author = {Lucie Daubigney and Olivier Pietquin},
title = {Single-pass P300 detection with Kalman filtering and SVMs},
year = {2011},
booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2011)},
pages = {399-404},
month = {April},
address = {Bruges (Belgium)},
url = {http://www.metz.supelec.fr//metz/personnel/pietquin/pdf/ESANN_2011_LDOP.pdf},
abstract = {Brain Computer Interfaces (BCI) are systems enabling humans to communicate with machines through signals generated by the brain. Several kinds of signals can be envisioned as well as means to measure them. In this paper we are particularly interested in visually evoked potential signals (P300) measured with surface electroencephalograms (EEG). These signals arise when the human is stimulated with visual inputs 300 ms after the stimulus has been received. Yet, the EEG signal is often very noisy which makes the P300 detection hard. It is customary to use an average of several trials to enhance the P300 signal and reduce the random noise but this results in a lower bit rate of the interface. In this contribution, we propose a novel approach to P300 detection using Kalman filtering and SVMs. Experiments show that this method allows single-pass detection pass detections of P300.}