Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis

  title={Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis},
  author={Aapo Hyv{\"a}rinen and Pavan Ramkumar and Lauri Parkkonen and Riitta Hari},
  volume={49 1},
Analysis of spontaneous EEG/MEG needs unsupervised learning methods. While independent component analysis (ICA) has been successfully applied on spontaneous fMRI, it seems to be too sensitive to technical artifacts in EEG/MEG. We propose to apply ICA on short-time Fourier transforms of EEG/MEG signals, in order to find more "interesting" sources than with time-domain ICA, and to more meaningfully sort the obtained components. The method is especially useful for finding sources of rhythmic… CONTINUE READING
59 Citations
31 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 59 extracted citations


Publications referenced by this paper.
Showing 1-10 of 31 references

Independent Component Analysis. Wiley Interscience

  • A. Hyvärinen, J. Karhunen, E. Oja
  • 2001
Highly Influential
7 Excerpts

Scale mixing of symmetric distributions with zero means

  • E.M.L. Beale, C. L. Mallows
  • The Annals of Mathematical Statistics
  • 1959
Highly Influential
5 Excerpts

A blind source separation technique based on second order statistics

  • A. Belouchrani, K. A. Meraim, Cardoso, J.-F, E. Moulines
  • IEEE Trans. on Signal Processing
  • 1997
Highly Influential
4 Excerpts

Identification of stimulus-related and intrinsic networks by spatial independent component analysis of MEG signals. Abstract presented at the Society for Neuroscience Meeting, San Diego, California

  • P. Ramkumar, L. T. Parkkonen, B. J. He, M. E. Raichle, M. S. Hämäläinen, R. Hari
  • 2007
2 Excerpts

Spatiotemporal dynamics in fMRI recordings revealed with complex independent component analysis

  • J. Anemüller, Duann, J.-R, T. J. Sejnowski, S. Makeig
  • Neurocomputing 69,
  • 2006
1 Excerpt

Similar Papers

Loading similar papers…