A kernel based system for the estimation of non-stationary signals

Author

Jemili, Kanaan ; Westerkamp, John J.

Author_Institution

Dept. of Electr. Eng., Dayton Univ., OH, USA

Volume

5

fYear

1995

fDate

9-12 May 1995

Firstpage

3423

Abstract

A new signal estimation technique is introduced for highly non-stationary signals. The system uses the wavelet transform to extract time-frequency components of the signal plus noise, followed by a radial basis function neural network that adaptively estimates the underlying signal. The method is applied to the visual evoked potential (EP) signal, which is a transient signal corrupted by the ongoing electroencephalogram (EEG) noise, with a signal-to-noise ratio often less than -6 dB. The proposed system gives good time-varying estimates of the EP, while suppressing the on-going EEG

Keywords

adaptive estimation; adaptive signal processing; electroencephalography; interference suppression; medical signal processing; neural nets; time-frequency analysis; visual evoked potentials; wavelet transforms; electroencephalogram noise; kernel based system; nonstationary signals; radial basis function neural network; signal estimation technique; time-frequency components; time-varying estimates; transient signal; visual evoked potential signal; wavelet transform; Delay; Discrete wavelet transforms; Electroencephalography; Estimation; Kernel; Neural networks; Signal processing; Signal to noise ratio; Time frequency analysis; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479721

Filename

479721