Wavelet data compression for neural network preprocessing

Alastair D. McAulay; Jian Tian Li

doi:10.1117/12.138244

9 July 1992 Wavelet data compression for neural network preprocessing

Alastair D. McAulay, Jian Tian Li

Proceedings Volume 1699, Signal Processing, Sensor Fusion, and Target Recognition; (1992) https://doi.org/10.1117/12.138244
Event: Aerospace Sensing, 1992, Orlando, FL, United States

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.

Citation Download Citation

Alastair D. McAulay and Jian Tian Li "Wavelet data compression for neural network preprocessing", Proc. SPIE 1699, Signal Processing, Sensor Fusion, and Target Recognition, (9 July 1992); https://doi.org/10.1117/12.138244

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