| BP神经网络遥感水深反演算法的改进 |
| |
| 引用本文： | 曹斌,邱振戈,朱述龙,曹彬才.BP神经网络遥感水深反演算法的改进[J].测绘通报,2017,0(2):40-44. |
| |
| 作者姓名： | 曹斌 邱振戈 朱述龙 曹彬才 |
| |
| 作者单位： | 1. 上海海洋大学海洋科学学院, 上海 201306;
2. 信息工程大学, 河南 郑州 450001 |
| |
| 摘 要： | 针对BP神经网络遥感水深反演算法（简称传统BP算法）的缺点，提出了改进型BP神经网络遥感水深反演算法（简称改进型BP算法），其基本原理是在模型训练过程中反复运用粒子群算法对BP神经网络的权值和阈值进行优化以弥补传统BP算法的不足。试验表明：改进型BP算法的训练迭代收敛速度明显快于传统BP算法，浅水区的水深反演精度优于传统BP算法，且学习算法对初始权值和阈值不敏感。
|
| 关 键 词： | 遥感水深反演 传统BP算法 粒子群算法 改进型BP算法 权值和阈值优化 |
| 收稿时间： | 2016-06-11 |
| 修稿时间： | 2016-09-11 |
Improvement of BPANN Based Algorithm for Estimating Water Depth from Satellite Imagery |
| |
| CAO Bin,QIU Zhenge,ZHU Shulong,CAO Bincai.Improvement of BPANN Based Algorithm for Estimating Water Depth from Satellite Imagery[J].Bulletin of Surveying and Mapping,2017,0(2):40-44. |
| |
| Authors: | CAO Bin QIU Zhenge ZHU Shulong CAO Bincai |
| |
| Institution: | 1. College of Marine Sciences, Shanghai Ocean University, Shanghai 201306, China;
2. Information Engineering University, Zhengzhou 450001, China |
| |
| Abstract: | BPANN algorithm is commonly used for estimating water depth from satellite imagery. In this paper, an improved BPANN algorithm is presented to overcome some disadvantages of BPANN algorithm. Its principle is that particle swarm optimization (PSO) is used to optimize the weights and thresholds of ANN in the process of training. The experiments show that improved BPANN algorithm has faster convergence speed and better generalization ability, it is not sensitive to initial weights and thresholds, and it can make more accurate results than BPANN algorithm. |
| |
| Keywords: | estimating water depth from satellite imagery backpropagation-based artificial neural network algorithm ( BPANN algorithm) particle swarm optimization (PSO) improved BPANN algorithm optimization of initial weights and thresholds |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《测绘通报》浏览原始摘要信息 |
| 点击此处可从《测绘通报》下载免费的PDF全文 |
