Share Email Print

Proceedings Paper

Using neural networks to interpret subsurface radar imagery of reinforced concrete
Author(s): L. Newnham; A. Goodier
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper reports aspects of a study into the use of neural networks to interpret sub-surface radar data collected from surveys of a number of construction components containing targets such as reinforcing bars and underslab voids. The paper details the data collection and alternative synthetic data generation, the pre-processing undertaken to reduce the volume of the inputs to the neural networks, the neural network topologies investigated and presents the results of the network training and testing.

Paper Details

Date Published: 27 April 2000
PDF: 7 pages
Proc. SPIE 4084, Eighth International Conference on Ground Penetrating Radar, (27 April 2000); doi: 10.1117/12.383607
Show Author Affiliations
L. Newnham, Building Research Establishment Ltd. (United Kingdom)
A. Goodier, Building Research Establishment Ltd. (United Kingdom)

Published in SPIE Proceedings Vol. 4084:
Eighth International Conference on Ground Penetrating Radar
David A. Noon; Glen F. Stickley; Dennis Longstaff, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?