Live Demonstration: A Dry electrode-based Brain Computer Interface for P300-based Car Driving

In this live demonstration the RIDDANCE (distuRb-resIstant Dry electroDe-based brAiN Computer intErface) framework is presented. It is a Brain-Computer Interface (BCI) framework that characterizes and counteracts several factors that make difficult applying BCIs to real life contexts. RIDDANCE exploits data from an 8-channel dry EEG headset by g. Tec, Data collection for training/testing is typically carried out in not controlled environment (often disturbed) to improve the training and the classification robustness. For the purpose RIDDANCE embeds a user-tailored neural network (NN) topology selector that find the most robust model in terms of average validation loss. RIDDANCE is optimized for P300-based tasks and tested in a prototype car driving application.