A Classification Approach Based on SVM for
A Classification Approach Based on SVM for
复制标题
DOI：
--
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
A. Massa;A. Boni;M. Donelli
中科院分区：
文献类型：
--
作者：
A. Massa;A. Boni;M. Donelli
在清理受地雷和/或未爆炸弹药 (UXO) 污染或可能污染的地形时，通常需要进行快速的大范围监视。然而，对于某些场景/应用来说，识别危险区域（而不是检测每个地下物体）就足够了，从而以节省成本的方式提供适当的安全级别。在这样的框架中，本文描述了一种定义风险图的概率方法。从散射电磁场的测量开始，通过基于支持向量机的适当定义的分类器来确定所研究的地下区域中危险目标出现的概率。为了评估所提出方法的有效性并评估其鲁棒性，提出了与二维几何相关的选定数值结果。
In clearing terrains contaminated or potentially con- taminated by landmines and/or unexploded ordnances (UXOs), a quick wide-area surveillance is often required. Nevertheless, the identification of dangerous areas (instead of the detection of each subsurface object) can be enough for some scenarios/applications, allowing a suitable level of security in a cost-saving way. In such a framework, this paper describes a probabilistic approach for the definition of risk maps. Starting from the measurement of the scat- tered electromagnetic field, the probability of occurrence of dan- gerous targets in an investigated subsurface area is determined through a suitably defined classifier based on a support vector ma- chine. To assess the effectiveness of the proposed approach and to evaluate its robustness, selected numerical results related to a two-dimensional geometry are presented.