基于手机大数据的城市功能区识别方法  

Urban Functional Area Identification Method Based on Mobile Big Data

作　　者：肖迪 张小咏 胡杨 Xiao Di;Zhang Xiaoyong;Hu Yang(Beijing Information Science&Technology University,School of Information and Telecommunication Engineering,Beijing 100101,China;Beijing Key Laboratory of High Dynamic Navigation Technology,University of Beijing Information Science&Technology,Beijing 100101,China)

机构地区：[1]北京信息科技大学信息与通信工程学院,北京100101 [2]北京信息科技大学高动态导航技术北京市重点实验室,北京100101

出　　处：《系统仿真学报》2019年第11期2281-2288,共8页Journal of System Simulation

基　　金：北京市自然基金(9182004);北京信息科技大学“勤信人才”培育计划(QXTCPB201903)

摘　　要：随着城市化进程的迅猛发展,城市土地功能不断发生演变,实时、准确地识别城市功能区具有重要意义。智能手机普及和互联网快速发展促使手机成为人类活动的传感器。提出了一种基于时序手机数据挖掘与兴趣点(point of interest, POI)语义分析的城市功能区识别方法,该方法面向街区尺度提取剩余手机定位量时序特征,以此特征构建模糊C均值聚类算法,结合区域内各类兴趣点的密度分布,分析并解释了聚类结果的土地功能语义。实验结果表明,该方法基本实现了城市功能区的识别。With the rapid development of urbanization, the function of urban land is constantly evolving. It is of great significance to identify urban functional areas in real time and accurately. In recent years, accompanied by the popularity of smart phones and the rapid development of the Internet, mobile phones have become sensors of human activities. In this paper, a method of urban functional area identification based on time series mobile phone data mining and POI semantics analysis is proposed. The time series feature of remaining mobile phone positioning is extracted facing block scale. And a FCM clustering algorithm based on this feature is constructed. Combining the point density distribution of POI in different regions, the functional attributes of clustering results are analyzed and explained. The experimental results show that the method basically realizes the identification of urban functional area.

关 键 词：手机大数据 功能区识别 兴趣点 剩余手机定位量 FCM聚类算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]