Alternative CSP approaches for multimodal distributed BCI data

Stephanie Brandl, Klaus Muller, Wojciech Samek

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

Abstract

Brain-Computer Interfaces (BCIs) are trained to distinguish between two (or more) mental states, e.g., left and right hand motor imagery, from the recorded brain signals. Common Spatial Patterns (CSP) is a popular method to optimally separate data from two motor imagery tasks under the assumption of an unimodal class distribution. In out of lab environments where users are distracted by additional noise sources this assumption may not hold. This paper systematically investigates BCI performance under such distractions and proposes two novel CSP variants, ensemble CSP and 2-step CSP, which can cope with multimodal class distributions. The proposed algorithms are evaluated using simulations and BCI data of 16 healthy participants performing motor imagery under 6 different types of distraction. Both methods are shown to significantly enhance the performance compared to the standard procedure.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3742-3747
Number of pages6
ISBN (Electronic)9781509018970
DOIs
Publication statusPublished - 2017 Feb 6
Event2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Budapest, Hungary
Duration: 2016 Oct 92016 Oct 12

Other

Other2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016
CountryHungary
CityBudapest
Period16/10/916/10/12

Fingerprint

Brain computer interface
Spatial Pattern
Alternatives
Brain
Ensemble
Imagery
Simulation
Class

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Control and Optimization
  • Human-Computer Interaction

Cite this

Brandl, S., Muller, K., & Samek, W. (2017). Alternative CSP approaches for multimodal distributed BCI data. In 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings (pp. 3742-3747). [7844816] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2016.7844816

Alternative CSP approaches for multimodal distributed BCI data. / Brandl, Stephanie; Muller, Klaus; Samek, Wojciech.

2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3742-3747 7844816.

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

Brandl, S, Muller, K & Samek, W 2017, Alternative CSP approaches for multimodal distributed BCI data. in 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings., 7844816, Institute of Electrical and Electronics Engineers Inc., pp. 3742-3747, 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016, Budapest, Hungary, 16/10/9. https://doi.org/10.1109/SMC.2016.7844816
Brandl S, Muller K, Samek W. Alternative CSP approaches for multimodal distributed BCI data. In 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3742-3747. 7844816 https://doi.org/10.1109/SMC.2016.7844816
Brandl, Stephanie ; Muller, Klaus ; Samek, Wojciech. / Alternative CSP approaches for multimodal distributed BCI data. 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3742-3747
@inproceedings{053f5afbd58f4b97be2a860367f13920,
title = "Alternative CSP approaches for multimodal distributed BCI data",
abstract = "Brain-Computer Interfaces (BCIs) are trained to distinguish between two (or more) mental states, e.g., left and right hand motor imagery, from the recorded brain signals. Common Spatial Patterns (CSP) is a popular method to optimally separate data from two motor imagery tasks under the assumption of an unimodal class distribution. In out of lab environments where users are distracted by additional noise sources this assumption may not hold. This paper systematically investigates BCI performance under such distractions and proposes two novel CSP variants, ensemble CSP and 2-step CSP, which can cope with multimodal class distributions. The proposed algorithms are evaluated using simulations and BCI data of 16 healthy participants performing motor imagery under 6 different types of distraction. Both methods are shown to significantly enhance the performance compared to the standard procedure.",
author = "Stephanie Brandl and Klaus Muller and Wojciech Samek",
year = "2017",
month = "2",
day = "6",
doi = "10.1109/SMC.2016.7844816",
language = "English",
pages = "3742--3747",
booktitle = "2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Alternative CSP approaches for multimodal distributed BCI data

AU - Brandl, Stephanie

AU - Muller, Klaus

AU - Samek, Wojciech

PY - 2017/2/6

Y1 - 2017/2/6

N2 - Brain-Computer Interfaces (BCIs) are trained to distinguish between two (or more) mental states, e.g., left and right hand motor imagery, from the recorded brain signals. Common Spatial Patterns (CSP) is a popular method to optimally separate data from two motor imagery tasks under the assumption of an unimodal class distribution. In out of lab environments where users are distracted by additional noise sources this assumption may not hold. This paper systematically investigates BCI performance under such distractions and proposes two novel CSP variants, ensemble CSP and 2-step CSP, which can cope with multimodal class distributions. The proposed algorithms are evaluated using simulations and BCI data of 16 healthy participants performing motor imagery under 6 different types of distraction. Both methods are shown to significantly enhance the performance compared to the standard procedure.

AB - Brain-Computer Interfaces (BCIs) are trained to distinguish between two (or more) mental states, e.g., left and right hand motor imagery, from the recorded brain signals. Common Spatial Patterns (CSP) is a popular method to optimally separate data from two motor imagery tasks under the assumption of an unimodal class distribution. In out of lab environments where users are distracted by additional noise sources this assumption may not hold. This paper systematically investigates BCI performance under such distractions and proposes two novel CSP variants, ensemble CSP and 2-step CSP, which can cope with multimodal class distributions. The proposed algorithms are evaluated using simulations and BCI data of 16 healthy participants performing motor imagery under 6 different types of distraction. Both methods are shown to significantly enhance the performance compared to the standard procedure.

UR - http://www.scopus.com/inward/record.url?scp=85015777539&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015777539&partnerID=8YFLogxK

U2 - 10.1109/SMC.2016.7844816

DO - 10.1109/SMC.2016.7844816

M3 - Conference contribution

AN - SCOPUS:85015777539

SP - 3742

EP - 3747

BT - 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -