采用决策树算法进行居民地自动综合  

Auto Generalization of Settlement by Using Decision Tree Algorithm

作　　者：何海威[1] 钱海忠[1] 刘闯[1] 谢丽敏[1] HE Haiwei QIAN Haizhong LIU Chuang XIE Limin(Information Engineering University, Zhengzhou 450001, China)

机构地区：[1]信息工程大学,河南郑州450001

出　　处：《测绘科学技术学报》2016年第6期623-628,共6页Journal of Geomatics Science and Technology

基　　金：国家自然科学基金项目(41171305;41571442)

摘　　要：借鉴人工智能领域中的机器学习研究成果,提出一种采用决策树算法进行居民地智能选取的新方法。将制图专家对居民地综合的结果作为参照,对其进行结构化描述并构建和转化为案例库;采用决策树算法对案例库中的案例进行分类,把制图综合问题转化为分类问题,从案例库中归纳出if-then规则,进而指导同类居民地的自动综合。试验验证,算法能够较好地还原专家的选取规律,在同类型的居民地自动综合试验中取得了良好的效果。A new method of intelligent decision-making based on decision tree algorithm is proposed in this paper, which is based on the research of machine learning in the field of artificial intelligence. The generalization results of the experts are taken as reference cases in this method. The decision tree algorithm is used to classify the cases in the case base, and then the cartographic generalization problem is transformed into the classification problem. The if-then rule is derived from the case base, which is used to guide the automatic generalization of the same kind of settlement features. The result of the experiment shows that this method can restore the selection rule of experts and gain the better efficiency in the same type of settlement feature automatic generalization test.

关 键 词：居民地 自动制图综合 决策树 案例推理 规则推理 

分 类 号：P208[天文地球—地图制图学与地理信息工程]