登录 | 注册 | 充值 | 退出 | 公司首页 | 繁体中文 | 满意度调查
综合馆
基于客流数据的区域出行特征聚类
  • 摘要

    区域功能发现对完善城市规划有着重要的指导意义.区域居民的出行特征提取与发掘可以作为建立模型分析区域功能的数据支撑.随着智能交通技术在轨道交通系统的应用,大量蕴含行人移动性和出行目的地信息的客流数据被采集得到,发现客流数据与地铁站相关区域功能有紧密联系.从地铁客流数据中提取出乘客出行模式和地铁站客流模式,并以此为基础建立概率图模型,实现了区域出行特征聚类.首先,以地铁客流数据为基础提取了乘客出行模式和地铁站客流模式,发现地铁站客流集中性和潮汐性的特性,能在一定程度上反映地铁的区域功能.然后,采用了文本分析领域经典的概率图模型,建立基于潜在狄利克雷分配(latent Dirichlet allocation,LDA)主题模型的地铁客流出行特征聚类模型,将具有出行规律相似性的地铁站聚类在一起.最后,通过分析聚类实验结果,发现在不同客流峰段内的区域功能和相互客流关系.

  • 作者

    冷彪  赵文远  Leng Biao  Zhao Wenyuan 

  • 作者单位

    北京航空航天大学计算机学院 北京 100191

  • 刊期

    2014年12期 ISTIC EI PKU

  • 关键词

    出行特征聚类  人类移动性  概率图模型  地铁客流  数据挖掘  ridership characteristic clustering  human mobility  probabilistic graphical model  metro passenger flow  data mining 

参考文献
  • [1] Biao LENG,Jiabei ZENG,Zhang XIONG,Weifeng LV,Yueliang WAN. Probability tree based passenger flow prediction and its application to the Beijing subway system. 中国计算机科学前沿, 2013,2
  • [2] Xiaolong LI,Gang PAN,Zhaohui WU,Guande QI,Shijian LI,Daqing ZHANG,Wangsheng ZHANG,Zonghui WANG. Prediction of urban human mobility using large-scale taxi traces and its applications. 中国计算机科学前沿, 2012,1
  • [3] Antikainen J. The concept of functional urban area. Findings of the Espon Project, 2005,01
  • [4] Sheng C;Zheng Y;Hsu W. Answering top-k similar region queries. Berlin:Springer-Verlag, 2010
  • [5] Xue A Y;Zhang R;Zheng Y. Destination prediction by sub-trajectory synthesis and privacy protection against such prediction. Piscataway,NJ:IEEE, 2013
  • [6] Chen C;Chen J;Barry J. Diurnal pattern of transit ridership:A case study of the New York City subway system. Journal of Transport Geography, 2009,03
  • [7] Blei D M;Ng A Y;Jordan M I. Latent dirichlet allocation. JOURNAL OF MACHINE LEARNING RESEARCH, 2003,02
  • [8] Steyvers M;Griffiths T. Probabilistic topic models. Handbook of Latent Semantic Analysis, 2007,07
  • [9] Kruschke J K. Bayesian data analysis. Wiley Interdisciplinary Reviews:Cognitive Science, 2010,05
  • [10] Wilkinson G G. Results and implications of a study of fifteen years of satellite image classification experiments. IEEE Transactions on Geoscience and Remote Sensing, 2005,03
  • [11] Azzopardi L;Girolami M;van Risjbergen K. Investigating the relationship between language model perplexity and IR precision-recall measures. New York:ACM, 2003
  • [12] National Bureau of Statistics of China. China Statistics Yearbook 2012. 北京:中国统计出版社, 2013
  • [13] Herold M;Liu X;Clarke K C. Spatial metrics and image texture for mapping urban land use. Photogrammetric Engineering & Remote Sensing, 2003,09
  • [14] Liu L;Biderman A;Ratti C. Urban mobility landscape:Real time monitoring of urban mobility patterns. Piscataway,NJ:IEEE, 2009
  • [15] Goh C Y;Dauwels J;Mitrovic N. Online mapmatching based on Hidden Markov model for real-time traffic sensing applications. Piscataway,NJ:IEEE, 2012
  • [16] Liu W;Zheng Y;Chawla S. Discovering spatiotemporal causal interactions in traffic data streams. New York:ACM, 2011
  • [17] Zheng Y;Xie X. Learning location correlation from gps trajectories. Piscataway,NJ:IEEE, 2010
  • [18] Zheng Y;Zhang L;Xie X. Mining correlation between locations using human location history. New York:ACM, 2009
  • [19] Guc B;May M;Saygin Y. Semantic annotation of GPS trajectories. Berlin:Springer-Verlag, 2008
  • [20] Yuan J;Zheng Y;Xie X. Discovering regions of different functions in a city using human mobility and POIs. New York:ACM, 2012
  • [21] Pan G;Qi G;Wu Z. Land-use classification using taxi GPS traces. IEEE Trans on Intelligent Transportation Systems, 2012,01
查看更多︾
相似文献 查看更多>>
18.234.51.17