A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300-based BCI

Abstract

This work introduces a novel classifier for a P300-based speller, which, contrary to common methods, can be trained entirely unsupervisedly using an Expectation Maximization approach, eliminating the need for costly dataset collection or tedious calibration sessions. We use publicly available datasets for validation of our method and show that our unsupervised classifier performs competitively with supervised state-of-the-art spellers. Finally, we demonstrate the added value of our method in different experimental settings which reflect realistic usage situations of increasing difficulty and which would be difficult or impossible to tackle with existing supervised or adaptive methods.

Zero Training for BCI – Reality for BCI Systems Based on Event-Related Potentials

“…Now, another brick has been placed to form this important fundament -a completely unsupervised signal processing approach [16]. Discarding calibration recordings completely -even for novel subjects -this method allows for a kick-start usage of BCI systems, which are based on eventrelated potentials (ERP) like the P300.…”

Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review

“…It also allows keeping optimal performance by adapting to mental and environmental changes during the session, enabling continuous adjustments ("pursuing"), thus ensuring reliability and robustness throughout the session and across-sessions [30,62,[64][65][66].…”

Subject-Independent P300 BCI Using Ensemble Classifier, Dynamic Stopping and Adaptive Learning

“…We conduct the experiments using 5 different classification schemes, evaluated on a large multi-subject public P3S datasets which had been used in various studies [11], [22], [23]. The results show that our method can boost up the P3S performance (in terms of higher accuracy and shorter time) by a significant amount as compared to the related studies.…”