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.

Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF) / Kumaravel, Velu Prabhakar; Buiatti, Marco; Parise, Eugenio; Farella, Elisabetta. - In: SENSORS. - ISSN 1424-8220. - 22:19(2022), pp. 731401-731417. [10.3390/s22197314]

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

Kumaravel, Velu Prabhakar;Buiatti, Marco;Parise, Eugenio;
2022-01-01

Abstract

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.
2022
19
Kumaravel, Velu Prabhakar; Buiatti, Marco; Parise, Eugenio; Farella, Elisabetta
Adaptable and Robust EEG Bad Channel Detection Using Local Outlier Factor (LOF) / Kumaravel, Velu Prabhakar; Buiatti, Marco; Parise, Eugenio; Farella, Elisabetta. - In: SENSORS. - ISSN 1424-8220. - 22:19(2022), pp. 731401-731417. [10.3390/s22197314]
File in questo prodotto:
File Dimensione Formato  
sensors-22-07314-v2.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 687.28 kB
Formato Adobe PDF
687.28 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/355078
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact