Unsupervised adaptation of the LDA classifier for Brain-Computer Interfaces
Year: 2008
Type: article
Abstract: This paper discusses simulated on-line unsupervised adaptation of the LDA classifier in order to counteract the harmful effect of non-class related non-stationarities in EEG during BCI sessions. Three types of adaptation procedures were applied to the two large BCI data sets from TU Graz and Berlin BCI project. Our results demonstrate that the unsupervised adaptive classifiers can improve performance substantially under different BCI settings. More importantly, since label information is not necessary, they are applicable to wide ranges of practical BCI tasks.
Authors: C. Vidaurre, A. Schlögl, B. Blankertz, M. Kawanabe, K.-R. Müller
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7006819763