From full calibration to zero training for a code-modulated visual evoked potentials brain computer interface

Objective. Typically, a brain computer interface (BCI) is calibrated using user- and session-specific data because of the individual idiosyncrasies and the non-stationary signal properties of the electroencephalogram (EEG). Therefore, it is normal that BCIs undergo a time-consuming passive training stage that prevents users from directly operating it. In this study, we systematically reduce the training dataset in a step-wise fashion, to ultimately arrive at a calibration-free method for a code-modulated visually evoked potentials (cVEP) based BCI to fully eliminate the tedious training stage.

Approach. In an extensive offline analysis we compare our sophisticated encoding model with a traditional event-related potential (ERP) technique. We calibrate the encoding model in a standard way, with data limited to a single class while generalizing to all others, and without any data. Additionally, we investigate the feasibility of the zero-training cVEP BCI in an online setting.

Main results. By adopting the encoding model, the training data can be reduced substantially, while maintaining both the classification performance as well as the explained variance of the ERP method. More so, with data of only a one class or even no data at all, it still shows excellent performance. Besides, the zero-training cVEP BCI achieved high communication rates in an online spelling task, proving its feasibility in practical use.

Significance. To date this is the fastest zero-training cVEP BCI in the field, allowing high communication speeds without calibration while using only a few non-invasive water-based EEG electrodes. This allows to skip the training stage altogether and spent all precious time on direct operation. This minimizes session time and opens up new exciting directions to practical plug-and-play BCI. Fundamentally, these results validate that the adopted neural encoding model compresses data into event-responses without loss of explanatory power as compared to using full ERPs as template.