In this paper, a method for converting GPS height to normal one by means of support vector machine is proposed, and compared with the methods of neural network, polynomial fitting etc.
结合GPS测量和水准测量资料，利用支持向量机方法对GPS高程进行了转换，并与神经网络和多项式拟合等拟合的结果进行了比较，得出了一些有益的结论。
The paper discusses above problems by practice, and draws some conclusions about the network configuration of BP neural network applied in GPS height conversion.
本文结合实例分析了上述问题，从而得出了BP神经网络用于GPS高程转换时网络配置问题的一些相关结论。
Generally, under the case of enough amounts and evenly distributed of coincident points, the accuracy of GPS height fitting can meet the requirement of the fourth order leveling network.
一般在重合点数量充足且分布均匀的情况下，GPS高程拟合的精度可达到四等水准网的精度要求。
应用推荐