基于Rough集的居民地属性知识约简与结构化选取  

Attributes Reduction and Structured Selection in Automatic Cartographical Generalization Based on Rough Set

作　　者：宋鹰[1] 何宗宜[1] 粟卫民[1] 

机构地区：[1]武汉大学资源与环境科学学院

出　　处：《武汉大学学报（信息科学版）》2005年第4期329-332,共4页Geomatics and Information Science of Wuhan University

基　　金：国家基础测绘科技计划资助项目(1469990324231)。

摘　　要：基于Rough集理论提出了居民地属性知识约简及其结构化选取的方法。该方法充分利用 Rough集理论具有较强知识挖掘能力的特点,定量分析居民地选取中条件属性的重要性,简化属性知识,并以此为基础计算每个居民地的重要性,实现居民地的结构化选取。实例证明,该方法能够从数据库中挖掘出相关知识,具有较强的自适应能力。This paper presents a method for attributes reduction and structured selection of settlements in automatic cartographical generalization based on rough set. Rough set with strong ability to knowledge mining is applied to quantitatively analyze the importance of settlements attributes and attributes reduction. A case study is used to illustrate the method. The major conclusion of this study is that in the precondition without transcendental knowledge, attributes of settlements can be filtrated based on rough set so that conditional attribute sets can be optimized, and significance value of each attribute can be extracted.

关 键 词：ROUGH集 知识约简 自动综合 居民地 结构化选取 

分 类 号：P208[天文地球—地图制图学与地理信息工程] P283.1[天文地球—测绘科学与技术]