Optimizing spatial filters with kernel methods for BCI applications

Jiacai Zhang; Jianjun Tang; Li Yao

doi:10.1117/12.743539

14 November 2007 Optimizing spatial filters with kernel methods for BCI applications

Jiacai Zhang, Jianjun Tang, Li Yao

Proceedings Volume 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications; 67903V (2007) https://doi.org/10.1117/12.743539
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China

Abstract

Brain Computer Interface (BCI) is a communication or control system in which the user's messages or commands do not depend on the brain's normal output channels. The key step of BCI technology is to find a reliable method to detect the particular brain signals, such as the alpha, beta and mu components in EEG/ECOG trials, and then translate it into usable control signals. In this paper, our objective is to introduce a novel approach that is able to extract the discriminative pattern from the non-stationary EEG signals based on the common spatial patterns(CSP) analysis combined with kernel methods. The basic idea of our Kernel CSP method is performing a nonlinear form of CSP by the use of kernel methods that can efficiently compute the common and distinct components in high dimensional feature spaces related to input space by some nonlinear map. The algorithm described here is tested off-line with dataset I from the BCI Competition 2005. Our experiments show that the spatial filters employed with kernel CSP can effectively extract discriminatory information from single-trial EGOG recorded during imagined movements. The high recognition of linear discriminative rates and computational simplicity of "Kernel Trick" make it a promising method for BCI systems.

Citation Download Citation

Jiacai Zhang, Jianjun Tang, and Li Yao "Optimizing spatial filters with kernel methods for BCI applications", Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 67903V (14 November 2007); https://doi.org/10.1117/12.743539

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available