基于最小二乘支持向量机回归的GPS高程转换模型

GPS elevation transform model based on least squares support vector regression

探讨了将最小二乘估计引入到支持向量机中,给出最小二乘支持向量机回归(LS-SVR)算法,该算法用等式约束代替传统支持向量机回归中的不等式约束,使得求解过程更为简单。将构建的LS-SVR模型应用到GPS高程转换中,提出该回归模型的实现步骤。实例表明,在有限样本情况下,LS-SVR完全可以达到与传统GPS高程拟合方法相同的精度,但实现起来更简单,而且在泛化性能方面具有理论上的保证。

This paper introduces least squares estimation into SVM and deduces least squares support vector regression （LS-SVR） algorithm, which applies equality constraint instead of inequality constraint of SVM and makes it easier to obtain ,solutions. Then LS-SVR model is applied into GPS elevation transform and its imple- menting process is designed. Finally, a sample is given to testify that LS-SVR can acquire the same precision as traditional fitting methods in GPS elevation transform , which is simpler and with theoretical foundation in extension property.