Focal-Test-Based Spatial Decision Tree Learning: A Summary of Results
Focal-Test-Based Spatial Decision Tree Learning: A Summary of Results
复制标题
基于焦点测试的空间决策树学习：结果总结
DOI：
10.1109/icdm.2013.96
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
J. Corcoran
中科院分区：
文献类型：
--
作者：
Zhe Jiang;S. Shekhar;Xun Zhou;Joseph K. Knight;J. Corcoran
给定栅格空间框架以及训练集和测试集，空间决策树学习（SDTL）问题旨在最小化分类错误以及椒盐噪声。SDTL问题是重要的，由于许多社会应用，如遥感土地覆盖分类。然而，SDTL问题是具有挑战性的，由于类标签的空间自相关性，以及潜在的指数数量的候选树。由于使用了基于局部测试的决策节点，在测试阶段不能充分模拟空间自相关，导致高盐和胡椒噪声，相关工作受到限制。相比之下，我们提出了一种基于焦点测试的空间决策树（FTSDT）模型，其中位置的树遍历方向不仅基于局部，而且基于焦点（即，邻居）位置的属性。在真实的遥感数据集上的实验结果表明，该方法有效地抑制了椒盐噪声，提高了分类精度。
Given a raster spatial framework, as well as training and test sets, the spatial decision tree learning (SDTL) problem aims to minimize classification errors as well as salt-and-pepper noise. The SDTL problem is important due to many societal applications such as land cover classification in remote sensing. However, the SDTL problem is challenging due to the spatial autocorrelation of class labels, and the potentially exponential number of candidate trees. Related work is limited due to the use of local-test-based decision nodes, which can not adequately model spatial autocorrelation during test phase, leading to high salt-and-pepper noise. In contrast, we propose a focal-test-based spatial decision tree (FTSDT) model, where the tree traversal direction for a location is based on not only local but also focal (i.e., neighborhood) properties of the location. Experimental results on real world remote sensing datasets show that the proposed approach reduces salt-and-pepper noise and improves classification accuracy.