Format

Send to

Choose Destination
See comment in PubMed Commons below
Conf Proc IEEE Eng Med Biol Soc. 2012;2012:4911-4. doi: 10.1109/EMBC.2012.6347095.

Using NIRS as a predictor for EEG-based BCI performance.

Author information

1
Department of Computer Science, Technical University Berlin, Germany. fazli@cs.tu-berlin.de

Abstract

Multimodal recordings of EEG and NIRS of 14 subjects are analyzed in the context of sensory-motor based Brain Computer Interface (BCI). Our findings indicate that performance fluctuations of EEG-based BCI control can be predicted by preceding Near-Infrared Spectroscopy (NIRS) activity. These NIRS-based predictions are then employed to generate new, more robust EEG-based BCI classifiers, which enhance classification significantly, while at the same time minimize performance fluctuations and thus increase the general stability of BCI performance.

PMID:
23367029
DOI:
10.1109/EMBC.2012.6347095
[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for IEEE Engineering in Medicine and Biology Society
    Loading ...
    Support Center