Reduction of EEG artifacts by ICA in different sleep stages

Romero, Sergio; Mañanas, Miguel Ángel; Clos, S.; Giménez, Sandra; Barbanoj, M.J.

doi:10.1109/iembs.2003.1280467

Cited by 23 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2000, Jung et al removed artifacts from EEG by the extended ICA, and results comparing effectively to regression algorithm [ 50 ]. Romero et al applied ICA to reduce EEG artifacts in different sleep stages, and found the bidirectional property of EEG and EOG had little effect on ICA [ 51 ]. A method using probability and kurtosis to eliminate semi-automatically was discussed by Delorme et al [ 52 ].…”

Section: Single Artifacts Removal Techniquesmentioning

confidence: 99%

Removal of Artifacts from EEG Signals: A Review

Jiang

Bian

Tian

2019

Sensors

483

329

View full text Add to dashboard Cite

Electroencephalogram (EEG) plays an important role in identifying brain activity and behavior. However, the recorded electrical activity always be contaminated with artifacts and then affect the analysis of EEG signal. Hence, it is essential to develop methods to effectively detect and extract the clean EEG data during encephalogram recordings. Several methods have been proposed to remove artifacts, but the research on artifact removal continues to be an open problem. This paper tends to review the current artifact removal of various contaminations. We first discuss the characteristics of EEG data and the types of different artifacts. Then, a general overview of the state-of-the-art methods and their detail analysis are presented. Lastly, a comparative analysis is provided for choosing a suitable methods according to particular application.

show abstract

Section: Single Artifacts Removal Techniquesmentioning

confidence: 99%

Removal of Artifacts from EEG Signals: A Review

Jiang

Bian

Tian

2019

Sensors

483

329

View full text Add to dashboard Cite

show abstract

“…EOG artifact removal on the basis of isolation into independent components (ICs) using BSS has been demonstrated in [ 14 ]. Another approach employs the second order statistics based “algorithm for multiple unknown signals extraction (AMUSE)” to detect EEG artifacts in sleep studies [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Online Artifact Removal for Brain-Computer Interfaces Using Support Vector Machines and Blind Source Separation

Halder

Bensch

Mellinger

et al. 2007

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

We propose a combination of blind source separation (BSS) and independent component analysis (ICA) (signal decomposition into artifacts and nonartifacts) with support vector machines (SVMs) (automatic classification) that are designed for online usage. In order to select a suitable BSS/ICA method, three ICA algorithms (JADE, Infomax, and FastICA) and one BSS algorithm (AMUSE) are evaluated to determine their ability to isolate electromyographic (EMG) and electrooculographic (EOG) artifacts into individual components. An implementation of the selected BSS/ICA method with SVMs trained to classify EMG and EOG artifacts, which enables the usage of the method as a filter in measurements with online feedback, is described. This filter is evaluated on three BCI datasets as a proof-of-concept of the method.

show abstract

“…Then, an Independent Component Analysis (ICA) was performed to remove residual ocular, muscular, and electrocardiograph artifacts using EEGLAB (Delorme & Makeig, 2004). This procedure allows to significantly reduce the impact of EEG artifacts on power computation and on the identification of individual graphoelements, while producing negligible changes in physiological signals of interest (Iriarte et al, 2003;Romero et al, 2003). Rejected channels were interpolated using spherical splines.…”

Section: Methodsmentioning

confidence: 99%

Visual imagery and visual perception induce similar changes in occipital slow waves of sleep

Bernardi

Betta

Cataldi

et al. 2019

Preprint

View full text Add to dashboard Cite

Previous studies have shown that regional slow wave activity (SWA) during NREM-sleep is modulated by prior experience and learning. While this effect has been convincingly demonstrated for the sensorimotor domain, attempts to extend these findings to the visual system have provided mixed results. Here we asked whether depriving subjects of external visual stimuli during daytime would lead to regional changes in slow waves during sleep and whether the degree of 'internal visual stimulation' (spontaneous imagery) would influence such changes. In two 8h-long sessions spaced one-week apart, twelve healthy volunteers either were blindfolded while listening to audiobooks or watched movies (control condition), after which their sleep was recorded with high-density EEG. We found that during NREMsleep the number of small, local slow waves in the occipital cortex decreased after listening with blindfolding relative to movie watching in a way that depended on the degree of visual imagery subjects reported during blindfolding: subjects with low visual imagery showed a significant reduction of occipital sleep slow waves, while those who reported a high degree of visual imagery did not. We also found a positive relationship between the reliance on visual imagery during blindfolding and audiobook listening and the degree of correlation in sleep SWA between visual areas and language-related areas. These preliminary results demonstrate that short-term alterations in visual experience may trigger slow wave changes in cortical visual areas. Furthermore, they suggest that plasticity-related EEG changes during sleep may reflect externally induced ('bottom-up') visual experiences, as well as internally generated ('top-down') processes.

show abstract

Reduction of EEG artifacts by ICA in different sleep stages

Cited by 23 publications

References 4 publications

Removal of Artifacts from EEG Signals: A Review

Removal of Artifacts from EEG Signals: A Review

Online Artifact Removal for Brain-Computer Interfaces Using Support Vector Machines and Blind Source Separation

Visual imagery and visual perception induce similar changes in occipital slow waves of sleep

Contact Info

Product

Resources

About