@article {2133, title = {A graphical model framework for decoding in the visual ERP-based BCI speller.}, journal = {Neural Comput}, volume = {23}, year = {2011}, month = {01/2011}, pages = {160-82}, abstract = {

We present a graphical model framework for decoding in the visual ERP-based speller system. The proposed framework allows researchers to build generative models from which the decoding rules are obtained in a straightforward manner. We suggest two models for generating\ brain\ signals conditioned on the stimulus events. Both models incorporate letter frequency information but assume different dependencies between\ brain\ signals and stimulus events. For both models, we derive decoding rules and perform a discriminative training. We show on real visual speller data how decoding performance improves by incorporating letter frequency information and using a more realistic graphical model for the dependencies between the\ brain\ signals and the stimulus events. Furthermore, we discuss how the standard approach to decoding can be seen as a special case of the graphical model framework. The letter also gives more insight into the discriminative approach for decoding in the visual speller system.

}, keywords = {Artificial Intelligence, Computer User Training, Discrimination Learning, Electroencephalography, Evoked Potentials, Evoked Potentials, Visual, Humans, Language, Models, Neurological, Models, Theoretical, Reading, Signal Processing, Computer-Assisted, User-Computer Interface, Visual Cortex, Visual Perception}, issn = {1530-888X}, doi = {10.1162/NECO_a_00066}, url = {http://www.ncbi.nlm.nih.gov/pubmed/20964540}, author = {Martens, S M M and Mooij, J M and Jeremy Jeremy Hill and Farquhar, Jason and Sch{\"o}lkopf, B} }