Tackling noise, artifacts and nonstationarity in BCI with robust divergences

Wojciech Samek, Klaus Muller

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

2 Citations (Scopus)

Abstract

Although the field of Brain-Computer Interfacing (BCI) has made incredible advances in the last decade, current BCIs are still scarcely used outside laboratories. One reason is the lack of robustness to noise, artifacts and nonstationarity which are intrinsic parts of the recorded brain signal. Furthermore out-of-lab environments imply the presence of external variables that are largely beyond the control of the user, but can severely corrupt signal quality. This paper presents a new generation of robust EEG signal processing approaches based on the information geometric notion of divergence. We show that these divergence-based methods can be used for robust spatial filtering and thus increase the systems' reliability when confronted to, e.g., environmental noise, users' motions or electrode artifacts. Furthermore we extend the divergence-based framework to heavy-tail distributions and investigate the advantages of a joint optimization for robustness and stationarity.

Original languageEnglish
Title of host publication2015 23rd European Signal Processing Conference, EUSIPCO 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2741-2745
Number of pages5
ISBN (Print)9780992862633
DOIs
Publication statusPublished - 2015 Dec 22
Externally publishedYes
Event23rd European Signal Processing Conference, EUSIPCO 2015 - Nice, France
Duration: 2015 Aug 312015 Sep 4

Other

Other23rd European Signal Processing Conference, EUSIPCO 2015
CountryFrance
CityNice
Period15/8/3115/9/4

Fingerprint

Brain
Electroencephalography
Signal processing
Electrodes

Keywords

  • Brain-Computer Interfacing
  • Common Spatial Patterns
  • Nonstationarity
  • Robustness

ASJC Scopus subject areas

  • Media Technology
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Samek, W., & Muller, K. (2015). Tackling noise, artifacts and nonstationarity in BCI with robust divergences. In 2015 23rd European Signal Processing Conference, EUSIPCO 2015 (pp. 2741-2745). [7362883] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EUSIPCO.2015.7362883

Tackling noise, artifacts and nonstationarity in BCI with robust divergences. / Samek, Wojciech; Muller, Klaus.

2015 23rd European Signal Processing Conference, EUSIPCO 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 2741-2745 7362883.

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

Samek, W & Muller, K 2015, Tackling noise, artifacts and nonstationarity in BCI with robust divergences. in 2015 23rd European Signal Processing Conference, EUSIPCO 2015., 7362883, Institute of Electrical and Electronics Engineers Inc., pp. 2741-2745, 23rd European Signal Processing Conference, EUSIPCO 2015, Nice, France, 15/8/31. https://doi.org/10.1109/EUSIPCO.2015.7362883
Samek W, Muller K. Tackling noise, artifacts and nonstationarity in BCI with robust divergences. In 2015 23rd European Signal Processing Conference, EUSIPCO 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 2741-2745. 7362883 https://doi.org/10.1109/EUSIPCO.2015.7362883
Samek, Wojciech ; Muller, Klaus. / Tackling noise, artifacts and nonstationarity in BCI with robust divergences. 2015 23rd European Signal Processing Conference, EUSIPCO 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 2741-2745
@inproceedings{b6c72031ce9c41169c5e9de64bda7230,
title = "Tackling noise, artifacts and nonstationarity in BCI with robust divergences",
abstract = "Although the field of Brain-Computer Interfacing (BCI) has made incredible advances in the last decade, current BCIs are still scarcely used outside laboratories. One reason is the lack of robustness to noise, artifacts and nonstationarity which are intrinsic parts of the recorded brain signal. Furthermore out-of-lab environments imply the presence of external variables that are largely beyond the control of the user, but can severely corrupt signal quality. This paper presents a new generation of robust EEG signal processing approaches based on the information geometric notion of divergence. We show that these divergence-based methods can be used for robust spatial filtering and thus increase the systems' reliability when confronted to, e.g., environmental noise, users' motions or electrode artifacts. Furthermore we extend the divergence-based framework to heavy-tail distributions and investigate the advantages of a joint optimization for robustness and stationarity.",
keywords = "Brain-Computer Interfacing, Common Spatial Patterns, Nonstationarity, Robustness",
author = "Wojciech Samek and Klaus Muller",
year = "2015",
month = "12",
day = "22",
doi = "10.1109/EUSIPCO.2015.7362883",
language = "English",
isbn = "9780992862633",
pages = "2741--2745",
booktitle = "2015 23rd European Signal Processing Conference, EUSIPCO 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Tackling noise, artifacts and nonstationarity in BCI with robust divergences

AU - Samek, Wojciech

AU - Muller, Klaus

PY - 2015/12/22

Y1 - 2015/12/22

N2 - Although the field of Brain-Computer Interfacing (BCI) has made incredible advances in the last decade, current BCIs are still scarcely used outside laboratories. One reason is the lack of robustness to noise, artifacts and nonstationarity which are intrinsic parts of the recorded brain signal. Furthermore out-of-lab environments imply the presence of external variables that are largely beyond the control of the user, but can severely corrupt signal quality. This paper presents a new generation of robust EEG signal processing approaches based on the information geometric notion of divergence. We show that these divergence-based methods can be used for robust spatial filtering and thus increase the systems' reliability when confronted to, e.g., environmental noise, users' motions or electrode artifacts. Furthermore we extend the divergence-based framework to heavy-tail distributions and investigate the advantages of a joint optimization for robustness and stationarity.

AB - Although the field of Brain-Computer Interfacing (BCI) has made incredible advances in the last decade, current BCIs are still scarcely used outside laboratories. One reason is the lack of robustness to noise, artifacts and nonstationarity which are intrinsic parts of the recorded brain signal. Furthermore out-of-lab environments imply the presence of external variables that are largely beyond the control of the user, but can severely corrupt signal quality. This paper presents a new generation of robust EEG signal processing approaches based on the information geometric notion of divergence. We show that these divergence-based methods can be used for robust spatial filtering and thus increase the systems' reliability when confronted to, e.g., environmental noise, users' motions or electrode artifacts. Furthermore we extend the divergence-based framework to heavy-tail distributions and investigate the advantages of a joint optimization for robustness and stationarity.

KW - Brain-Computer Interfacing

KW - Common Spatial Patterns

KW - Nonstationarity

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=84963939269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963939269&partnerID=8YFLogxK

U2 - 10.1109/EUSIPCO.2015.7362883

DO - 10.1109/EUSIPCO.2015.7362883

M3 - Conference contribution

SN - 9780992862633

SP - 2741

EP - 2745

BT - 2015 23rd European Signal Processing Conference, EUSIPCO 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -