| 用于成像光谱数据特征矿物识别的人工神经网络结构研究 |
| |
| 引用本文： | 何勇强,姚国清.用于成像光谱数据特征矿物识别的人工神经网络结构研究[J].国土资源遥感,2004,15(3):23-27. |
| |
| 作者姓名： | 何勇强 姚国清 |
| |
| 作者单位： | 中国地质大学信息工程学院,北京,100083 |
| |
| 摘 要： | 当某一问题很难甚至无法用数学方法建立精确模型时,人工神经网络的方法则显示了优势。对于一个具体问题,采用何种网络结构是至关重要的。本文以美国内华达州Cuprite矿区成像光谱数据特征矿物识别为例,采用6种不同结构的多层前馈网络模型,从其训练难度、运算效率及识别效果等方面进行了综合对比分析。
|
| 关 键 词： | 人工神经网络 多层前馈网络 成像光谱 模式识别 |
| 文章编号： | 1001-070X(2004)03-0023-05 |
| 收稿时间： | 2004-03-08 |
| 修稿时间： | 2004年3月8日 |
THE STRUCTURES OF ARTIFICIAL NEURAL NETWORKS USED FOR IMAGING SPECTRAL DATA PATTERN RECOGNITION |
| |
| HE Yong-qiang,YAO Guo-qing.THE STRUCTURES OF ARTIFICIAL NEURAL NETWORKS USED FOR IMAGING SPECTRAL DATA PATTERN RECOGNITION[J].Remote Sensing for Land & Resources,2004,15(3):23-27. |
| |
| Authors: | HE Yong-qiang YAO Guo-qing |
| |
| Institution: | School of Information Engineering, China University of Geosciences, Beijing 100083, China |
| |
| Abstract: | When it is difficult or even impossible to construct a precise model for solving a problem, the artificial neural networks (ANN) will show its advantage. The selection of the structure of ANN to deal with a specific problem is important. In this paper, six kinds of multilayer feedforward neural networks models were used for imaging spectral data pattern recognition of characteristic minerals, and their learning difficulties, operation efficiencies and recognition effects were studied synthetically. |
| |
| Keywords: | Artificial neural networks Multilayer feedforward neural networks Imaging spectral Pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《国土资源遥感》浏览原始摘要信息 |
| 点击此处可从《国土资源遥感》下载免费的PDF全文 |
