Semi-Supervised Support Vector Biophysical Parameter Estimation
IGARSS (3)(2008)
摘要
ABSTRACT Two kernel-based methods for semi-supervised regression are presented. The methods,rely on building a graph or hyper- graph Laplacian with both the labeled and unlabeled data, which,is further used to deform the training kernel matrix. The deformed,kernel is then used for support vector regres- sion (SVR). The semi-supervised SVR methods,are sucess- fully tested in LAI estimation and ocean chlorophyll concen- tration prediction from remotely sensed images.
更多查看译文
关键词
oceanography,image processing,neural networks,regression analysis,support vector,spatial resolution,parameter estimation,estimation,artificial neural networks,remote monitoring,support vector regression,graph laplacian,vegetation,kernel,testing,remote sensing,support vector machines
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络