Inverse scattering of dielectric cylinders by using radial basis function neural networks

In this paper, a new on-line inverse scattering methodology, which is based on radial basis function neural networks, is presented. The construction o f these networks is implemented by means of the orthogonal least squares al gorithm. By applying this training algorithm we can calculate the values of the free parameters of the network and also define its structure. Thus a t rial-and-error strategy concerning the definition of the network size is av oided. In particular, the network is constructed to perforin the mapping fr om scattered-field measurements to electromagnetic and geometric properties of the scatterer. Although this approach can be applied to various inverse scattering applications, we focus on the reconstruction of cylindrical die lectric scatterers from simulated measurements of the scattered electric fi eld, while transverse magnetic illuminations are used. The objective is to estimate the relative dielectric constant, the size, and the position of th e scatterer. In numerical results an investigation of the performance of th e network is carried out. After the completion of the training procedure th e network can rapidly estimate the scatterer properties, without extreme st orage demands. Finally, the robustness of the proposed methodology in inver ting measurements that are corrupted by additive white Gaussian noise is ex amined.