基于地铁刷卡数据的城市居民行为模式变化分析  

Analysis on the Activity Pattem Change of Residents Based on Their Metro Card Swiping Data

作　　者：吴文昊 沈枭麒 WU Wenhao;SHEN Xiaoqi(School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China;School of Environment Science and Spatial Informatics,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079 [2]中国矿业大学环境与测绘学院,江苏徐州221116

出　　处：《测绘地理信息》2022年第4期105-109,共5页Journal of Geomatics

基　　金：国家重点研发计划(2017YFB0503604)

摘　　要：目前主流的时空数据分析方法侧重于研究行为的空间特征,将居民行为抽象地看作发生于一个时间点上。然而,这种对行为的抽象和简化忽略了行为的持续性。为了发掘行为模式中丰富的时间信息,以深圳地铁刷卡数据为例,构建时间兴趣区域对居民行为的起止时间和持续时长进行表达,基于CLIQUE算法对居民行为模式进行挖掘,最后对挖掘出的显著模式进行变化分析。实验表明,该刷卡数据集中含有4种显著行为模式,每种模式都具有特定的变化规律,为居民行为模式挖掘与研究提供了一种新思路。Currently the mainstream spatio-temporal data analysis methods focus on the spatial characteristics of activity,and the residents’activities are regarded as an abstract occurrence at a time point.However,this kind of abstraction and simplification ignore the persistence of activities.In order to explore more abundant time information in the pattern of activities,this paper takes card swiping data of Shenzhen Metro as an example,constructs the temporal area of interest to express the start time,end time and duration of residents’activity,then mines the pattern of residents’activity based on CLIQUE algorithm,and finally analyzes the changes of the typical pattern.Experiments show that there are four typical activity patterns in the data set,each of which has a specific change rule.

关 键 词：时空数据分析 地铁刷卡数据 时间兴趣区域 CLIQUE算法 居民行为模式挖掘 

分 类 号：P208[天文地球—地图制图学与地理信息工程] TU984[天文地球—测绘科学与技术]