An electromagnetic approach based on neural networks for the GPR investigation of buried cylinders

An electromagnetic approach based on neural networks for the GPR investigation of buried cylinders Author(s): Caorsi, S (Caorsi, S); Cevini, G (Cevini, G) Source: IEEE GEOSCIENCE AND REMOTE SENSING LETTERS Volume: 2 Issue: 1 Pages: 3-7 DOI: 10.1109/LGRS.2004.839648 Published: JAN 2005 Times Cited: 9 (from Web of Science) Cited References: 24 [ view related records ] Citation Map Abstract: In this letter, neural networks (NNs) are used to reconstruct the geometric and dielectric characteristics of buried cylinders. The NN is designed to work with input data extracted from the transient electric fields scattered by the target. To this aim, a simple simulation of a typical ground-penetrating radar setting is performed and different sets of data examined. Moreover, different neural network algorithms have been exploited, and results have been compared. Finally, the "robustness" of the proposed approach has been tested against noisy data and against uncertainties in the modelization. Accession Number: WOS:000230795700001 Document Type: Article Language: English Author Keywords: buried objects; ground-penetrating radar (GPR); microwave imaging; neural network (NN) KeyWords Plus: GROUND-PENETRATING RADAR; BORN ITERATIVE METHOD; INVERSE-SCATTERING; DIELECTRIC CHARACTERIZATION; CONDUCTING CYLINDERS; GRADIENT-METHOD; OBJECTS; TOMOGRAPHY Reprint Address: Caorsi, S (reprint author), Univ Pavia, Dept Elect, I-27100 Pavia, Italy Addresses: 1. Univ Pavia, Dept Elect, I-27100 Pavia, Italy E-mail Address: salvatore.caorsi@unipv.it, gaia.cevini@unipv.it Publisher: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 445 HOES LANE, PISCATAWAY, NJ 08855 USA Web of Science Category: Geochemistry & Geophysics; Engineering, Electrical & Electronic; Remote Sensing Subject Category: Geochemistry & Geophysics; Engineering; Remote Sensing IDS Number: 949NP ISSN: 1545-598X