Minimizing calibration time of single-trial recognition of error potentials in brain-computer interfaces
One of the main problems of both synchronous and asynchronous EEG-based BCIs is the need of an initial calibration phase before the system can be used. This phase is necessary due to the high non-stationarity of the EEG, since it changes between sessions and users. The calibration limits the BCI systems to scenarios where the outputs are very controlled, and makes these systems non-friendly and exhausting for the users. Although it has been studied how to reduce calibration time for asynchronous signals, it is still an open issue for event- related potentials. Here, we analyze the differences between users for single-trial error-related potentials, and propose the design of classifiers based on inter-subject features to either remove or minimize the calibration time. The results show that it is possible to have a classifier with a high performance from the beginning of the experiment, which is able to adapt itself without the user noticing.