eprintid: 715
rev_number: 12
eprint_status: archive
userid: 4
dir: disk0/00/00/07/15
datestamp: 2016-12-30 09:18:47
lastmod: 2024-11-07 16:50:42
status_changed: 2016-12-30 09:18:47
type: monograph
metadata_visibility: show
creators_name: Salucci, M.
creators_name: Anselmi, N.
creators_name: Oliveri, G.
creators_name: Massa, A.
title: An Adaptive Learning-by-Examples Methodology for Accurate Crack Characterization in NDT-NDE Problems
ispublished: pub
subjects: MLBE
full_text_status: public
monograph_type: technical_report
keywords: Eddy current testing, inverse scattering, nondestructive testing and evaluation, statistical learning, learning-by-examples, support vector regression, output space filling, partial least squares, adaptive sampling
abstract: This document presents an adaptive learning-by-examples (LBE) inversion strategy for the accurate and real-time characterization of a defect within a planar conductive structure. More precisely, the developed technique exploits a Partial Least Squares (PLS) linear feature extraction strategy in order to compress the relevant information about the underlying relationship between defect and measurements into a small set of predictive features. Successively, an innovative adaptive sampling strategy is exploited in order to collect a set of N input-output (I/O) training pairs such that an even exploration of the PLS-extracted feature space is obtained.  Such a training database is then used to train a Support Vector Regressor (SVR) for building an accurate and robust estimator of the crack dimensions starting from ECT measurements. Some numerical results are shown in order to validate the proposed approach also when a non-negligible amount of noise is superimposed on testing data.
date: 2016
publisher: University of Trento
referencetext: [1] M. Salucci, N. Anselmi, G. Oliveri, P. Calmon, R. Miorelli, C. Reboud, and A. Massa, "Real-time NDT-NDE through an innovative adaptive partial least squares SVR inversion approach," IEEE Trans. Geosci. Remote Sens., vol. 54, no. 11, pp. 6818-6832, Nov. 2016. 
[2] M. Salucci, G. Oliveri, F. Viani, R. Miorelli, C. Reboud, P. Calmon, and A. Massa, "A learning-by-examples approach for non-destructive localization and characterization of defects through eddy current testing measurements," in 2015 IEEE International Symposium on Antennas and Propagation, Vancouver, 2015, pp. 900-901.
[3] M. Salucci, S. Ahmed and A. Massa, "An adaptive Learning-by-Examples strategy for efficient Eddy Current Testing of conductive structures," in 2016 European Conference on Antennas and Propagation, Davos, 2016, pp. 1-4.
[4] P. Rocca, M. Benedetti, M. Donelli, D. Franceschini, and A. Massa, "Evolutionary optimization as applied to inverse problems," Inverse Probl., vol. 25, pp. 1-41, Dec. 2009.
[5] A. Massa, P. Rocca, and G. Oliveri, "Compressive sensing in electromagnetics - A review," IEEE Antennas Propag. Mag., pp. 224-238, vol. 57, no. 1, Feb. 2015.
[6] N. Anselmi, G. Oliveri, M. Salucci, and A. Massa, "Wavelet-based compressive imaging of sparse targets," IEEE Trans. Antennas Propag., vol. 63, no. 11, pp. 4889-4900, Nov. 2015. 
[7] M. Salucci, G. Oliveri, and A. Massa, "GPR prospecting through an inverse-scattering frequency-hopping multifocusing approach," IEEE Trans. Geosci. Remote Sens., vol. 53, no. 12, pp. 6573-6592, Dec. 2015.
[8] T. Moriyama, G. Oliveri, M. Salucci, and T. Takenaka, "A multi-scaling forward-backward time-stepping method for microwave imaging," IEICE Electron. Express, vol. 11, no. 16, pp. 1-12, Aug. 2014.
[9] T. Moriyama, M. Salucci, M. Tanaka, and T. Takenaka, "Image reconstruction from total electric field data with no information on the incident field," J. Electromagnet. Wave., vol. 30, no. 9, pp. 1162-1170, 2016. 
[10] M. Salucci, L. Poli, and A. Massa, "Advanced multi-frequency GPR data processing for non-linear deterministic imaging," Signal Processing - Special Issue on "Advanced Ground-Penetrating Radar Signal-Processing Techniques," vol. 132, pp. 306-318, Mar. 2017.
citation:   Salucci, M. and Anselmi, N. and Oliveri, G. and Massa, A.  (2016) An Adaptive Learning-by-Examples Methodology for Accurate Crack Characterization in NDT-NDE Problems.  Technical Report. University of Trento.     
document_url: http://www.eledia.org/students-reports/715/1/An_Adaptive_Learning-by-Examples_Methodology_for_Accurate_Crack_Characterization_in_NDT-NDE_Problems.v2.pdf