Determination of the permittivity of spherical scatterers using a neural network approach

Abstract EN

A solution of the inverse scattering problem for spherical scatterers based on the neural network approach is presented.

The neural network analysis is performed to predict the lossy and lossless dielectric constant of the spherical scatterer from the scattered field coefficients.

The scattered field coefficients are used to train the neural network to model the highly nonlinear relation between the dielectric constant of the scatterer and the scattered field coefficients.

To test the model, a random set of amplitude coefficients is fed to the neural network and the predicted results are in very good agreement with the analytical data.