| 基于自适应UKF的BP神经网络及其在高程拟合中的应用 |
| |
| 引用本文： | 聂建亮,秦勇,刘辉.基于自适应UKF的BP神经网络及其在高程拟合中的应用[J].测绘科学,2007,32(6):120-122. |
| |
| 作者姓名： | 聂建亮 秦勇 刘辉 |
| |
| 作者单位： | 长安大学地测学院,西安,710054;军事经济学院襄樊分院基础部,湖北襄樊,441118;河南省公路工程监理咨询有限公司,郑州,450052 |
| |
| 基金项目： | 信阳师范学院青年骨干教师资助计划，交通部科技项目(200531881203)，武汉大学地球空间环境与大地测量教育部重点实验室测绘基础研究基金(1469990324233-04-02) |
| |
| 摘 要： | 针对BP神经网络收敛速度慢、容易陷入局部极小值点和泛化能力差等问题,基于自适应Kalman滤波理论,提出一种自适应非线性滤波(UKF)训练BP神经网络的方法。该方法采用Kalman滤波框架,引入自适应因子,对神经网络的连接权进行训练,提高了神经网络的学习质量。高程异常拟合算例表明,基于自适应UKF的BP神经网络比标准BP神经网络收敛速度快,泛化能力强,从而证明了该方法是一种有效的连接权训练方法。
|
| 关 键 词： | BP神经网络 非线性滤波(UKF) UT变换 自适应因子 泛化能力 |
| 文章编号： | 1009-2307（2007）06-0120-03 |
| 修稿时间： | 2006-09-26 |
The application of BP neural network based on UKF height fitting |
| |
| NIE Jian-liang,QIN Yong,LIU Hui.The application of BP neural network based on UKF height fitting[J].Science of Surveying and Mapping,2007,32(6):120-122. |
| |
| Authors: | NIE Jian-liang QIN Yong LIU Hui |
| |
| Abstract: | BP neural network based on adaptive UKF is introduced in this paper for the standard BP neural network has slow converges,local minimum value and weak generalization ability.It can train weight of BP and improve the efficiency of BP without linearization by using the frame of Kalman filters and adaptive factor to adjust the variance of dynamic model.In the height fitting,BP based on UKF has quicker converges and stronger generalization ability than the standard BP.So it shows that BP neural network based on adaptive UKF is a kind of efficient neural network. |
| |
| Keywords: | BP neural network unscented Kalman filter unscented transformation adaptive factor generalization ability |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
