Share Email Print
cover

Proceedings Paper

Wavelet data compression for neural network preprocessing
Author(s): Alastair D. McAulay; Jian Tian Li
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Preprocessing is beneficial before classification with neural networks because eliminating irrelevant data produces faster learning due to smaller datasets and due to a reduction of confusion caused by irrelevant data. In this paper we demonstrate a further benefit due to smoothing that may be accomplished at the same time. A common trade off with neural networks is between accuracy of classification of training sets versus accuracy of classification of testing sets not used for training. Classification of testing sets requires the network to interpolate. We show that the smoothing obtained by data compression, by omitting low frequency components of the wavelet transform, can enhance interpolation, thus producing improved classification on testing data sets. A wavelet transform decomposes a signal obtained from a radar simulator into frequency and spatial domains using a Mexican hat wavelet. Varying cut-off frequencies are used in omitting higher frequency components of the wavelet transform. An inverse wavelet transform shows the lest square degradation in signal due to smoothing. We demonstrate that omitting high frequency terms results in faster computation in neural network learning and provides better interpolation, that is increases classification performance with testing data sets. The reasons are explained. The wavelet compression results are compared with using low pass filtering.

Paper Details

Date Published: 9 July 1992
PDF: 10 pages
Proc. SPIE 1699, Signal Processing, Sensor Fusion, and Target Recognition, (9 July 1992); doi: 10.1117/12.138244
Show Author Affiliations
Alastair D. McAulay, Wright State Univ. (United States)
Jian Tian Li, Wright State Univ. (United States)


Published in SPIE Proceedings Vol. 1699:
Signal Processing, Sensor Fusion, and Target Recognition
Vibeke Libby; Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top