Share Email Print

Proceedings Paper

Signal classification using wavelets and neural networks
Author(s): Christopher M. Johnson; Edward W. Page; Gene A. Tagliarini
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The ability of wavelet decomposition to reduce signals to a relatively small number of components can be exploited in pattern recognition applications. Several recent studies have shown that wavelet decomposition extracts salient signal features which can lead to improved pattern classification by a neural network. The performance of the neural network classifier is heavily dependent upon the ability of wavelet processing to yield discriminatory features. This paper considers the combination of wavelet and neural processing for classifying 1- dimensional signals embedded in noise. Noisy signals were decomposed using the Haar wavelet basis and feedforward neural networks were trained on wavelet series coefficients at various scales. The experiment was repeated using the 4-coefficient Daubechies wavelet basis. The classification accuracy for both wavelet bases is compared over multiple scales, several signal-to-noise ratios, and varying numbers of training epochs.

Paper Details

Date Published: 22 March 1996
PDF: 6 pages
Proc. SPIE 2762, Wavelet Applications III, (22 March 1996); doi: 10.1117/12.235994
Show Author Affiliations
Christopher M. Johnson, SGT, Inc. (United States)
Edward W. Page, Clemson Univ. (United States)
Gene A. Tagliarini, Clemson Univ. (United States)

Published in SPIE Proceedings Vol. 2762:
Wavelet Applications III
Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top