首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于贝叶斯正则化BP神经网络的DEM趋势面逼近
引用本文:陈再辉,江丽钧,朱晓燕,江伟勇.基于贝叶斯正则化BP神经网络的DEM趋势面逼近[J].海洋测绘,2009,29(4):32-34.
作者姓名:陈再辉  江丽钧  朱晓燕  江伟勇
作者单位:丽水市建设局城建测量队,浙江,丽水,323000
摘    要:趋势面从宏观上揭示了研究对象的特性,在各领域发挥着重要作用。BP神经网络可以对复杂系统进行无限逼近,进而进行预测。建立了基于贝叶斯正则化BP神经网络的数字高程模型趋势面,与二次多项式建立的数字高程模型趋势面进行比较分析,证明了该方法的可行性和有效性。

关 键 词:贝叶斯正则化  BP神经网络  数字高程模型  趋势面

Bayesian Regularization BP Neutral Network for the Construction of DEM Trend
CHEN Zai-hui,JIANG Li-jun,ZHU Xiao-yan,JIANG Wei-yong.Bayesian Regularization BP Neutral Network for the Construction of DEM Trend[J].Hydrographic Surveying and Charting,2009,29(4):32-34.
Authors:CHEN Zai-hui  JIANG Li-jun  ZHU Xiao-yan  JIANG Wei-yong
Institution:( Surveying Union of City Construction, Bureau of Construction in Lishui, Lishui, Zhejiang, 323000)
Abstract:Trend can open out the characteristic of research object, and exert important effect in many domains. BP neutral network can approach complex system adinfinitum, and process forecast. In this paper, DEM trend based on Bayesian Regularization BP neutral network is constructed. Compared with DEM trend using quadratic polynomial , the feasibility and validity are proved.
Keywords:Bayesian regularization  BP neutral network(BPNN)  digital elevation model(DEM)  trend
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《海洋测绘》浏览原始摘要信息
点击此处可从《海洋测绘》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号