Electromagnetic detection of dielectric cylinders by a neural network approach

In this paper, the neural network approach is applied to the detection of c ylindric objects as well as their geometric and electrical characteristics inside a given investigation domain. The electric field values scattered by the object and available at a small number of locations are fed into the n etwork, whose output is the dielectric permittivity, and the location and r adius of the cylinder. The results are evaluated using different sets of te sting data, and the dependence of the various output parameters to the inpu t are considered. The algorithm performance shows that the approach is able to solve the inve rse scattering problem quickly. This may be useful for real-time remote-sen sing applications.