Analysis of Human Spatio-Temporal Behaviour

Analysis of Human Spatio-Temporal Behaviour

City organization and residents behavior is one of the key research in urban geography. With the rapid development of information technology, the impact of research on residents spatial and temporal behavior on urban spatial organization and structure shows a growing trend, therefore in-depth analysis of the spatio-temporal behavior of city space and urban residents have high research value. Our researchers have put great efforts in understanding the spatio-temporal behavior of urban residents through the analysis of data from urban mobile networks, campus WiFi networks and satellite position system (i.e., Beidou).

The spatio-temporal behavior patterns of people living within a city are crucial to many applications ranging from personalized location based services to city management. Facilitating data from urban mobile network and campus WiFi network, we provide an objective, large-scale measurement framework incorporating multiple-layer behaviors: network, application and user behaviors. Comprehension of the changeability helps to optimize existing mobility models in network researches accompanied by a reinforced interpretation of human behavior, and additionally paves a new way to estimate abnormal mobilities which gives assistance to, say, stolen devices’ retrieval or school security management. With the GPS data from Beidou system, we focus on three aspects: user’s semantic trajectory extraction, fine-grained user profile and spatial-temporal anomaly detection.


自2013年以来,OMNILab的研究人员通过分析隐私处理后的杭州移动数据、校园WiFi数据、北斗位置数据对用户时空行为分析进行了深入的研 究。对于杭州移动数据的研究集中于用户移动性及网络流量特性,挖掘并理解城市范围内用户的时空行为特征将会助力与包括从基于位置的个性化推荐到城市规划的 各个应用领域。校园WiFi数据挖掘主要用于研究用户轨迹模型变化,将离散的用户时空行为抽象描述成时空序列数据,并结合地点、应用语义添加相应标签,提 取用户的轨迹模型。在实际应用中,轨迹模式变化的检测,不仅有助于对已有的网络设施部署进行调整和优化,也能够透过用户的行为信息,检测出特定时空域的群 体事件,为安全管理提供方便的途径。北斗数据分析研究主要集中于:用户语义轨迹的提取、细粒度用户分类、时空行为异常检测。用户时空行为分析是我们的长期 研究领域,希望能和更多的合作伙伴共享我们的技术,将研究成果用于实际当中。

Person/Organization: Siwei Qiang, Wenjuan Gong, Xiaming Chen, Haiyang Wang

  • Hangzhou mobile network dataset analysis
  • Campus WiFi networks data mining
  • BeiDou location data Mining project


  • Urban Spatio-temporal Behavior Analysis Based on Mobile Network Traffic Logs, CCF Big Data 2014 (recommended to Journal of Computer Research and Development).
  • Gong, Wenjuan; Chen, Xiaming; Qiang, Siwei; Jin, Yaohui; Trajectory pattern change analysis in campus WiFi networks, Proceedings of the Second ACM SIGSPATIAL International Workshop on Mobile Geographic Information Systems,1-8,2013,ACM.