ON THE EFFECTIVENESS OF ICA BASED EYE ARTIFACT REMOVAL FROM EEG WINDOWS OF DIFFERENT LENGTHS

Foad Ghaderi, Elsa Andrea Kirchner

View Full Paper

References

  1. [1] S. Sanei, Adaptive Processing of Brain Signals, Wiley,2013.
  2. [2] F. Ghaderi, K. Nazarpour, J.G. McWhirter, and S. Sanei,“Removal of ballistocardiogram artifacts using the cyclosta-tionary source extraction method,” IEEE Trans Biomed Eng,vol. 57, no. 11, pp. 2667–2676, 2010.
  3. [3] F. Ghaderi, S. K. Kim, and E. A. Kirchner, “Effects of eyeartifact removal methods on single trial P300 detection, acomparative study,” J NEUROSCI METH, vol. 221, no. 0,pp. 41–47, 2014.
  4. [4] H. Hyv¨arinen, J. Karhunen, and E. Oja, Independent Com-ponent Analysis, Wiley-Interscience, 2001.
  5. [5] A. Mognon, J Jovicich, L Bruzzone, and M Buiatti, “AD-JUST: An automatic EEG artifact detector based on the jointuse of spatial and temporal features,” Psychophysiology,vol. 48, no. 2, pp. 229–240, 2011.
  6. [6] S. Halder, M. Bensch, J. Mellinger, M. Bogdan, A. K¨ubler,N. Birbaumer, and W. Rosenstiel, “Online artifact removalfor brain-computer interfaces using support vector machinesand blind source separation,” Intell. Neuroscience, vol.2007, pp. 8:1–8:9, Apr. 2007.
  7. [7] J. Gao, C. Zheng, and P. Wang, “Online removal of muscleartifact from electroencephalogram signals based on canon-ical correlation analysis,” Clin EEG Neurosci, vol. 41, no.1, pp. 53–59, 2010.
  8. [8] F. Matsusaki, T. Ikuno, Y. Katayama, and K. Iramina, “On-line artifact removal in EEG signals,” in World Congresson Medical Physics and Biomedical Engineering May 26-31, 2012, Beijing, China, Mian Long, Ed., vol. 39 ofIFMBE Proceedings, pp. 352–355. Springer Berlin Heidel-berg, 2013.
  9. [9] J. S¨arel¨a and R. Vig´ario, “Overlearning in marginaldistribution-based ICA: Analysis and solutions,” J. Mach.Learn. Res., vol. 4, no. 7-8, pp. 1447–1469, Oct. 2004.
  10. [10] A. Delorme and S. Makeig, “EEGLAB: an open source tool-box for analysis of single-trial EEG dynamics including in-dependent component analysis,” Journal of NeuroscienceMethods, vol. 134, no. 1, pp. 9–21, 2004.
  11. [11] J. Onton and S. Makeig, “Information-based modeling ofevent-related brain dynamics,” in Event-Related Dynam-ics of Brain Oscillations, Christa Neuper and WolfgangKlimesch, Eds., vol. 159 of Progress in Brain Research, pp.99 – 120. Elsevier, 2006.
  12. [12] A. Hyv¨arinen, J. S¨arel¨a, and R. Vig´ario, “Bumps andSpikes: Artefacts Generated by Independent ComponentAnalysis with Insufficient Sample Size,” in Int. Workshopon Independent Component Analysis and Blind Signal Sep-aration (ICA’99), 1999, pp. 425–429.
  13. [13] G. Korats, S. Cam, R. Ranta, and M. Hamid, “ApplyingICA in EEG: Choice of the window length and of the decor-relation method,” in Biomedical Engineering Systems andTechnologies, vol. 357 of Communications in Computer andInformation Science, pp. 269–286. Springer Berlin Heidel-berg, 2013.
  14. [14] A. J. Bell and T. J. Sejnowski, “An information-maximization approach to blind separation and blind decon-volution,” Neural Computation, vol. 7, no. 6, pp. 1129–1159, 1995.
  15. [15] C. Chih-Chung and L. Chih-Jen, “LIBSVM: A library forsupport vector machines,” ACM Transactions on IntelligentSystems and Technology, vol. 2, pp. 27:1–27:27, 2011.
  16. [16] M. M. Krell, S. Straube, A. Seeland, H. W¨ohrle, J. Teiwes,J. H. Metzen, E. A. Kirchner, and F. Kirchner, “pySPACE - asignal processing and classification environment in Python,”Frontiers in Neuroinformatics, vol. 7, no. 40, Dec 2013.
  17. [17] S. Straube and M. M. Krell, “How to evaluate an agent’sbehaviour to infrequent events? – reliable performance esti-mation insensitive to class distribution,” Frontiers in Com-putational Neuroscience, vol. 8, no. 43, 2014.

Important Links:

Go Back