Advanced search
1 file | 1.59 MB Add to list

Bi-smoothed functional independent component analysis for EEG artifact removal

(2021) MATHEMATICS. 9(11).
Author
Organization
Abstract
Motivated by mapping adverse artifactual events caused by body movements in electroencephalographic (EEG) signals, we present a functional independent component analysis based on the spectral decomposition of the kurtosis operator of a smoothed principal component expansion. A discrete roughness penalty is introduced in the orthonormality constraint of the covariance eigenfunctions in order to obtain the smoothed basis for the proposed independent component model. To select the tuning parameters, a cross-validation method that incorporates shrinkage is used to enhance the performance on functional representations with a large basis dimension. This method provides an estimation strategy to determine the penalty parameter and the optimal number of components. Our independent component approach is applied to real EEG data to estimate genuine brain potentials from a contaminated signal. As a result, it is possible to control high-frequency remnants of neural origin overlapping artifactual sources to optimize their removal from the signal. An R package implementing our methods is available at CRAN.
Keywords
functional data, functional kurtosis, penalized splines, smoothed principal components, auditory-motor coupling task, EEG, motion artifacts, PRINCIPAL-COMPONENTS, ASYMPTOTIC THEORY, MULTIVARIATE, SPLINES, CHOICE

Downloads

  • mathematics-09-01243.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.59 MB

Citation

Please use this url to cite or link to this publication:

MLA
Vidal Badia, Marc, et al. “Bi-Smoothed Functional Independent Component Analysis for EEG Artifact Removal.” MATHEMATICS, vol. 9, no. 11, 2021, doi:10.3390/math9111243.
APA
Vidal Badia, M., Rosso, M., & Aguilera, A. M. (2021). Bi-smoothed functional independent component analysis for EEG artifact removal. MATHEMATICS, 9(11). https://doi.org/10.3390/math9111243
Chicago author-date
Vidal Badia, Marc, Mattia Rosso, and Ana M. Aguilera. 2021. “Bi-Smoothed Functional Independent Component Analysis for EEG Artifact Removal.” MATHEMATICS 9 (11). https://doi.org/10.3390/math9111243.
Chicago author-date (all authors)
Vidal Badia, Marc, Mattia Rosso, and Ana M. Aguilera. 2021. “Bi-Smoothed Functional Independent Component Analysis for EEG Artifact Removal.” MATHEMATICS 9 (11). doi:10.3390/math9111243.
Vancouver
1.
Vidal Badia M, Rosso M, Aguilera AM. Bi-smoothed functional independent component analysis for EEG artifact removal. MATHEMATICS. 2021;9(11).
IEEE
[1]
M. Vidal Badia, M. Rosso, and A. M. Aguilera, “Bi-smoothed functional independent component analysis for EEG artifact removal,” MATHEMATICS, vol. 9, no. 11, 2021.
@article{8709819,
  abstract     = {{Motivated by mapping adverse artifactual events caused by body movements in electroencephalographic (EEG) signals, we present a functional independent component analysis based on the spectral decomposition of the kurtosis operator of a smoothed principal component expansion. A discrete roughness penalty is introduced in the orthonormality constraint of the covariance eigenfunctions in order to obtain the smoothed basis for the proposed independent component model. To select the tuning parameters, a cross-validation method that incorporates shrinkage is used to enhance the performance on functional representations with a large basis dimension. This method provides an estimation strategy to determine the penalty parameter and the optimal number of components. Our independent component approach is applied to real EEG data to estimate genuine brain potentials from a contaminated signal. As a result, it is possible to control high-frequency remnants of neural origin overlapping artifactual sources to optimize their removal from the signal. An R package implementing our methods is available at CRAN.}},
  articleno    = {{1243}},
  author       = {{Vidal Badia, Marc and Rosso, Mattia and Aguilera, Ana M.}},
  issn         = {{2227-7390}},
  journal      = {{MATHEMATICS}},
  keywords     = {{functional data,functional kurtosis,penalized splines,smoothed principal components,auditory-motor coupling task,EEG,motion artifacts,PRINCIPAL-COMPONENTS,ASYMPTOTIC THEORY,MULTIVARIATE,SPLINES,CHOICE}},
  language     = {{eng}},
  number       = {{11}},
  pages        = {{16}},
  title        = {{Bi-smoothed functional independent component analysis for EEG artifact removal}},
  url          = {{http://doi.org/10.3390/math9111243}},
  volume       = {{9}},
  year         = {{2021}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: