Abstract
The quantitative inspection of unknown targets or bodies by means of microwave tomography requires a proper modeling of the field scattered by the structures under test, which in turn depends on several factors related to the adopted antennas and measurement configuration. In this article, a multifrequency tomographic approach in nonconstant-exponent Lebesgue spaces is enhanced by a preliminary step that processes the measured scattered field with a neural network based on long short-term memory cells. In the considered cases, this approach allows dealing with measurements in three-dimensional settings obtained with non-ideal antennas and measurement points, while retaining a canonical two-dimensional formulation of the inverse problem. The adopted data-driven model is trained with a set of simulations of cylindrical targets performed with a finite-difference time domain method, considering a simplified bistatic measurement configuration as an initial case study. The inversion procedure is then validated with numerical simulations involving cylindrical and spherical structures.
Highlights
T HE RECENT advances in microwave imaging are paving the way to many interesting scenarios, which range from innovative biomedical diagnostics [1], [2] to security applications [3], [4] and civil engineering [5]
In the framework of quantitative microwave tomography, an interesting class is represented by nonlinear Newton-based approaches [28]–[30], which have been recently formulated in non-Hilbertian Lebesgue spaces with constant and nonconstant exponents [31]
The data-driven preprocessing network has been trained with time-domain numerical simulations involving cylindrical targets, where a simplified bistatic measurement configuration has been taken as a preliminary case study
Summary
T HE RECENT advances in microwave imaging are paving the way to many interesting scenarios, which range from innovative biomedical diagnostics [1], [2] to security applications [3], [4] and civil engineering [5]. The good performance of these methods has been proven in different case studies, with both single- and multifrequency data [32] This kind of tomographic Newton-based techniques have been formulated by considering excitations from infinite linecurrent sources and ideal observation domains [31], [33] or with rectangular waveguide models of the radiating and receiving antenna elements [34]. In the considered cases, this approach allows dealing with data collected in 3D cylindrical configurations with non-ideal probes, while retaining a canonical 2D formulation of the inverse problem This connection is intrinsically approximate, but leads to significant benefits in the quantitative reconstruction of unknown scatterers.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call