Improving zero-training brain-computer interfaces by mixing model estimators.

@article{Verhoeven2017ImprovingZB,
  title={Improving zero-training brain-computer interfaces by mixing model estimators.},
  author={Thibault Verhoeven and David H{\"u}bner and Michael Tangermann and Karen Reetz M{\"u}ller and Joni Dambre and Pieter-Jan Kindermans},
  journal={Journal of neural engineering},
  year={2017},
  volume={14 3},
  pages={036021}
}
OBJECTIVE Brain-computer interfaces (BCI) based on event-related potentials (ERP) incorporate a decoder to classify recorded brain signals and subsequently select a control signal that drives a computer application. Standard supervised BCI decoders require a tedious calibration procedure prior to every session. Several unsupervised classification methods have been proposed that tune the decoder during actual use and as such omit this calibration. Each of these methods has its own strengths and… CONTINUE READING