REG-ICA: A new hybrid method for EOG Artifact Rejection

Manousos A. Klados, Christos L. Papadelis, Panagiotis D. Bamidis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The plethora of Artifact Rejection (AR) techniques proposed for removing electrooculographic (EOG) artifacts from electroencephalographic (EEG) signals can be separated into two main categories. The first category is composed of regression - based methods, while the second one consists of Blind Source Separation (BSS) - methods. A major disadvantage of BSS - based methodology is that the artifactual components include also neural activity, thus their rejection leads to the distortion of the underlying cerebral activity. The current study tries to solve the aforementioned problem by proposing a new hybrid algorithm for EOG AR. According to this automatic approach, called REG-ICA, Independent Component Analysis (ICA) is used to decompose EEG signals into spatial independent components (ICs). Then an adaptive filter, based on a stable Version of the Recursive Least Square (sRLS) algorithm, is applied to ICs so as to remove only EOG artifacts and maintain the neural signals intact. Then the cleaned ICs are projected back, reconstructing the artifact - free EEG signals. In order to evaluate the performance of the proposed technique, REG-ICA has been compared with the Least Mean Square (LMS) approach, in simulated EEG data. Two criteria were used for the comparison: how successfully algorithms remove eye blinking artifacts, and how much the EEG signals are distorted. Results support the argument that REG-ICA removes successfully EOG activity, while it minimizes the distortion of the underlying cerebral activity in contrast to LMS.
LanguageEnglish
Title of host publication2009 9th International Conference on Information Technology and Applications in Biomedicine
PublisherIEEE
Pages1-4
Number of pages4
ISBN (Electronic)978-1-4244-5379-5
DOIs
Publication statusPublished - Nov 2009
Event9th International Conference on Information Technology and Applications in Biomedicine - Larnaca, Cyprus
Duration: 4 Nov 20097 Nov 2009

Conference

Conference9th International Conference on Information Technology and Applications in Biomedicine
Abbreviated titleITAB 2009
CountryCyprus
CityLarnaca
Period4/11/097/11/09

Fingerprint

Independent component analysis
Blind source separation
Adaptive filters

Keywords

  • analysis
  • artifact rejection
  • biological
  • eeg
  • electroculogram
  • electroencephalogram
  • eog
  • ica
  • independent component
  • physiological
  • regression
  • the most frequently seen

Cite this

Klados, M. A., Papadelis, C. L., & Bamidis, P. D. (2009). REG-ICA: A new hybrid method for EOG Artifact Rejection. In 2009 9th International Conference on Information Technology and Applications in Biomedicine (pp. 1-4). IEEE. https://doi.org/10.1109/ITAB.2009.5394295
Klados, Manousos A. ; Papadelis, Christos L. ; Bamidis, Panagiotis D. / REG-ICA: A new hybrid method for EOG Artifact Rejection. 2009 9th International Conference on Information Technology and Applications in Biomedicine. IEEE, 2009. pp. 1-4
@inproceedings{152a3592ad1a4e90b94556065b143b54,
title = "REG-ICA: A new hybrid method for EOG Artifact Rejection",
abstract = "The plethora of Artifact Rejection (AR) techniques proposed for removing electrooculographic (EOG) artifacts from electroencephalographic (EEG) signals can be separated into two main categories. The first category is composed of regression - based methods, while the second one consists of Blind Source Separation (BSS) - methods. A major disadvantage of BSS - based methodology is that the artifactual components include also neural activity, thus their rejection leads to the distortion of the underlying cerebral activity. The current study tries to solve the aforementioned problem by proposing a new hybrid algorithm for EOG AR. According to this automatic approach, called REG-ICA, Independent Component Analysis (ICA) is used to decompose EEG signals into spatial independent components (ICs). Then an adaptive filter, based on a stable Version of the Recursive Least Square (sRLS) algorithm, is applied to ICs so as to remove only EOG artifacts and maintain the neural signals intact. Then the cleaned ICs are projected back, reconstructing the artifact - free EEG signals. In order to evaluate the performance of the proposed technique, REG-ICA has been compared with the Least Mean Square (LMS) approach, in simulated EEG data. Two criteria were used for the comparison: how successfully algorithms remove eye blinking artifacts, and how much the EEG signals are distorted. Results support the argument that REG-ICA removes successfully EOG activity, while it minimizes the distortion of the underlying cerebral activity in contrast to LMS.",
keywords = "analysis, artifact rejection, biological, eeg, electroculogram, electroencephalogram, eog, ica, independent component, physiological, regression, the most frequently seen",
author = "Klados, {Manousos A.} and Papadelis, {Christos L.} and Bamidis, {Panagiotis D.}",
year = "2009",
month = "11",
doi = "10.1109/ITAB.2009.5394295",
language = "English",
pages = "1--4",
booktitle = "2009 9th International Conference on Information Technology and Applications in Biomedicine",
publisher = "IEEE",
address = "United States",

}

Klados, MA, Papadelis, CL & Bamidis, PD 2009, REG-ICA: A new hybrid method for EOG Artifact Rejection. in 2009 9th International Conference on Information Technology and Applications in Biomedicine. IEEE, pp. 1-4, 9th International Conference on Information Technology and Applications in Biomedicine, Larnaca, Cyprus, 4/11/09. https://doi.org/10.1109/ITAB.2009.5394295

REG-ICA: A new hybrid method for EOG Artifact Rejection. / Klados, Manousos A.; Papadelis, Christos L.; Bamidis, Panagiotis D.

2009 9th International Conference on Information Technology and Applications in Biomedicine. IEEE, 2009. p. 1-4.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - REG-ICA: A new hybrid method for EOG Artifact Rejection

AU - Klados, Manousos A.

AU - Papadelis, Christos L.

AU - Bamidis, Panagiotis D.

PY - 2009/11

Y1 - 2009/11

N2 - The plethora of Artifact Rejection (AR) techniques proposed for removing electrooculographic (EOG) artifacts from electroencephalographic (EEG) signals can be separated into two main categories. The first category is composed of regression - based methods, while the second one consists of Blind Source Separation (BSS) - methods. A major disadvantage of BSS - based methodology is that the artifactual components include also neural activity, thus their rejection leads to the distortion of the underlying cerebral activity. The current study tries to solve the aforementioned problem by proposing a new hybrid algorithm for EOG AR. According to this automatic approach, called REG-ICA, Independent Component Analysis (ICA) is used to decompose EEG signals into spatial independent components (ICs). Then an adaptive filter, based on a stable Version of the Recursive Least Square (sRLS) algorithm, is applied to ICs so as to remove only EOG artifacts and maintain the neural signals intact. Then the cleaned ICs are projected back, reconstructing the artifact - free EEG signals. In order to evaluate the performance of the proposed technique, REG-ICA has been compared with the Least Mean Square (LMS) approach, in simulated EEG data. Two criteria were used for the comparison: how successfully algorithms remove eye blinking artifacts, and how much the EEG signals are distorted. Results support the argument that REG-ICA removes successfully EOG activity, while it minimizes the distortion of the underlying cerebral activity in contrast to LMS.

AB - The plethora of Artifact Rejection (AR) techniques proposed for removing electrooculographic (EOG) artifacts from electroencephalographic (EEG) signals can be separated into two main categories. The first category is composed of regression - based methods, while the second one consists of Blind Source Separation (BSS) - methods. A major disadvantage of BSS - based methodology is that the artifactual components include also neural activity, thus their rejection leads to the distortion of the underlying cerebral activity. The current study tries to solve the aforementioned problem by proposing a new hybrid algorithm for EOG AR. According to this automatic approach, called REG-ICA, Independent Component Analysis (ICA) is used to decompose EEG signals into spatial independent components (ICs). Then an adaptive filter, based on a stable Version of the Recursive Least Square (sRLS) algorithm, is applied to ICs so as to remove only EOG artifacts and maintain the neural signals intact. Then the cleaned ICs are projected back, reconstructing the artifact - free EEG signals. In order to evaluate the performance of the proposed technique, REG-ICA has been compared with the Least Mean Square (LMS) approach, in simulated EEG data. Two criteria were used for the comparison: how successfully algorithms remove eye blinking artifacts, and how much the EEG signals are distorted. Results support the argument that REG-ICA removes successfully EOG activity, while it minimizes the distortion of the underlying cerebral activity in contrast to LMS.

KW - analysis

KW - artifact rejection

KW - biological

KW - eeg

KW - electroculogram

KW - electroencephalogram

KW - eog

KW - ica

KW - independent component

KW - physiological

KW - regression

KW - the most frequently seen

UR - https://ieeexplore.ieee.org/document/5394295/

U2 - 10.1109/ITAB.2009.5394295

DO - 10.1109/ITAB.2009.5394295

M3 - Conference contribution

SP - 1

EP - 4

BT - 2009 9th International Conference on Information Technology and Applications in Biomedicine

PB - IEEE

ER -

Klados MA, Papadelis CL, Bamidis PD. REG-ICA: A new hybrid method for EOG Artifact Rejection. In 2009 9th International Conference on Information Technology and Applications in Biomedicine. IEEE. 2009. p. 1-4 https://doi.org/10.1109/ITAB.2009.5394295