Post-Adaptation Effects in a Motor Imagery Brain-Computer Interface Online Coadaptive Paradigm

Online coadaptive training has been successfully employed to enable people control motor imagery (MI)-based brain-computer interfaces (BCIs), allowing completely skip the lengthy and demotivating open-loop calibration stage traditionally applied before closed-loop control. However, practical reasons may often dictate eventually switch off decoder adaptation proceed with BCI under a fixed model, situation that remains rather unexplored. This work studies existence magnitude of potential post-adaptation effects on system performance, subject learning brain signal modulation stability in state-of-the-art, regime inspired by game-like design. The results extracted cohort 20 able-bodied individuals reveal ceasing classifier after three runs (approx. 30 min) single-session protocol had no significant impact any examined aspects remaining two (about classifier. Fifteen achieved accuracies are better than chance level allowed them execute given task. These findings alleviate major concern regarding applicability MI training, thus helping further establish this approach allow full exploitation its benefits.