Three Dimensional Electromagnetic Sub-Surface Sensing by Means of a Multi-Step SVM-Based Classification Technique

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]

[img]
Preview
PDF
DISI-11-229.C136.pdf

Download (221kB) | Preview

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.

Item Type: Technical Report
Subjects: Uncategorized > TU Technical Reports and Publications
URI: http://www.eledia.org/students-reports/id/eprint/364

Actions (login required)

View Item View Item