Cover
Vol. 15 No. 1 (2019)

Published: July 31, 2019

Pages: 1-12

Original Article

Comparison of Complex-Valued Independent Component Analysis Algorithms for EEG Data

Ali Al-Saegh 1
1Computer Engineering Department University of Mosul Mosul, Iraq
History
  • Received: May 31, 2019
  • Available Online: July 31, 2019
DOI

https://doi.org/10.37917/ijeee.15.1.1

Abstract

Independent Component Analysis (ICA) has been successfully applied to a variety of problems, from speaker identification and image processing to functional magnetic resonance imaging (fMRI) of the brain. In particular, it has been applied to analyze EEG data in order to estimate the sources form the measurements. However, it soon became clear that for EEG signals the solutions found by ICA often depends on the particular ICA algorithm, and that the solutions may not always have a physiologically plausible interpretation. Therefore, nowadays many researchers are using ICA largely for artifact detection and removal from EEG, but not for the actual analysis of signals from cortical sources. However, a recent modification of an ICA algorithm has been applied successfully to EEG signals from the resting state. The key idea was to perform a particular preprocessing and then apply a complex- valued ICA algorithm. In this paper, we consider multiple complex-valued ICA algorithms and compare their performance on real-world resting state EEG data. Such a comparison is problematic because the way of mixing the original sources (the “ground truth”) is not known. We address this by developing proper measures to compare the results from multiple algorithms. The comparisons consider the ability of an algorithm to find interesting independent sources, i.e. those related to brain activity and not to artifact activity. The performance of locating a dipole for each separated independent component is considered in the comparison as well. Our results suggest that when using complex-valued ICA algorithms on preprocessed signals the resting state EEG activity can be analyzed in terms of physiological properties. This reestablishes the suitability of ICA for EEG analysis beyond the detection and removal of artifacts with real-valued ICA applied to the signals in the time-domain.

Keywords

References

  1. A. Hyvärinen, J. Karhunen, and E. Oja, Wiley, 2001.
  2. M. Castella and J.-C. Pesquet, “An Iterative Blind Source Separation Method for Convolutive Mixtures of Images,” Indep. Compon. Anal. Blind Signal Sep. , vol. 3195, pp. 922–929, 2004.
  3. T. P. Jung et al. , “Removing electroencephalographic artifacts by blind source separation.,” Psychophysiology , vol. 37, no. 2, pp. 163–178, Mar. 2000.
  4. A. Al-Saegh, “Independent component analysis for separation of speech mixtures: a comparison among thirty algorithms,” Iraqi J. Electr. Electron. Eng. , vol. 11, no. 1, pp. 1–9, 2015.
  5. M. L. Scheuer, “Continuous EEG monitoring Suppl 3, pp. 114–127, Jan. 2002.
  6. P. L. Nunez and R. Srinivasan, Electric Fields of the Brain: the neurophysics of EEG , 2nd ed. Oxford University Press, 2006.
  7. J. Anemüller, T. J. Sejnowski, and S. Makeig, “Complex independent component analysis of frequency-domain electroencephalographic data.,” Neural Netw. , vol. 16, no. 9, pp. 1311–1323, Nov. 2003.
  8. A. Hyvärinen, P. Ramkumar, L. Parkkonen, and R. Hari, “Independent component analysis of short-time Fourier transforms for spontaneous EEG/MEG analysis.,” Neuroimage , vol. 49, no. 1, pp. 257–271, Jan. 2010.
  9. M. Novey and T. Adali, “Adaptable Nonlinearity for Complex Maximization of Nongaussianity and a Fixed-Point Algorithm,” 2006 16th IEEE Signal Process. Soc. Work. Mach. Learn. Signal Process. , no. x, pp. 79–84, Sep. 2006.
  10. X. Li and T. Adali, “Complex Independent Component Analysis by Entropy Bound Minimization,” vol. 57, no. 7, pp. 1417–1430, 2010.
  11. H. Li and T. Adali, “A class of complex ICA algorithms based on the kurtosis cost function.,” IEEE Trans. Neural Netw. , vol. 19, no. 3, pp. 408–420, Mar. 2008.
  12. E. Ollila and V. Koivunen, “Complex ICA using generalized uncorrelating transform,” Signal Processing , vol. 89, no. 4, pp. 365– 377, Apr. 2009.
  13. J. Eriksson and V. Koivunen, “Complexvalued ICA using second order statistics,” in Machine Learning for Signal Processing, 2004. Proceedings of the 2004 14th IEEE Signal Processing Society Workshop , 2004, pp. 183–192.
  14. A. Hyvärinen and E. Oja, “Independent component analysis: algorithms and applications.,” Neural Netw. , vol. 13, no. 4–5, pp. 411–430, 2000.
  15. J. Onton and S. Makeig, “Information-based modeling of event-related brain dynamics.,” Prog. Brain Res. , vol. 159, pp. 99–120, Jan. 2006.
  16. R. Oostenveld and P. Praamstra, “The five percent electrode system for high-resolution EEG and ERP measurements.,” Clin. Neurophysiol. , vol. 112, no. 4, pp. 713–719, Apr. 2001.