On the use of SVM for electromagnetic subsurface sensing

In this paper, a classification approach for the real-time identification of “occupation” areas (instead of the detection of each subsurface object) in sub-surface sensing applications is applied. A suitable SVM-based strategy is developed for determining the probability of occurrence of buried targets and to define a “risk map” of the investigation domain. To assess the effectiveness of the proposed approach and to evaluate its robustness, selected numerical results related to a two-dimensional geometry are presented.