DMCA
Boosting Bit Rates and Error Detection for the Classification of Fast-paced Motor Commands Based on Single-trial EEG Analysis (2003)
Cached
Download Links
| Citations: | 75 - 25 self |
BibTeX
@MISC{Blankertz03boostingbit,
author = {Benjamin Blankertz and Guido Dornhege and Christin Schäfer and Roman Krepki and Jens Kohlmorgen and Klaus-Robert Müller and Volker Kunzmann and Florian Losch and Gabriel Curio},
title = {Boosting Bit Rates and Error Detection for the Classification of Fast-paced Motor Commands Based on Single-trial EEG Analysis},
year = {2003}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Brain-Computer-Interfaces (BCI) involve two coupled adapting systems: the human subject and the computer. In developing our BCI, our goal was to minimize the need for subject training and to impose the major learning load on the computer. To this end, we use behavioral paradigms that exploit single-trial EEG potentials preceding voluntary nger movements. Here, we report recent results on the basic physiology of such pre-movement event-related potentials (ERP): 1) We predict the laterality of imminent left vs. right hand nger movements in a natural keyboard typing condition and demonstrate that a single-trial classi- cation based on the lateralized Bereitschaftspotential (BP) achieves good accuracies even at a pace as fast as 2 taps per second. Results for 4 out of 8 subjects reached a peak information transfer rate of more than 15 bits per minute (bpm); the 4 other subjects reached 6-10 bpm. 2) We detect cerebral error potentials from single false-response trials in a forced-choice task, reecting the subject's recognition of an erroneous response. Based on a specically tailored classi cation procedure that limits the rate of false positives at, e.g. 2 %, the algorithm manages to detect 85 % of error trials in 7/8 subjects. Thus, concatenating a primary single-trial BP-paradigm involving nger classication feedback with such secondary error detection could serve as an ecient on-line conrmation/correction tool for improvement of bit rates in a future BCI setting. As the present variant of the Berlin BCI (BBCI) is designed to achieve fast classications in normally behaving subjects, it opens a new perspective for assistance of action control in time-critical behavioral contexts; the potential transfer to paralysed patients will require further study.
Keyphrases
bit rate single-trial eeg analysis error detection fast-paced motor command single false-response trial action control erroneous response good accuracy subject training natural keyboard pre-movement event-related potential single-trial eeg potential basic physiology single-trial classi cation primary single-trial bp-paradigm error trial human subject berlin bci voluntary nger movement 6-10 bpm cerebral error potential peak information transfer rate present variant potential transfer ecient on-line conrmation correction tool recent result fast classications imminent left v secondary error detection false positive time-critical behavioral context classication feedback new perspective right hand nger movement classi cation procedure future bci setting forced-choice task behavioral paradigm
