EURASIP Journal on Applied Signal Processing
Volume 2005 (2005), Issue 19, Pages 3128-3140
doi:10.1155/ASP.2005.3128
Feature Selection and Blind Source Separation in an EEG-Based Brain-Computer Interface
1Department of Computer Science, Center for Biomedical Research in Music, Molecular,
Cellular, and Integrative Neurosciences Program and Department of Psychology, Colorado State University, Fort Collins 80523, CO, USA
2Department of Computer Science, Colorado State University, Fort Collins 80523, CO, USA
3Department of Mathematics, Colorado State University, Fort Collins 80523, CO, USA
4Department of Computer Science and Molecular, Cellular, and Integrative Neurosciences Program, Colorado State University, Fort Collins 80523, CO, USA
5Center for Biomedical Research in Music and Molecular, Cellular, and Integrative Neurosciences Program, Colorado State University, Fort Collins 80523, CO, USA
Received 1 February 2004; Revised 14 March 2005
Abstract
Most EEG-based BCI systems make use of well-studied
patterns of brain activity. However, those systems involve tasks
that indirectly map to simple binary commands such as “yes” or
“no” or require many weeks of biofeedback training. We
hypothesized that signal processing and machine learning methods
can be used to discriminate EEG in a direct “yes”/“no” BCI
from a single session. Blind source separation (BSS) and spectral
transformations of the EEG produced a 180-dimensional feature
space. We used a modified genetic algorithm (GA) wrapped around a
support vector machine (SVM) classifier to search the space of
feature subsets. The GA-based search found feature subsets that
outperform full feature sets and random feature subsets. Also, BSS
transformations of the EEG outperformed the original time series,
particularly in conjunction with a subset search of both spaces.
The results suggest that BSS and feature selection can be used to
improve the performance of even a “direct,” single-session BCI.