An assessment of support vector machines for land cover classi(cid:142) cation
An assessment of support vector machines for land cover classi(cid:142) cation
复制标题
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
Chengquan Huang;L. Davis;J. Townshend
中科院分区：
文献类型：
--
作者：
Chengquan Huang;L. Davis;J. Townshend
.支持向量机（SVM）是一组理论上优越的机器学习算法。它被发现与最好的机器学习算法在分类高维数据集的竞争。本文介绍了支持向量机的理论发展，并对支持向量机在遥感影像土地覆盖分类中的精度、稳定性和训练速度进行了实验评价。将SVM与其他三种流行的分类器进行了比较，包括最大似然分类器（MLC）、神经网络分类器（NNC）和决策树分类器（DTC）。实验中还考察了核函数配置对SVM性能的影响以及训练数据和输入变量的选择对四种分类器性能的影响。
. The support vector machine (SVM) is a group of theoreticallysuperior machine learning algorithms. It was found competitive with the best available machine learning algorithms in classifying high-dimensionaldata sets. This paper gives an introduction to the theoretical development of the SVM and an experimental evaluation of its accuracy, stability and training speed in deriving land cover classi(cid:142) cations from satellite images. The SVM was compared to three other popular classi(cid:142) ers, including the maximum likelihood classi(cid:142) er (MLC), neural network classi(cid:142) ers (NNC) and decision tree classi(cid:142) ers (DTC). The impacts of kernel con(cid:142)guration on the performance of the SVM and of the selection of training data and input variables on the four classi(cid:142) ers were also evaluated in this experiment.