Noise Reduction in a Non-Homogenous Ground Penetrating Radar Problem by Multiobjective Neural Networks

Author

Travassos, X.L., Jr. ; Vieira, D. A G ; Palade, V. ; Nicolas, A.

Author_Institution

SENAI-Centro Integrado de Manufatura e Tecnol., Salvador

Volume

45

Issue

3

fYear

2009

fDate

3/1/2009 12:00:00 AM

Firstpage

1454

Lastpage

1457

Abstract

This paper applies artificial neural networks (ANNs) trained with a multiobjective algorithm to preprocess the ground penetrating radar data obtained from a finite-difference time-domain (FDTD) model. This preprocessing aims at improving the target´s reflected wave signal-to-noise ratio (SNR). Once trained, the NN behaves as an adaptive filter which minimizes the cross-validation error. Results considering both white and colored Gaussian noise, with many different SNR, are presented and they show the effectiveness of the proposed approach.

Keywords

AWGN; adaptive filters; finite difference time-domain analysis; ground penetrating radar; neural nets; FDTD model; adaptive filter; artificial neural networks; colored Gaussian noise; cross-validation error; finite-difference time-domain model; multiobjective neural networks; noise reduction; nonhomogenous ground penetrating radar; target reflected wave; white Gaussian noise; Ground penetrating radar; inverse problems; multiobjective training algorithms; neural networks (NNs); noise; regularization methods;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/TMAG.2009.2012677

Filename

4787489