Neural Network Inverse Method for Dielectric Structures by Multifrequency Signals

Author

Drobakhin, O.O. ; Doronin, A.V.

Author_Institution

Dept. of Radiophys., Dnepropetrovsk Nat. Univ.

fYear

2006

Firstpage

39

Lastpage

42

Abstract

Application of neural network ideology for layered dielectric structure inverse problem solution is under consideration. The 3-layered feed-forward with activation function as a sigmoid (S-shaped) was chosen. The real part of reflection coefficient at many frequencies is used as input signal. Levenberg-Marquardt algorithm was used for training of the network. Some results of numerical simulation for two-layered structure in presence of Gaussian additive noise are demonstrated

Keywords

Gaussian noise; dielectric properties; feedforward neural nets; inverse problems; signal processing; 3-layered feed-forward; Gaussian additive noise; Levenberg-Marquardt algorithm; inverse problem solution; layered dielectric structure; multifrequency signals; neural network ideology; reflection coefficient; Antenna measurements; Artificial neural networks; Dielectrics; Electromagnetic measurements; Electromagnetic reflection; Frequency; Inverse problems; Neural networks; Parameter estimation; Permittivity measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory, Proceedings of XIth International Seminar/Workshop on

Conference_Location

Tbilisi, Georgia

Print_ISBN

966-02-3873-8

Type

conf

DOI

10.1109/DIPED.2006.314284

Filename

4105755