基于密度聚类算法的校园人群聚集和移动规律分析  

Analysis of crowd aggregation and movement on campus based on density clustering algorithm

作　　者：郭玉彬[1] 吴宇航 周哲帆 李西明[1] Guo Yubin;Wu Yuhang;Zhou Zhefan;Li Ximing(College of Mathematics&Information,South China Agricultural University,Guangzhou 510642,China)

机构地区：[1]华南农业大学数学与信息学院,广州510642

出　　处：《计算机应用研究》2020年第3期688-692,698,共6页Application Research of Computers

基　　金：国家重点研发计划资助项目(2016YFD0800307,2016YFC0501801);国家科技支撑计划资助项目(2015BAD06B03-3)。

摘　　要：针对某高校无线网日志数据进行挖掘分析,获取校园人群聚集点分布和人群移动规律。首先利用分布式统计算法统计校园内各建筑物的无线网络连接人次;然后建立校园建筑物的中心点经纬坐标的R树索引,并对R树叶子节点分组,以此将校园分成几个部分;再利用密度聚类算法对校园每一个部分中的建筑物中心点经纬坐标进行聚类得到校园区域划分;最后结合聚类结果和统计结果获取人群聚集区域和区域之间人群移动规律。研究结果可为学校校车路径规划、共享单车部署和校园功能区规划等工作提供参考。This paper analyzed the wireless network log data of a university to study the law of crowd aggregation and movement on campus.Firstly,the number of wireless network connections of each building on campus was obtained by distributed statistical algorithms.Secondly,it established the R-tree index of building central latitude-longitude coordinates,and grouped the R-tree leaf nodes to divide the campus into parts.Thirdly,it clustered the building central latitude-longitude coordinates of each part to get the campus area division by the density clustering algorithm.Finally,this paper got the law of crowd aggregation area and movement between areas from clustering results and statistical results.Result of this paper can be used as refe-rence for school bus route planning,shared bicycle deployment and campus function area planning.

关 键 词：无线网络 日志数据 R树 密度聚类 人群聚集和移动 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]