEB Deutscher Verlag für Grundstoffindustrie, LeipzigGoogle Scholar
  10. 10.
    Hyvarinen A, Karhunen J et al (2001) Independent component analysis. Wiley, New YorkCrossRefGoogle Scholar
  11. 11.
    James CJ, Hesse CW (2005) Independent component analysis for biomedical signals. Physiol Meas 26(1):R15–R39CrossRefGoogle Scholar
  12. 12.
    Knuth KH (1998) Maximum entropy and Bayesian methods. Springer, BoiseGoogle Scholar
  13. 13.
    Knuth KH, Shah AS et al (2006) Differentially variable component analysis: identifying multiple evoked components using trial-to-trial variability. J Neurophysiol 95(5):3257–3276. doi: 10.1152/jn.00663.2005 CrossRefGoogle Scholar
  14. 14.
    Krishnaveni V, Jayaraman S et al (2005) Comparison of independent component analysis algorithms for removal of ocular artifacts from electroencephalogram. Meas Sci Rev 5(2):67–78Google Scholar
  15. 15.
    Krishnaveni V, Jayaraman S et al (2006) Application of mutual information based least dependent component analysis (MILCA) for removal of ocular artifacts from electroencephalogram. Meas Sci Rev 1(1):63–74Google Scholar
  16. 16.
    Li Y, Powers D et al (2000) Comparison of blind source separation algorithms. World Scientific and Engineering Society Press, pp 18–21Google Scholar
  17. 17.
    Milanesi M, Martini N et al (2008) Independent component analysis applied to the removal of motion artifacts from electrocardiographic signals. Med Biol Eng Comput 46(3):251–261. doi: 10.1007/s11517-007-0293-8 CrossRefGoogle Scholar
  18. 18.
    Nicolaou N, Nasuto SJ (2003) Comparison of temporal and standard independent component analysis (ICA) algorithms for EEG analysis. In: Tenth international conference on neural information processing (ICANN/ICONIP’03), pp 157–160Google Scholar
  19. 19.
    Rodenbeck A, Binder R et al (2006) A review of sleep EEG patterns. Part I: A compilation of amended rules for their visual recognition according to Rechtschaffen and Kales. Somnol Sleep Res Sleep Med 10(4):159–175Google Scholar
  20. 20.
    Stogbauer H, Kraskov A et al (2004) Least-dependent-component analysis based on mutual information. Phys Rev E Stat Nonlin Soft Matter Phys 70(6 Pt 2):66–123MathSciNetGoogle Scholar
  21. 21.
    Truccolo W, Knuth KH et al (2003) Estimation of single-trial multicomponent ERPs: differentially variable component analysis (dVCA). Biol Cybern 89(6):426–438. doi: 10.1007/s00422-003-0433-7 zbMATHCrossRefGoogle Scholar
  22. 22.
    Vincent E, Rémi G et al (2006) Performance measurement in blind audio source separation. IEEE Trans Audio Speech Lang Process 14(4). doi: 10.1109/TSA.2005.858005
  23. 23.
    Weber H (1992) Einführung in die Wahrscheinlichkeitsrechnung und Statistik für Ingenieure. Teubner, StuttgartzbMATHGoogle Scholar
  24. 24.
    Wiklund U, Karlsson M et al (2007) Adaptive spatio-temporal filtering of disturbed ECGs: a multi-channel approach to heartbeat detection in smart clothing. Med Biol Eng Comput 45(6):515–523. doi: 10.1007/s11517-007-0183-0 CrossRefGoogle Scholar
  25. 25.
    Xu W, Erdogmus D et al (2004) Independent component analysis and blind signal separation. Springer, HeidelbergGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2009

Authors and Affiliations

  1. 1.Biomedical Engineering Department, Faculty of Computer Science and Automation, Institute of Biomedical Engineering and InformaticsTechnische Universität IlmenauIlmenau, ThuringiaGermany
  2. 2.Department of Signal Processing and Pattern Recognition, Biomedical Signal Processing, Faculty of Mathematics and Natural Sciences II, Institute of Computer ScienceHumboldt-Universität zu BerlinBerlinGermany

Personalised recommendations