| 基于最小二乘配置法的BP神经网络GPS高呈异常拟合方法研究 |
| |
| 引用本文： | 沈雪峰,高成发,潘树国. 基于最小二乘配置法的BP神经网络GPS高呈异常拟合方法研究[J]. 测绘工程, 2011, 20(4): 14-17,21 |
| |
| 作者姓名： | 沈雪峰 高成发 潘树国 |
| |
| 作者单位： | 1. 东南大学交通学院,江苏南京,210096
2. 东南大学仪器科学与工程学院,江苏南京,210096 |
| |
| 基金项目： | “十一五”国家科技支撑计划重点资助项目(2008BAJ11B05) |
| |
| 摘 要： | 传统的BP神经网络在GPS高程异常拟合应用有其一定的局限性,特别是在对于外推高程异常值方面,传统的BP神经网络的不足表现得尤为明显.针对高程异常的特性,既有趋势性也有随机性,结合BP神经网络的优点,提出一种改进型的BP神经网络高程异常拟合方法,利用最小二乘配置法综合考虑高程异常的趋势性和随机性的特点,采用BP神经网络方...
|
| 关 键 词： | GPS 高程异常 BP神经网络 最小二乘配置法 |
Research on GPS elevation abnormal fitting based on least squares collocation method and BP neural network |
| |
| SHEN Xue-feng,GAO Cheng-fa,PAN Shu-guo. Research on GPS elevation abnormal fitting based on least squares collocation method and BP neural network[J]. Engineering of Surveying and Mapping, 2011, 20(4): 14-17,21 |
| |
| Authors: | SHEN Xue-feng GAO Cheng-fa PAN Shu-guo |
| |
| Affiliation: | SHEN Xue-feng1,GAO Cheng-fa1,PAN Shu-guo2(1.Transportation College,Southeast University,Nanjing 210096,China,2.Department of Instrument Science and Engineering,China) |
| |
| Abstract: | Traditional BP neural network has its limitations in the application of fitting GPS height anomaly.Especially in regard to extrapolate the value of height anomaly,the lack of traditional BP neural network has been particularly evident.Because of the characteristics of height anomaly,which has tendency and randomicity,combined with the advantages of BP neural network,an improved BP neural network height anomaly fitting method is presented in this paper.Least squares collocation method for comprehensive consi... |
| |
| Keywords: | GPS height anomaly BP neural network least squares collocation method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
