Noise reduction in a non-homogenous ground penetrating radar problem by multiobjective neural networks

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

doi:10.1109/TMAG.2009.2012677

Noise reduction in a non-homogenous ground penetrating radar problem by multiobjective neural networks

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

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

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.

Original language	English
Article number	4787489
Pages (from-to)	1454-1457
Number of pages	4
Journal	IEEE Transactions on Magnetics
Volume	45
Issue number	3
DOIs	https://doi.org/10.1109/TMAG.2009.2012677
Publication status	Published - Mar 2009
Externally published	Yes

Keywords

Ground penetrating radar
Inverse problems
Multiobjective training algorithms
Neural networks (NNs)
Noise
Regularization methods

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/TMAG.2009.2012677

Cite this

@article{4abfa1d85b324c4f9baa1ca9a9810400,

title = "Noise reduction in a non-homogenous ground penetrating radar problem by multiobjective neural networks",

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 = "Ground penetrating radar, Inverse problems, Multiobjective training algorithms, Neural networks (NNs), Noise, Regularization methods",

author = "Travassos, {X. L.} and Vieira, {D. A G} and V. Palade and A. Nicolas",

year = "2009",

month = mar,

doi = "10.1109/TMAG.2009.2012677",

language = "English",

volume = "45",

pages = "1454--1457",

journal = "IEEE Transactions on Magnetics",

issn = "0018-9464",

publisher = "Institute of Electrical and Electronics Engineers",

number = "3",

}

TY - JOUR

T1 - Noise reduction in a non-homogenous ground penetrating radar problem by multiobjective neural networks

AU - Travassos, X. L.

AU - Vieira, D. A G

AU - Palade, V.

AU - Nicolas, A.

PY - 2009/3

Y1 - 2009/3

N2 - 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.

AB - 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.

KW - Ground penetrating radar

KW - Inverse problems

KW - Multiobjective training algorithms

KW - Neural networks (NNs)

KW - Noise

KW - Regularization methods

UR - http://www.scopus.com/inward/record.url?scp=61449223713&partnerID=8YFLogxK

U2 - 10.1109/TMAG.2009.2012677

DO - 10.1109/TMAG.2009.2012677

M3 - Article

AN - SCOPUS:61449223713

SN - 0018-9464

VL - 45

SP - 1454

EP - 1457

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

IS - 3

M1 - 4787489

ER -

Noise reduction in a non-homogenous ground penetrating radar problem by multiobjective neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this