Bayesian Regression for Artifact correction in ElectroencephalographyKarl-Heinz Fiebig; Vinay Jayaram; Thomas Hesse; Alexander Blank; Jan Peters; Moritz Grosse-Wentrup
In: Gernot R. Müller-Putz; David Steyrl; Selina C. Wriessnegger; Reinhold Scherer (Hrsg.). From Vision to Reality - Proceedings of the 7th Graz Brain-Computer Interface Conference. Graz Brain-Computer Interface Conference (GBCIC-2017), September 18-22, Graz, Austria, Verlag der Technischen Universitaet Graz, 2017.
Many brain-computer interfaces (BCIs) measure brain activity using electroencephalography (EEG). Unfortunately, EEG is highly sensitive to artifacts originating from non-neural sources, requiring procedures to remove the artifactual contamination from the signal. This work presents a probabilistic interpretation for artifact correction that unifies session transfer of linear models and calibration to upcoming sessions. A linear artifact correction model is derived within a Bayesian multi-task learning (MTL) framework, which captures influences of artifact sources on EEG channels across different sessions to correct for artifacts in new sessions or calibrate with session-specific data. The new model was evaluated with a cross-correlation analysis on a real world EEG data set. We show that the new model matches stateof-the-art correlation reduction abilities, but ultimately converges to a simple group mean model for the experimental data set. This observation leaves the proposed MTL approach open for a more detailed investigations of artifact tasks.