GIS分析与互信息属性约简的停车库选址决策

Site selection decision-making with GIS for mechanical parking system based on mutual information attribute reduction

为了使城区立体车库的选址更加合理,充分发挥其建成后对交通缓解的作用,提出了一种城区立体停车库选址决策方法.通过采用地理信息系统分析方法,建立基于地理信息系统分析的规划选址立体车库属性信息数据,运用模糊粗糙集互信息属性约简算法挖掘出立体车库的选址与多种地理因素的关系知识进行属性约简,从而用地理信息分析和演绎推理相结合的归纳学习算法生成决策树和决策规则进行选址决策的评价及分析.对兰州市规划中的立体停车库选址建模仿真,仿真结果表明该方法能较好地运用在待求解问题中,从而为智能交通系统提供参考依据.

In order to be more reasonable of site selection decision-making of mechanical parking system in urban, give full play to its alleviation of traffic after the completion of the action, a method of site selection decision is proposed. Firstly~ by using GIS （geographic information system） analysis method, the attribute information database sets of planning parking system are established. Secondly, applying fuzzy rough sets mutual information attribute reduction algorithm to mine the geography knowledge between parking system＇s location and a variety of geography factor using attribute reduction algorithms. Then, with decision tree and decision rules generated by geographic information analysis and deductive reasoning combination of inductive learning algorithm, location decision-making is evaluated and analyzed. Finally, a case study of Lanzhou is presented, and the results show that this method not only can do well in site selection decision of urban and so on, but also can provide a reference for intelligence transportation system.