Discrimination of task-related eeg signals using diffusion adaptation and S-transform coherency

This work presents a novel approach for discriminating complex mental and motor tasks using diffusion adaptation and brain connectivity measures. In particular, in this paper, we use a S-transform based measure to estimate the connectivity on single-trial basis and diffusion Kalman filtering to train a model that can classify different tasks. The superiority of the method is proven when compared with solutions that don´t rely on cooperation.