eprintid: 364
rev_number: 5
eprint_status: archive
userid: 5
dir: disk0/00/00/03/64
datestamp: 2011-07-26
lastmod: 2013-06-28 12:14:58
status_changed: 2013-06-28 12:14:58
type: techreport
metadata_visibility: show
item_issues_count: 0
creators_name: Donelli, Massimo
creators_name: Benedetti, Manuel
creators_name: Rocca, Paolo
creators_name: Melgani, Farid
creators_name: Massa, Andrea
title: Three Dimensional Electromagnetic Sub-Surface Sensing by Means of a Multi-Step SVM-Based Classification Technique
ispublished: pub
subjects: TU
full_text_status: public
abstract: In this paper, the classification approach is extended from 2D to the three-dimensional(3D) case carefully addressing the increased complexity issue by means of an effective multi-step strategy. As a matter of fact, by iteratively processing the training dataset (without requiring an extra amount of measurements), the proposed method is aimed at improving the spatial resolution of the original classification technique [6] even though dealing with a more complex problem. The effectiveness of the proposed approach has been preliminary assessed through a set of numerical experiments also in correspondence with blurred data and some representative results are shown in the following. This is the author's version of the final version available at IEEE.
date: 2011-01
date_type: published
institution: University of Trento
department: informaticat
refereed: FALSE
referencetext: [1] IEEE Trans. Geosci. Remote Sens., Special Issue on: “New Advances in Subsurface Sensing: Systems, Modeling and Signal Processing,” vol. 39, Jun. 2001. [2] A. Massa et al., “An innovative real-time technique for buried object detection,” IEEE Trans. Geosci. Remote Sens., vol. 41, , pp. 927-931, Apr. 2003. [3] A. Massa et al., “A comparative study of NN and SVM-based electromagnetic inverse scattering approaches for on-line detection of buried objects,” ACES Journal, vol. 18, pp. 1-11, Jul. 2003. [4] I. Rekanos, “Neural-network-based inverse-scattering technique for online microwave medical imaging,” IEEE Trans. Magnetics, vol. 38, pp. 1061-1064, Mar. 2002. [5] A. Massa et al., “Learning-by-examples strategies for sub-surface imaging: from regression to classification approach,” PIERS2003 in Hawaii, p. 118, Oct. 2003. [6] M. Donelli et al. “A classification approach based on SVM for electromagnetic sub- surface sensing,” IEEE Trans. Geosci. Remote Sens., vol. 43, pp. 2084-2093, Sep. 2005. [7] V. Vapnik, Statistical Learning Theory. New York: Wiley, 1998.
citation:   Donelli, Massimo and Benedetti, Manuel and Rocca, Paolo and Melgani, Farid and Massa, Andrea  (2011) Three Dimensional Electromagnetic Sub-Surface Sensing by Means of a Multi-Step SVM-Based Classification Technique.  [Technical Report]     
document_url: http://www.eledia.org/students-reports/364/1/DISI-11-229.C136.pdf