摘要
本文论述了正交多项式和基于BP人工神经网络的GPS高程异常拟合原理,分析了这几种算法的优缺点。并结合实例计算,比较分析各方法的精度。最后得出改进的BP神经网络的方法精度要优于多项式拟合和标准BP算法。
The principle of quadric polynomail and artificial neural network for conversion of GPS height is discussed ,and their anvantages and disadvantages is presented .The pro-gram was done by Matlab software ,calculated with specific example .The accuracy was ana-lyzed and compared with different methods .At last the conclusion shows that the improved BP neural network is better than the standard BP neural network and quadric polynomail .
出处
《全球定位系统》
2014年第1期68-71,共4页
Gnss World of China
关键词
GPS高程异常
正交多项式
BP神经网络
Matlab
GPS height abmormal
quadric polynomial
BP neural network
Matlab