Spatial filtering in the training process of a brain computer interface
- 25 August 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (1094687X) , 639-642
- https://doi.org/10.1109/iembs.2001.1019016
Abstract
The spatial filtering of electroencephalogram data is crucial when analyzing brain activity. Spatial filters increase the signal-to-noise ratio, thus allowing better classification of the analyzed mental states. This study shows the evolution in the selection of the most appropriate spatial filter when subjects are training to control a brain-computer interface. Different filters - the common average reference and the estimation of the surface Laplacian both using finite different methods and spherical splines - have been adapted and evaluated for a particular configuration of electrodes, using only eight positions: F/sub 3/, C/sub 3/, P/sub 3/, C/sub z/, P/sub z/, F/sub 4/, C/sub 4/, and P/sub 4/.Keywords
This publication has 8 references indexed in Scilit:
- Local neural classifier for EEG-based recognition of mental tasksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- A spelling device for the paralysedNature, 1999
- Spatial filter selection for EEG-based communicationElectroencephalography and Clinical Neurophysiology, 1997
- Multichannel EEG-based brain-computer communicationElectroencephalography and Clinical Neurophysiology, 1994
- Numerical Analysis of Electromagnetic FieldsPublished by Springer Nature ,1993
- The Spline-Laplacian in Clinical NeurophysiologyJournal Of Clinical Neurophysiology, 1991
- Spherical splines for scalp potential and current density mappingElectroencephalography and Clinical Neurophysiology, 1989
- A theoretical justification of the average reference in topographic evoked potential studiesElectroencephalography and Clinical Neurophysiology/Evoked Potentials Section, 1985