Exploring Session-to-Session Transfer for Brain-Computer Interfaces based on Code-Modulated Visual Evoked Potentials

Brain-computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs) hold promise to serve as a fast and reliable hands-free communication tool for people with severe disabilities. A c-VEP BCI application presents flickering target objects (e. g. letters of a keyboard) coded with different time-lags of a code pattern. Template matching methods are used to identify the target of interest. Unfortunately, this approach requires a training session, in which several trials of EEG data are recorded and analysed. Long training sessions are necessary to ensure good signal-to-noise ratios. For the user, these training sessions may be tedious. Especially for patients, who may use the system on a daily basis e. g. for communication, alternative approaches are desirable. This paper investigates the feasibility of session-to-session transfer of EEG templates for c-VEP BCIs, where templates recorded in a previous session are used, so the application could be used instantly. Ten healthy participants went through training and copy-spelling tasks in two experimental sessions (they were scheduled two weeks apart). In the second session, the templates recorded in the first session were used. Eight participants yielded good results with the session-to-session transfer approach with accuracies of 97.1% and information transfer rates of 85.7 bit/min on average. For these participants, the results were not significantly different from the values achieved using the standard approach (training in the same session). For two participants, however, the system was not controllable with the priorly recorded templates. The results demonstrate that for most users daily recalibration is not required.