Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00322574" target="_blank" >RIV/68407700:21230/18:00322574 - isvavai.cz</a>

Výsledek na webu

<a href="http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0201900" target="_blank" >http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0201900</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1371/journal.pone.0201900" target="_blank" >10.1371/journal.pone.0201900</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Suppression of overlearning in independent component analysis used for removal of muscular artifacts from electroencephalographic records

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

PLoS ONE

ISSN

1932-6203

e-ISSN

1932-6203

Svazek periodika

13

Číslo periodika v rámci svazku

8

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

21

Strana od-do

—

Kód UT WoS článku

000441662800016

EID výsledku v databázi Scopus

2-s2.0-85051552389