Electromagnetic detection of dielectric cylinders by a neural network approach

Caorsi, S.; Gamba, Paolo

doi:10.1109/36.752198

Cited by 111 publications

(45 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The capability of this architecture in facing inverse scattering problems has been already shown in the presence of a homogeneous scenario [13]. Therefore, we used it also for the solution of an inverse scattering problem in the presence of a half-space geometry.…”

Section: The Architecture and The Training Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

An Inverse Scattering Approach Based on A Neural Network Technique for the Detection of Dielectric Cylinders Buried in a Lossy Half-Space

Bermani

Caorsi

Raffetto

2000

PIER

View full text Add to dashboard Cite

Section: The Architecture and The Training Algorithmmentioning

confidence: 99%

“…Therefore, we used it also for the solution of an inverse scattering problem in the presence of a half-space geometry. In particular, we have considered an architecture involving a number of neurons in the hidden layer equal to that of the input layer, as indicated in [13].…”

Section: The Architecture and The Training Algorithmmentioning

confidence: 99%

An Inverse Scattering Approach Based on A Neural Network Technique for the Detection of Dielectric Cylinders Buried in a Lossy Half-Space

Bermani

Caorsi

Raffetto

2000

PIER

View full text Add to dashboard Cite

“…In literature, two approaches can be basically found: inversion techniques mostly based on approximated solutions of the scattering integral equation (Joachimovicz et al, 1991;Caorsi et al, 1993;Pierri et al, 2002;Lambot et al, 2004; Correspondence to: S. Caorsi (salvatore.caorsi@unipv.it) Kao et al, 2007) or "learning by examples" procedures employing artificial neural networks (Hoole, 1993;Caorsi and Gamba, 1999;Youn and Chen, 2003;Caorsi and Cevini, 2005a). The former approach, generally more precise and widely applicable, suffers high computational costs, and machine learning algorithms are now becoming powerful alternatives.…”

Section: Introductionmentioning

confidence: 99%

ANN-based sub-surface monitoring technique exploiting electromagnetic features extracted by GPR signals

Caorsi

Stasolla

2008

Adv. Geosci.

Self Cite

View full text Add to dashboard Cite

Abstract. In this work we consider the problem of determining the dielectric characteristics of sub-surface layers by means of GPR systems. In particular, a suitable electromagnetic feature (the R parameter), strictly related to the geophysical parameters of the scenario, is first extracted from the GPR e.m. signal and then fed to an artificial neural network (ANN) in order to derive the dielectric permittivity of the sub-surface layer.

show abstract

“…When the investigation domain is large, the number of unknowns of the inverse scattering problem increases and an iterative procedure for solving the inverse problem may fail to reach a convergent solution in addition to increasing the computation time [9]. Neural Networks have been employed to detect 2-D dielectric scatterers when only aspect limited scattered data is measurable, with the a priori knowledge that the scatterer is 2-D homogenous and with a circular cross section [10,11].…”

Section: Introductionmentioning

confidence: 99%

Localization of the Investigation Domain in Electromagnetic Imaging of Buried 2-D Dielectric Pipelines With Circular Cross Section

Thomas¹,

Yohannan²,

Lonappan³

et al. 2006

PIER

View full text Add to dashboard Cite

Abstract-Electromagnetic inverse scattering problems are computation intensive, ill-posed and highly non-linear. When the scatterer lies in an inaccessible domain, the ill-posedness is even more severe as only aspect limited data is available. Typical algorithms employed for solving this inverse scattering problem involve a large scale non-linear optimization that generates values for all pixels in the investigation domain including those that might not contain any useful information about the object. This communication is concerned with the localization in the investigation domain prior to inverse profiling of buried 2-D dielectric pipelines having circular cross section. A custom defined degree of symmetry is computed for each transmitter position, which is a measure of the symmetry of the measured (synthetic) scattered field vector. The degree of symmetry vector computed for a scatterer is found to exhibit unique features for the geometric and electric properties of the dielectric pipeline. A probabilistic neural network is trained with the degree of symmetry vectors computed for different object configurations. It classifies the test degree of symmetry vector of the unknown scatterer presented to it into one of the classes that indicate the localized region in the investigation domain in which the pipeline is located. The Distorted Born Iterative procedure is employed for imaging the pipeline that has been localized. The reduction in the investigation domain reduces the degrees of freedom of the inverse scattering problem and the results are found to be much superior to those when the entire investigation domain is employed.

show abstract

Electromagnetic detection of dielectric cylinders by a neural network approach

Cited by 111 publications

References 31 publications

An Inverse Scattering Approach Based on A Neural Network Technique for the Detection of Dielectric Cylinders Buried in a Lossy Half-Space

An Inverse Scattering Approach Based on A Neural Network Technique for the Detection of Dielectric Cylinders Buried in a Lossy Half-Space

ANN-based sub-surface monitoring technique exploiting electromagnetic features extracted by GPR signals

Localization of the Investigation Domain in Electromagnetic Imaging of Buried 2-D Dielectric Pipelines With Circular Cross Section

Contact Info

Product

Resources

About