This paper addresses the overlearning problem in the independent component analysis (ICA) used for the removal of muscular artifacts from electroencephalographic (EEG) records. We note that for short EEG records with high number of channels the ICA fails to separate artifact-free EEG and muscular artifacts, which has been previously attributed to the phenomenon called overlearning. We address this problem by projecting an EEG record into several subspaces with a lower dimension, and perform the ICA on each subspace separately. Due to a reduced dimension of the subspaces, the overlearning is suppressed, and muscular artifacts are better separated. Once the muscular artifacts are removed, the signals in the individual subspaces are combined to provide an artifact free EEG record. We show that for short signals and high number of EEG channels our approach outperforms the currently available ICA based algorithms for muscular artifact removal. The proposed technique can efficiently suppress ICA overlearning for short signal segments of high density EEG signals.

Dept of Circuit Theory Czech Technical University Faculty of Electrical Engineering Prague Czech Republic

Zobrazit více v PubMed

Hyvärinen A, Oja E. Independent component analysis: algorithms and applications. Neural networks. 2000;13(4):411–430. PubMed

Vigário R, Sarela J, Jousmiki V, Hamalainen M, Oja E. Independent component approach to the analysis of EEG and MEG recordings. IEEE transactions on biomedical engineering. 2000;47(5):589–593. 10.1109/10.841330 PubMed DOI

Cheok NS, Raveendran P. Removal of EOG artifacts using ICA regression method. In: 4th Kuala Lumpur International Conference on Biomedical Engineering 2008. Springer; 2008. p. 226–229.

Mammone N, Morabito FC. Enhanced automatic artifact detection based on independent component analysis and Renyi’s entropy. Neural networks. 2008;21(7):1029–1040. 10.1016/j.neunet.2007.09.020 PubMed DOI

Ng SC, Raveendran P. Enhanced μ Rhythm Extraction Using Blind Source Separation and Wavelet Transform. IEEE Transactions on Biomedical Engineering. 2009;56(8):2024–2034. 10.1109/TBME.2009.2021987 PubMed DOI

Crespo-Garcia M, Atienza M, Cantero JL. Muscle artifact removal from human sleep EEG by using independent component analysis. Annals of biomedical engineering. 2008;36(3):467–475. 10.1007/s10439-008-9442-y PubMed DOI

Castellanos NP, Makarov VA. Recovering EEG brain signals: artifact suppression with wavelet enhanced independent component analysis. Journal of neuroscience methods. 2006;158(2):300–312. 10.1016/j.jneumeth.2006.05.033 PubMed DOI

Mammone N, La Foresta F, Morabito FC. Automatic artifact rejection from multichannel scalp EEG by wavelet ICA. IEEE Sensors Journal. 2012;12(3):533–542. 10.1109/JSEN.2011.2115236 DOI

Cassani R, Falk TH, Fraga FJ, Kanda PA, Anghinah R. The effects of automated artifact removal algorithms on electroencephalography-based Alzheimer’s disease diagnosis. Frontiers in aging neuroscience. 2014;6 10.3389/fnagi.2014.00055 PubMed DOI PMC

Fitzgibbon S, DeLosAngeles D, Lewis T, Powers D, Whitham E, Willoughby J, et al. Surface Laplacian of scalp electrical signals and independent component analysis resolve EMG contamination of electroencephalogram. International Journal of Psychophysiology. 2015;97(3):277–284. 10.1016/j.ijpsycho.2014.10.006 PubMed DOI

Fitzgibbon S, DeLosAngeles D, Lewis T, Powers D, Grummett T, Whitham E, et al. Automatic determination of EMG-contaminated components and validation of independent component analysis using EEG during pharmacologic paralysis. Clinical Neurophysiology. 2016;127(3):1781–1793. 10.1016/j.clinph.2015.12.009 PubMed DOI

Hyvärinen A, Särelä J, Vigário R. Spikes and bumps: Artefacts generated by independent component analysis with insufficient sample size. In: Proc. Int. Workshop on Independent Component Analysis and Signal Separation (ICA’99); 1999. p. 425–429.

Särelä J, Vigário R. The problem of overlearning in high-order ICA approaches: analysis and solutions. In: International Work-Conference on Artificial Neural Networks. Springer; 2001. p. 818–825.

Särelä J, Vigário R. Overlearning in marginal distribution-based ICA: analysis and solutions. Journal of machine learning research. 2003;4(Dec):1447–1469.

Delorme A, Sejnowski T, Makeig S. Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis. Neuroimage. 2007;34(4):1443–1449. 10.1016/j.neuroimage.2006.11.004 PubMed DOI PMC

Jung TP, Makeig S, Humphries C, Lee TW, Mckeown MJ, Iragui V, et al. Removing electroencephalographic artifacts by blind source separation. Psychophysiology. 2000;37(2):163–178. 10.1111/1469-8986.3720163 PubMed DOI

Hyv A, et al. Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks. 1999;10(3):626–634. 10.1109/72.761722 PubMed DOI

Shwedyk E, Balasubramanian R, Scott R. A nonstationary model for the electromyogram. IEEE Transactions on Biomedical Engineering. 1977;(5):417–424. 10.1109/TBME.1977.326175 PubMed DOI

Hyvärinen A, Karhunen J, Oja E. Independent component analysis. John Wiley & Sons; 2004.

Zeng K, Chen D, Ouyang G, Wang L, Liu X, Li X. An EEMD-ICA approach to enhancing artifact rejection for noisy multivariate neural data. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2016;24(6):630–638. 10.1109/TNSRE.2015.2496334 PubMed DOI

Perrin F, Bertrand O, Pernier J. Scalp Current Density Mapping: Value and Estimation from Potential Data. IEEE Transactions on Biomedical Engineering. 1987;34(4):283–288. 10.1109/TBME.1987.326089 PubMed DOI

Comon P. Independent component analysis, a new concept? Signal processing. 1994;36(3):287–314. 10.1016/0165-1684(94)90029-9 DOI

Whitham EM, Pope KJ, Fitzgibbon SP, Lewis T, Clark CR, Loveless S, et al. Scalp electrical recording during paralysis: quantitative evidence that EEG frequencies above 20 Hz are contaminated by EMG. Clinical Neurophysiology. 2007;118(8):1877–1888. 10.1016/j.clinph.2007.04.027 PubMed DOI

Bortel R, Sovka P. Electrode position scaling in realistic Laplacian computation. IEEE Transactions on Biomedical Engineering. 2008;55(9):2314–2316. 10.1109/TBME.2008.921168 PubMed DOI

Bortel R, Sovka P. Potential approximation in realistic Laplacian computation. Clinical Neurophysiology. 2013;124(3):462–473. 10.1016/j.clinph.2012.08.020 PubMed DOI

Belouchrani A, Abed-Meraim K, Cardoso JF, Moulines E. A blind source separation technique using second-order statistics. IEEE Transactions on signal processing. 1997;45(2):434–444. 10.1109/78.554307 DOI

Hara S, Kawahara Y, Washio T, Von BüNau P, Tokunaga T, Yumoto K. Separation of stationary and non-stationary sources with a generalized eigenvalue problem. Neural networks. 2012;33:7–20. 10.1016/j.neunet.2012.04.001 PubMed DOI

Janani AS, Grummett TS, Lewis TW, Fitzgibbon SP, Whitham EM, DelosAngeles D, et al. Improved artefact removal from EEG using Canonical Correlation Analysis and spectral slope. Journal of neuroscience methods. 2018;298:1–15. 10.1016/j.jneumeth.2018.01.004 PubMed DOI

Zobrazit více v PubMed

Dryad
10.5061/dryad.r4b69rg