Abstract : We consider a P300 BCI application where the subjects can write figures and letters in an unsupervised fashion. We (i) show that a generic speller can attain the state-of-the-art accuracy without any training phase or calibration and (ii) present an adaptive setup that consistently increases the bit rate for most of the subjects.
Type de document :
Communication dans un congrès
22nd European Symposium on Artificial Neural Networks, Apr 2014, Bruges, Belgium. 2014
https://hal.inria.fr/hal-01104024
Contributeur : Maureen Clerc
<>
Soumis le : samedi 17 janvier 2015 - 20:50:15
Dernière modification le : jeudi 18 janvier 2018 - 02:14:29
Document(s) archivé(s) le : vendredi 11 septembre 2015 - 06:53:16
Emmanuel Daucé, Eoin Thomas. Evidence build-up facilitates on-line adaptivity in dynamic environments: example of the BCI P300-speller. 22nd European Symposium on Artificial Neural Networks, Apr 2014, Bruges, Belgium. 2014. 〈hal-01104024〉