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.
Olaf Blanke, José del Rocio Millán Ruiz, Ronan Boulic, Bruno Herbelin, Ricardo Andres Chavarriaga Lozano, Fumiaki Iwane
Ricardo Andres Chavarriaga Lozano, Lucian Andrei Gheorghe, Marija Uscumlic, Ruslan Aydarkhanov
Friedhelm Christoph Hummel, Takuya Morishita, Pierre Theopistos Vassiliadis, Claudia Bigoni, Andéol Geoffroy Cadic-Melchior