BURIED PLANT-DETECTION - A VOLTERRA SERIES MODELING APPROACH USING ARTIFICIAL NEURAL NETWORKS

This paper discusses the embedding of artificial neural networks (ANNs ) into the framework of the Volterra series for modelling the problem of detecting buried pipes. This problem is formulated as a classificat ion task whereby it is necessary to discriminate between the ground su rface and an actual pipe reflection buried in noise in the return sign al from ground probing radar. The objective is to filter out the unwan ted surface reflection to enable improved mapping of the site being su rveyed. Since the ANN correctly maps out a real test site, it can be v iewed as having modelled the system transfer function relating the tra ining patterns to their respective classes. Using the weights learnt b y the ANN and its nodal functions, this transfer function is mathemati cally formulated. It is shown that the latter leads to a Volterra seri es representation of the pipe detection problem and effectively lends itself to the extraction of the Volterra kernels for this particular s ystem. Copyright (C) 1996 Elsevier Science Ltd