In this study, a radial basis function neural network approach is applied for the estimation of the localization and the radius of a conducting cylinder with a circular cross-section coated with a dielectric material. A set of features, the radar cross-section (RCS) values, are derived from scattered fields, which are calculated using the surface equivalence principle and the method of moment. RCS values are obtained using 10 different scattering angles that are fed into the network. The outputs of the network are the location (x0, y0) and the radius (rp) of the conducting cylinder. This is an application of the electromagnetic inverse scattering of the objects embedded in a material based on the use of a neural network.

In this study, a radial basis function neural network approach is applied for the estimation of the localization and the radius of a conducting cylinder with a circular cross-section coated with a dielectric material. A set of features, the radar cross-section (RCS) values, are derived from scattered fields, which are calculated using the surface equivalence principle and the method of moment. RCS values are obtained using 10 different scattering angles that are fed into the network. The outputs of the network are the location (x0, y0) and the radius (rp) of the conducting cylinder. This is an application of the electromagnetic inverse scattering of the objects embedded in a material based on the use of a neural network.