超声波技术处理含油污泥研究进展 |
| |
引用本文: | 张磊,仝坤,王星晖,王童,王恩旭. 超声波技术处理含油污泥研究进展[J]. 城市勘测, 2015, 25(6): 73-76. DOI: 10.3969/j.issn.1672-8262.2015.06.023 |
| |
作者姓名: | 张磊 仝坤 王星晖 王童 王恩旭 |
| |
作者单位: | 1. 北京航天泰坦科技股份有限公司,北京,100067;2. 武汉大学遥感信息工程学院,湖北武汉,430079 |
| |
基金项目: | 北京市科技新星计划,国家国际合作专项国家耕地资源动态监管核心技术引进与合作研究项目 |
| |
摘 要: | 以Indian Pine数据集为研究对象,利用等角特征映射对其进行特征提取,然后选取BP网络传统的梯度下降训练方法和正切拟牛顿法、Polak-Ribiere共轭梯度法、Levenberg-Marquart法3种数值优化的训练方法对其进行分类. 对分类结果进行对比分析,结果表明:基于数值分析的训练方法训练网络的耗时均比梯度下降法长,但收敛效果更好;总体分类精度均比梯度下降法至少提高6%;各类别制图精度都较高,且较为稳定,而梯度下降法只对易分的类别精度高;3种数值分析训练方法中,正切拟牛顿法和Polak-Ribiere共轭梯度法的收敛效率和分类精度比 Levenberg-Marquart法高.
|
关 键 词: | BP网络 训练 数值优化 高光谱影像 分类 |
Comparative Analysis of Several Training Methods of BP Network on Hyperspectral Image Classification |
| |
Abstract: | This paper study on hyperspectral image classification using BP network trained by numerical analysis methods such as OSS,CGP,LM and traditional gradient descent methods ,which based on Indian Pine dataset taking fea-ture extraction using isogonism characteristic mapping methods .Comparing the classification results ,it shows:the classifi-cation result using numerical analysis methods is better than GD methods .Firstly,the training time using numerical anal-ysis methods is longer than GD ,but the convergence effect is better .And then ,the total accuracy improves 6%at least a-gainst GD.In the end,the mapping accuracy of each category is better and more stable than GD ,which is only sensitive on easily classified category .At last ,Comparing the three numerical analysis methods ,the OSS method and CGP method is better than LM method . |
| |
Keywords: | BP Network training numerical analysis hyperspectral image classification |
本文献已被 万方数据 等数据库收录! |
| 点击此处可从《城市勘测》浏览原始摘要信息 |
|
点击此处可从《城市勘测》下载全文 |
|