Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records.
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 ar...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2018-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC6091961?pdf=render |
| _version_ | 1818261829018714112 |
|---|---|
| author | Jan Sebek Radoslav Bortel Pavel Sovka |
| author_facet | Jan Sebek Radoslav Bortel Pavel Sovka |
| author_sort | Jan Sebek |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-12T18:53:26Z |
| format | Article |
| id | doaj.art-8760a66637524427a672e1f2c8d5cb2f |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-12T18:53:26Z |
| publishDate | 2018-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-8760a66637524427a672e1f2c8d5cb2f2022-12-22T00:15:19ZengPublic Library of Science (PLoS)PLoS ONE1932-62032018-01-01138e020190010.1371/journal.pone.0201900Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records.Jan SebekRadoslav BortelPavel SovkaThis 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.http://europepmc.org/articles/PMC6091961?pdf=render |
| spellingShingle | Jan Sebek Radoslav Bortel Pavel Sovka Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records. PLoS ONE |
| title | Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records. |
| title_full | Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records. |
| title_fullStr | Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records. |
| title_full_unstemmed | Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records. |
| title_short | Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records. |
| title_sort | suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records |
| url | http://europepmc.org/articles/PMC6091961?pdf=render |
| work_keys_str_mv | AT jansebek suppressionofoverlearninginindependentcomponentanalysisusedforremovalofmuscularartifactsfromelectroencephalographicrecords AT radoslavbortel suppressionofoverlearninginindependentcomponentanalysisusedforremovalofmuscularartifactsfromelectroencephalographicrecords AT pavelsovka suppressionofoverlearninginindependentcomponentanalysisusedforremovalofmuscularartifactsfromelectroencephalographicrecords |