Asynchronous, Adaptive BCI using Movement Imagination Training and Rest-State Inference

S. Fazli, M. Danóczy, M. Kawanabe, and F. Popescu (Germany)


Machine learning, brain-computer interface, asynchronous design, Bayesian inference, idle state


The current study introduces an adaptive Bayesian learn ing scheme which discriminates between left hand move ment imagination, right hand movement imagination and idle (i.e. “no-command”) state in an EEG Brain Com puter Interface. Unlike previous BCI designs using mini mal training, the user does not have to continuously imag ine a movement in order to control a cursor. Rather, the cursor reacts meaningfully only when a trained movement imagination is produced. The algorithmic approach was to compute Gaussian probability distributions in log-variance of main Common Spatial Patterns for each movement class, infer from these a prior distribution of idle-class, and al low each distribution to adapt during feedback BCI perfor mance. By producing a markedly different but complexity constrained partition of feature space than with LDA clas sifiers, allowing the classifier to adapt and introducing an intermediary state driven by the classifier output through a dynamic control law, 90% level classification accuracy was achieved with less than 5 seconds activation time from cued onset.

Important Links:

Go Back