Geometric and dielectric characterization of buried cylinders by using simple time-domain electromagnetic data and neural networks

An analysis of the performances of the neural network approach for the geometric and dielectric characterization of buried cylinders is carried out. The neural-network-process data are obtained from the time-domain formulation of the electromagnetic scattering problem. This analysis is based on the rise of simplified models which allow the analytical calculations of the solutions. The question of what data need to be extracted from the transient scattered field in order to make the characterization process work correctly is addressed, and the results obtained are shown. (C) 2000 John Wiley & Sons, Inc.