Application of neural network and principal component analysis to GPR data

Author

Pantoja, Mario F. ; Rodríguez, Jesús B. ; Bretones, Amelia R. ; de Jong, C.M. ; García, S.G. ; Martin, Rafael G. ; Vieira, Douglas A G

Author_Institution

Dept. Electromagnetismo y Fis. de la Materia, Univ. de Granada, Granada, Spain

fYear

2011

fDate

22-24 June 2011

Firstpage

1

Lastpage

4

Abstract

This communication presents a prediction algorithm for the detection of features in GPR-based surveys. Based on signal processing and soft-computing techniques, the coupled use of principal-component analysis and neural networks enables a definition of an efficient method for analyzing GPR electromagnetic data. Results for detecting features of geological layers demonstrate not only the accuracy of the predictions of the method but also the simple interpretation of its output through reconstructed images of the scenarios.

Keywords

feature extraction; geomagnetism; geophysical image processing; ground penetrating radar; image reconstruction; neural nets; principal component analysis; terrestrial electricity; GPR data; GPR electromagnetic data; GPR-based surveys; feature detection; geological layers; neural network; prediction algorithm; principal component analysis; reconstructed images; signal processing; soft-computing techniques; Artificial neural networks; Finite difference methods; Ground penetrating radar; Materials; Principal component analysis; Time domain analysis; Training; Ground-Penetrating Radar; Neural network applications; Radar signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Ground Penetrating Radar (IWAGPR), 2011 6th International Workshop on

Conference_Location

Aachen

Print_ISBN

978-1-4577-0332-4

Electronic_ISBN

978-1-4577-0331-7

Type

conf

DOI

10.1109/IWAGPR.2011.5963854

Filename

5963854