Online-Capable Cleaning of Highly Artefactual EEG Data Recorded During Real Driving
conference paper
With an increased interest to develop brain-computer interface (BCI) applications that can be used in real-world contexts, comes an increased need to deal with the myriad sources of artefacts that interfere with the signal of interest. We present real-world data recorded in a moving car, contaminated with muscle artifacts, mechanical artifacts, and noise produced by the car’s electrical systems. We use artifact subspace reconstruction and independent component analysis to rigorously clean and filter the data. We demonstrate that using state-of-the-art methods, it is possible to identify cortical processes even in heavily contaminated data.
TNO Identifier
870415
Source title
Proceedings of the 7th Graz Brain-Computer Interface Conference 2017At: Graz, Austria
Files
To receive the publication files, please send an e-mail request to TNO Repository.