Machine-Learning Based Co-adaptive Calibration: Towards a Cure for BCI illiteracy

Brain-Computer Interfaces (BCIs) allow users to control a computer application by brain activity as acquired, e.g., by EEG. In our classic Machine Learning approach to BCIs, the participants undertake a calibration measurement without feedback to acquire data to train the BCI system. After the training, the user can control a BCI and improve the operation through some type of feedback. However, not all BCI users are able to perform sufficiently well during feedback operation. In fact, a non-negligible portion of participants (estimated 15%–30%) cannot control the system (BCI illiteracy problem, generic to all motor imagery based BCIs). We hypothesize that one main difficulty for a BCI-user is the transition from off-line calibration to on-line feedback. In this work we therefore investigate adaptive machine learning methods to eliminate offline calibration and analyze the performance of 11 volunteers in a BCI based on the modulation of sensorimotor rhythms. We present an adaptation scheme that individually guides the user initially starting from a subject-independent classifier operating on simple features to a subject-optimized state-of-the-art classifier within one session, while the user interacts continuously. These initial runs use supervised techniques for robust co-adaptive learning of user and machine. Subsequent runs use unsupervised adaptation to track the features’ drift during the session and provide an unbiased measure of BCI performance. Using this approach, without any off-line calibration measurement, good performance was obtained by six users (also one novice) after 3-6 minutes of adaptation. More importantly, this novel guided learning allows also participants suffering from BCI illiteracy to gain significant control with the BCI in less than 60 minutes. Additionally, one volunteer without sensory motor idle rhythm peak in the