Enhanced performance by a hybrid NIRS-EEG brain computer interface

Siamac Fazli; Jan Mehnert; Jens Steinbrink; Gabriel Curio; Arno Villringer; Klaus Robert Müller; Benjamin Blankertz

doi:10.1016/j.neuroimage.2011.07.084

Enhanced performance by a hybrid NIRS-EEG brain computer interface

Siamac Fazli^*
, Jan Mehnert
, Jens Steinbrink
, Gabriel Curio
, Arno Villringer
, Klaus Robert Müller
, Benjamin Blankertz

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

534 Citations (Scopus)

Abstract

Noninvasive Brain Computer Interfaces (BCI) have been promoted to be used for neuroprosthetics. However, reports on applications with electroencephalography (EEG) show a demand for a better accuracy and stability. Here we investigate whether near-infrared spectroscopy (NIRS) can be used to enhance the EEG approach. In our study both methods were applied simultaneously in a real-time Sensory Motor Rhythm (SMR)-based BCI paradigm, involving executed movements as well as motor imagery. We tested how the classification of NIRS data can complement ongoing real-time EEG classification. Our results show that simultaneous measurements of NIRS and EEG can significantly improve the classification accuracy of motor imagery in over 90% of considered subjects and increases performance by 5% on average (p < 0:01). However, the long time delay of the hemodynamic response may hinder an overall increase of bit-rates. Furthermore we find that EEG and NIRS complement each other in terms of information content and are thus a viable multimodal imaging technique, suitable for BCI.

Original language	English
Pages (from-to)	519-529
Number of pages	11
Journal	NeuroImage
Volume	59
Issue number	1
DOIs	https://doi.org/10.1016/j.neuroimage.2011.07.084
Publication status	Published - 2012 Jan 2

Bibliographical note

Funding Information:
This work was supported by German Ministry for Research , Bernstein Focus Neurotechnology Berlin ( 01GQ0850 ) and in part by NIH Grant nos. R42NS050007 and R44NS049734 . We would like to thank Stefan Haufe for fruitful discussions, NIRx Medizintechnik GmbH (Berlin, Germany) for providing the near-infrared imaging system and Michaela Rausch for the help with the measurements.

Keywords

Combined NIRS-EEG
Hybrid BCI
Meta-classifier

ASJC Scopus subject areas

Neurology
Cognitive Neuroscience

Access to Document

10.1016/j.neuroimage.2011.07.084

Cite this

@article{882fdac0db9c4b3ea2202299dbef5eb2,

title = "Enhanced performance by a hybrid NIRS-EEG brain computer interface",

abstract = "Noninvasive Brain Computer Interfaces (BCI) have been promoted to be used for neuroprosthetics. However, reports on applications with electroencephalography (EEG) show a demand for a better accuracy and stability. Here we investigate whether near-infrared spectroscopy (NIRS) can be used to enhance the EEG approach. In our study both methods were applied simultaneously in a real-time Sensory Motor Rhythm (SMR)-based BCI paradigm, involving executed movements as well as motor imagery. We tested how the classification of NIRS data can complement ongoing real-time EEG classification. Our results show that simultaneous measurements of NIRS and EEG can significantly improve the classification accuracy of motor imagery in over 90\% of considered subjects and increases performance by 5\% on average (p < 0:01). However, the long time delay of the hemodynamic response may hinder an overall increase of bit-rates. Furthermore we find that EEG and NIRS complement each other in terms of information content and are thus a viable multimodal imaging technique, suitable for BCI.",

keywords = "Combined NIRS-EEG, Hybrid BCI, Meta-classifier",

author = "Siamac Fazli and Jan Mehnert and Jens Steinbrink and Gabriel Curio and Arno Villringer and M{\"u}ller, \{Klaus Robert\} and Benjamin Blankertz",

note = "Funding Information: This work was supported by German Ministry for Research , Bernstein Focus Neurotechnology Berlin ( 01GQ0850 ) and in part by NIH Grant nos. R42NS050007 and R44NS049734 . We would like to thank Stefan Haufe for fruitful discussions, NIRx Medizintechnik GmbH (Berlin, Germany) for providing the near-infrared imaging system and Michaela Rausch for the help with the measurements.",

year = "2012",

month = jan,

day = "2",

doi = "10.1016/j.neuroimage.2011.07.084",

language = "English",

volume = "59",

pages = "519--529",

journal = "NeuroImage",

issn = "1053-8119",

publisher = "Academic Press Inc.",

number = "1",

}

TY - JOUR

T1 - Enhanced performance by a hybrid NIRS-EEG brain computer interface

AU - Fazli, Siamac

AU - Mehnert, Jan

AU - Steinbrink, Jens

AU - Curio, Gabriel

AU - Villringer, Arno

AU - Müller, Klaus Robert

AU - Blankertz, Benjamin

N1 - Funding Information: This work was supported by German Ministry for Research , Bernstein Focus Neurotechnology Berlin ( 01GQ0850 ) and in part by NIH Grant nos. R42NS050007 and R44NS049734 . We would like to thank Stefan Haufe for fruitful discussions, NIRx Medizintechnik GmbH (Berlin, Germany) for providing the near-infrared imaging system and Michaela Rausch for the help with the measurements.

PY - 2012/1/2

Y1 - 2012/1/2

N2 - Noninvasive Brain Computer Interfaces (BCI) have been promoted to be used for neuroprosthetics. However, reports on applications with electroencephalography (EEG) show a demand for a better accuracy and stability. Here we investigate whether near-infrared spectroscopy (NIRS) can be used to enhance the EEG approach. In our study both methods were applied simultaneously in a real-time Sensory Motor Rhythm (SMR)-based BCI paradigm, involving executed movements as well as motor imagery. We tested how the classification of NIRS data can complement ongoing real-time EEG classification. Our results show that simultaneous measurements of NIRS and EEG can significantly improve the classification accuracy of motor imagery in over 90% of considered subjects and increases performance by 5% on average (p < 0:01). However, the long time delay of the hemodynamic response may hinder an overall increase of bit-rates. Furthermore we find that EEG and NIRS complement each other in terms of information content and are thus a viable multimodal imaging technique, suitable for BCI.

AB - Noninvasive Brain Computer Interfaces (BCI) have been promoted to be used for neuroprosthetics. However, reports on applications with electroencephalography (EEG) show a demand for a better accuracy and stability. Here we investigate whether near-infrared spectroscopy (NIRS) can be used to enhance the EEG approach. In our study both methods were applied simultaneously in a real-time Sensory Motor Rhythm (SMR)-based BCI paradigm, involving executed movements as well as motor imagery. We tested how the classification of NIRS data can complement ongoing real-time EEG classification. Our results show that simultaneous measurements of NIRS and EEG can significantly improve the classification accuracy of motor imagery in over 90% of considered subjects and increases performance by 5% on average (p < 0:01). However, the long time delay of the hemodynamic response may hinder an overall increase of bit-rates. Furthermore we find that EEG and NIRS complement each other in terms of information content and are thus a viable multimodal imaging technique, suitable for BCI.

KW - Combined NIRS-EEG

KW - Hybrid BCI

KW - Meta-classifier

UR - https://www.scopus.com/pages/publications/80054090365

U2 - 10.1016/j.neuroimage.2011.07.084

DO - 10.1016/j.neuroimage.2011.07.084

M3 - Article

C2 - 21840399

AN - SCOPUS:80054090365

SN - 1053-8119

VL - 59

SP - 519

EP - 529

JO - NeuroImage

JF - NeuroImage

IS - 1

ER -

Enhanced performance by a hybrid NIRS-EEG brain computer interface

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this