B-PNN改进算法在土地估价信息系统的应用  

Application of Improved B-P Neural Network to Urban Land Evaluation Information System

作　　者：陈郁[1] 谷蕾[1] 秦奋[1] 

机构地区：[1]河南大学环境与规划学院,河南开封475004

出　　处：《地理空间信息》2010年第3期36-39,共4页Geospatial Information

基　　金：科技部基础条件平台建设资助项目(2005DKA32300)

摘　　要：人工神经网络是解决主观因素影响过大和智能化程度不高这两个问题的合适方法。主要采用人工神经网络中的B-P神经网络建立土地估价智能模型,在ArcGIS的开发平台下,实现了基于B-P神经网络改进算法的人工神经网络土地估价模型。研究得出,利用人工神经网络可以解决土地估价过程中主观因素影响过多这一问题,可以提高城镇土地定级估价信息系统智能化程度。The current problems of the Urban Land Classification and Evaluation Information System（UL-CEIS） are specificity functional,large subjective factors,lower intelligent degree in China.Artificial Neural Network（ANN） is an appropriate way to resolve large subjective factors and lower intelligent degree.In this paper,the B-P Neural Network（B-PNN） was used to establish the intelligent model of Land Evaluation.In the ArcGIS development platform,programmed two improved B-PNNs and developed the model of ANN Land Evaluation based on the improved B-P algorithm.And the data used to validate the model was the productions of the land classification and evaluation of San-menxia city,China in 2003a.The results indicate that the ANN can solve the problem which is more infection of subjective factors in land evaluation,and it can improve the intelligent degree of the ULCEIS in a certain extent.

关 键 词：土地估价 土地定级 B-P神经网络改进 地理信息系统 

分 类 号：P237[天文地球—摄影测量与遥感]