Title :
A neural network electromagnetic approach for GPR pavement diagnostic: A preliminary study
Author :
Caorsi, Salvatore ; Stasolla, Mattia
Author_Institution :
Dept. of Electron., Univ. of Pavia, Pavia, Italy
Abstract :
In this paper, a preliminary study, based on GPR data analysis by means of artificial neural networks, for automatic pavement diagnostic is addressed. The proposed solving solution models the pavement as a multi-layered medium composed of N parallel homogenous layers, which are separately analyzed through a recursive procedure able to reconstruct their permittivity and thickness. The basic processing module of the whole procedure, is here presented.
Keywords :
data analysis; geophysical techniques; ground penetrating radar; neural nets; GPR data analysis; automatic pavement diagnostic; multi-layered medium; neural network electromagnetic approach; parallel homogenous layers; pavement profiling; Artificial neural networks; Data analysis; Dielectrics; Electronic mail; Fluctuations; Geometry; Ground penetrating radar; Neural networks; Permittivity; Signal generators; GPR; artificial neural networks; pavement profiling;
Conference_Titel :
Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009
Conference_Location :
Cape Town
Print_ISBN :
978-1-4244-3394-0
Electronic_ISBN :
978-1-4244-3395-7
DOI :
10.1109/IGARSS.2009.5416947