Journal
FRONTIERS IN NEUROSCIENCE
Volume 3, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/neuro.20.003.2009
Keywords
paralysis; MRCP; motor imagination; brain-computer interface
Categories
Funding
- Danish Research Agency [2117-05-0083]
- Obel Family Foundation
- Deutsche Forschungsgemeinschaft (DFG), BMBF, Bundesministerium fur Bildung und Forschung, Bernstein Center, Neurocomputation [01GQ0831]
- Spanish Ministry of Science and European Funds (FEDER) [SEJ2007-62312]
Ask authors/readers for more resources
The study investigated the possibility of identifying the speed of an imagined movement from EEG recordings in amyotrophic lateral sclerosis (ALS) patients. EEG signals were acquired from four ALS patients during imagination of wrist extensions at two speeds (fast and slow), each repeated up to 100 times in random order. The movement-related cortical potentials (MRCPs) and averaged sensorimotor rhythm associated with the two tasks were obtained from the EEG recordings. Moreover, offline single-trial EEG classification was performed with discrete wavelet transform for feature extraction and support vector machine for classification. The speed of the task was encoded in the time delay of peak negativity in the MRCPs, which was shorter for faster than for slower movements. The average single-trial misclassification rate between speeds was 30.4 +/- 3.5% when the best scalp location and time interval were selected for each individual. The scalp location and time interval leading to the lowest misclassification rate varied among patients. The results indicate that the imagination of movements at different speeds is a viable strategy for controlling a brain-computer interface system by ALS patients.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available