Cargando…

Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)

Electroencephalogram (EEG) data are typically affected by artifacts. The detection and removal of bad channels (i.e., with poor signal-to-noise ratio) is a crucial initial step. EEG data acquired from different populations require different cleaning strategies due to the inherent differences in the...

Descripción completa

Detalles Bibliográficos
Autores principales: Kumaravel, Velu Prabhakar, Buiatti, Marco, Parise, Eugenio, Farella, Elisabetta
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571252/
https://www.ncbi.nlm.nih.gov/pubmed/36236413
http://dx.doi.org/10.3390/s22197314
_version_ 1784810318442004480
author Kumaravel, Velu Prabhakar
Buiatti, Marco
Parise, Eugenio
Farella, Elisabetta
author_facet Kumaravel, Velu Prabhakar
Buiatti, Marco
Parise, Eugenio
Farella, Elisabetta
author_sort Kumaravel, Velu Prabhakar
collection PubMed
description Electroencephalogram (EEG) data are typically affected by artifacts. The detection and removal of bad channels (i.e., with poor signal-to-noise ratio) is a crucial initial step. EEG data acquired from different populations require different cleaning strategies due to the inherent differences in the data quality, the artifacts’ nature, and the employed experimental paradigm. To deal with such differences, we propose a robust EEG bad channel detection method based on the Local Outlier Factor (LOF) algorithm. Unlike most existing bad channel detection algorithms that look for the global distribution of channels, LOF identifies bad channels relative to the local cluster of channels, which makes it adaptable to any kind of EEG. To test the performance and versatility of the proposed algorithm, we validated it on EEG acquired from three populations (newborns, infants, and adults) and using two experimental paradigms (event-related and frequency-tagging). We found that LOF can be applied to all kinds of EEG data after calibrating its main hyperparameter: the LOF threshold. We benchmarked the performance of our approach with the existing state-of-the-art (SoA) bad channel detection methods. We found that LOF outperforms all of them by improving the F1 Score, our chosen performance metric, by about 40% for newborns and infants and 87.5% for adults.
format Online
Article
Text
id pubmed-9571252
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95712522022-10-17 Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF) Kumaravel, Velu Prabhakar Buiatti, Marco Parise, Eugenio Farella, Elisabetta Sensors (Basel) Article Electroencephalogram (EEG) data are typically affected by artifacts. The detection and removal of bad channels (i.e., with poor signal-to-noise ratio) is a crucial initial step. EEG data acquired from different populations require different cleaning strategies due to the inherent differences in the data quality, the artifacts’ nature, and the employed experimental paradigm. To deal with such differences, we propose a robust EEG bad channel detection method based on the Local Outlier Factor (LOF) algorithm. Unlike most existing bad channel detection algorithms that look for the global distribution of channels, LOF identifies bad channels relative to the local cluster of channels, which makes it adaptable to any kind of EEG. To test the performance and versatility of the proposed algorithm, we validated it on EEG acquired from three populations (newborns, infants, and adults) and using two experimental paradigms (event-related and frequency-tagging). We found that LOF can be applied to all kinds of EEG data after calibrating its main hyperparameter: the LOF threshold. We benchmarked the performance of our approach with the existing state-of-the-art (SoA) bad channel detection methods. We found that LOF outperforms all of them by improving the F1 Score, our chosen performance metric, by about 40% for newborns and infants and 87.5% for adults. MDPI 2022-09-27 /pmc/articles/PMC9571252/ /pubmed/36236413 http://dx.doi.org/10.3390/s22197314 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kumaravel, Velu Prabhakar
Buiatti, Marco
Parise, Eugenio
Farella, Elisabetta
Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)
title Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)
title_full Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)
title_fullStr Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)
title_full_unstemmed Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)
title_short Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF)
title_sort adaptable and robust eeg bad channel detection using local outlier factor (lof)
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9571252/
https://www.ncbi.nlm.nih.gov/pubmed/36236413
http://dx.doi.org/10.3390/s22197314
work_keys_str_mv AT kumaravelveluprabhakar adaptableandrobusteegbadchanneldetectionusinglocaloutlierfactorlof
AT buiattimarco adaptableandrobusteegbadchanneldetectionusinglocaloutlierfactorlof
AT pariseeugenio adaptableandrobusteegbadchanneldetectionusinglocaloutlierfactorlof
AT farellaelisabetta adaptableandrobusteegbadchanneldetectionusinglocaloutlierfactorlof