Regularized kernel-based Wiener filtering. Application to magnetoencephalographic signals denoising

Author

Constantin, Ibtissam ; Richard, Cedric ; Lengelle, Regis ; Soufflet, Laurent

Author_Institution

FORENAP, Centre Hospitalier de Rouffach, France

Volume

4

fYear

2005

fDate

18-23 March 2005

Abstract

We take a new approach in nonlinear Wiener filtering. This approach is based on the theory of reproducing kernel Hilbert spaces (RKHS). By means of the well-known "kernel trick", the arithmetic operations are carried out in the initial space. We show that the solution is given by solving a linear system which may be ill-conditioned. To find a solution for such a problem, we resorted to a kernel principal component analysis (KPCA) method to perform dimensionality reduction in RKHS. A new reduced-rank Wiener filter based on KPCA is thus elaborated. It is applied on magnetoencephalographic (MEG) data for cardiac artifacts extraction.

Keywords

Hilbert spaces; Wiener filters; arithmetic; filtering theory; magnetoencephalography; medical signal processing; nonlinear filters; principal component analysis; signal denoising; MEG; arithmetic operations; cardiac artifacts extraction; dimensionality reduction; kernel PCA; kernel principal component analysis; kernel trick; magnetoencephalographic signal denoising; nonlinear Wiener filtering; reduced-rank Wiener filter; regularized kernel-based Wiener filtering; reproducing kernel Hilbert spaces; Data mining; Hilbert space; Kernel; Linear systems; Magnetic separation; Nonlinear filters; Principal component analysis; Signal denoising; Space technology; Wiener filter;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8874-7

Type

conf

DOI

10.1109/ICASSP.2005.1416002

Filename

1416002