Dr Carmen Vidaurre | Brain-computer interface and sensorimotor oscillations: novel perspectives and methods

Brain-computer interfaces (BCI) based on the modulation of sensorimotor-rhythms are often inefficient. There exist users who cannot achieve sufficient BCI control. Often, the classifiers are unable to separate different motor imagery tasks with high accuracy. This problem is related to the low signal-to-noise ratio of the features used for training. Also, changes occurring in the signals between offline and online phases of a BCI experiment or even during the feedback phase reduce the classification performance of BCI systems. In this talk I will show two alternatives to improve BCI control of users and neural characteristics related to it. One is based on the use of alternative calibration signals with better signal-to-noise ratio than motor imagery signals. I will also present results of a co-adaptive experiment with inexperienced users. Finally, I will talk about a new method to maximize the coherence of neural signals from different sources, that can be used to for example to better estimate cortico-muscular-coherence. All this research has been performed collaboratively between the department of Neurology at MPI for Human Cognitive and Brain Sciences, Leipzig, the Machine Learning Group of the TU-Berlin and the Dept. of Informatics, Statistics and Mathematics from the Public University of Navarre.