Preliminary results from real-time 'brain-computer interface' experiments are presented. The analysis is based on autoregressive modelling of a single EEG channel coupled with classification and temporal smoothing under a Bayesian paradigm. It is shown that uncertainty in decisions is taken into account under such a formalism and that this may be used to reject uncertain samples, thus dramatically improving system performance. Using the strictest rejection method, a classification performance of 86.5 +/- 6.9% is achieved over a set of seven subjects in two-way cursor movement experiments.
|Number of pages||6|
|Journal||Medical and Biological Engineering and Computing|
|Publication status||Published - Jan 2000|
- Bayes Theorem
- Computer-Assisted Signal Processing
- User-Computer Interface