基于概率图模型的乘客出行链提取方法
|
摘要
以公共交通智能卡数据为基础,构建概率图模型,从乘客连续出行行为以及时空转移角度提取乘客出行链。从进出站客流时间分布特征出发,构建混合泊松模型,识别出站点周边用地性质信息;然后结合乘客连续的活动序列,构建隐马尔科夫模型,从乘客连续出行的时间特征和空间用地特征上识别出行目的,从而构建每位乘客基于公共交通的出行链。以北京市某一周工作日的轨道交通智能卡数据为例实现本文模型,结果表明:工作类活动以及回家类活动在全天主要时段分布与以往研究和调查结果相吻合,验证了模型的有效性;对于出行链,通勤类出行为主要出行,占68.5%,而其他类活动以单程出行为主。
Base on Smart Card Data(SCD)of public transit,aprobabilistic graph model was built to extract passengers' trip chains from the perspective of passenger continuous trips and temporal-spatial transition.First,in accordance with temporal distribution of center/exist passenger flow,a Poisson mixture model was established to identify land use attributes around the stations.Then,combing with the continuous activity sequences for each passenger,a hidden Markov model was constructed to infer trip purpose integrating temporal characters and land use characters.After inferring trip purpose,every passenger's public transit trip chain can be formulated.Finally,The SCD of Beijing subway in weekdays were used to test this model.Results show that time distribution of working activities and going home activities in a day conforms to prior researches and survey results,which validates the proposed model.For trip chains,commuting trips are the main type accounting to 68.5%,and other trips are mainly single-trip.
Base on Smart Card Data(SCD)of public transit,aprobabilistic graph model was built to extract passengers' trip chains from the perspective of passenger continuous trips and temporal-spatial transition.First,in accordance with temporal distribution of center/exist passenger flow,a Poisson mixture model was established to identify land use attributes around the stations.Then,combing with the continuous activity sequences for each passenger,a hidden Markov model was constructed to infer trip purpose integrating temporal characters and land use characters.After inferring trip purpose,every passenger's public transit trip chain can be formulated.Finally,The SCD of Beijing subway in weekdays were used to test this model.Results show that time distribution of working activities and going home activities in a day conforms to prior researches and survey results,which validates the proposed model.For trip chains,commuting trips are the main type accounting to 68.5%,and other trips are mainly single-trip.
引文
[1]翁剑成,王昌,王月玥,等.基于个体出行数据的公共交通出行链提取方法[J].交通运输系统工程与信息,2017,17(3):67-73.Weng Jian-cheng,Wang Chang,Wang Yue-yue,et al.Extraction method of public transit trip chains based on the individual riders′data[J].Journal of Transportation Systems Engineering and Information Technology,2017,17(3):67-73.
[2]Jiang S,Yang Y,Gupta S,et al.The TimeGeo modeling framework for urban motility without travel surveys[J].Proceedings of the National Academy of Sciences,2016,113(37):E5370-E5378.
[3]Diao M,Zhu Y,Ferreira J,et al.Inferring individual daily activities from mobile phone traces:a Boston example[J].Environment and Planning B—Planning&Design,2016,43(5):920-940.
[4]龙瀛,张宇,崔承印.利用公交刷卡数据分析北京职住关系和通勤出行[J].地理学报,2012,67(10):1339-1352.Long Ying,Zhang Yu,Cui Cheng-yin.Identifying commuting pattern of Beijing using bus smart card data[J].Acta Geographica Sinica,2012,67(10):1339-1352.
[5]Zhong C,Batty M,Manley E,et al.Variability in regularity:mining temporal mobility patterns in London,Singapore and Beijing using smart-card data[J].PLoS One,2016,11:e01492222.
[6]Hasan S,Schneider C M,Ukkusuri S V,et al.Spatiotemporal patterns of urban human mobility[J].Journal of Statistical Physics,2013,151(1/2):304-318.
[7]Chakirov A,Erath A.Activity identification and primary location modelling based on smart card payment data for public transport[C]∥Proceedings of13th International Conference on Travel Behavior,Singapore:Research Institute for Transport Planning and Systems,2012:1-22.
[8]Ali A,Kim J,Lee S.Travel behavior analysis using smart card data[J].KSCE Journal of Civil Engineering,2016,20(4):1532-1539.
[9]Li G,Yu L,Ng W S,et al.Predicting home and work locations using public transport smart card data by spectral analysis[C]∥Proceedings of 2015IEEE 18th International Conference on Intelligent Transportation Systems,Washington:IEEE Computer Society,Las Palmas,2015:2788-2793.
[10]Jordan M I.Learning in Graphical Models[M].Massachusetts:MIT Press,1999.
[11]Koller D,Friedman N.概率图模型:原理与技术[M].北京:清华大学出版社,2015.
[12]Etienne C,Latifa O.Model-based count series clustering for bike sharing system usage mining:a case study with the velib system of Paris[J].ACM Transactions on Intelligent Systems&Technology,2014,5(3):1-21.
[13]Rau Andrea,Celeux Gilles,Martin-Magniette MarieLaure,et al.Clustering High-throughput Sequencing Data with Poisson Mixture Models[M].Paris:INRIA,2011.
[14]Hasan S,Schneider C M,Ukkusuri S V,et al.Spatiotemporal patterns of urban human mobility[J].Journal of Statistical Physics,2013,151(1/2):304-318.
[15]Bouman P,Lovric M,Li T,et al.Recognizing demand patterns from smart card data for agent-based micro-simulation of public transport[C]∥Proceedings of the 7th Workshop on Agents in Traffic and Transportation,Valencia,2012.
[16]Han G,Sohn K.Activity imputation for trip-chains elicited from smart-card data using a continuous hidden Markov model[J].Transportation Research Part B:Methodological,2016,83:121-135.
[17]北京市交通委员会.第五次北京城市交通综合调查报告[R].北京:北京市交通委员会,2016.
[18]谢留宏,路峰,张俊辉,等.北京实行错峰上下班解决交通拥堵问题的分析探讨[J].交通标准化,2011(增刊1):53-57.Xie Liu-hong,Lu Feng,Zhang Jun-hui,et al.Analysis and investigation on implementation of peak shifting to solve traffic congestion problem in Beijing[J].Transport Standardization,2011(Sup.1):53-57.
[2]Jiang S,Yang Y,Gupta S,et al.The TimeGeo modeling framework for urban motility without travel surveys[J].Proceedings of the National Academy of Sciences,2016,113(37):E5370-E5378.
[3]Diao M,Zhu Y,Ferreira J,et al.Inferring individual daily activities from mobile phone traces:a Boston example[J].Environment and Planning B—Planning&Design,2016,43(5):920-940.
[4]龙瀛,张宇,崔承印.利用公交刷卡数据分析北京职住关系和通勤出行[J].地理学报,2012,67(10):1339-1352.Long Ying,Zhang Yu,Cui Cheng-yin.Identifying commuting pattern of Beijing using bus smart card data[J].Acta Geographica Sinica,2012,67(10):1339-1352.
[5]Zhong C,Batty M,Manley E,et al.Variability in regularity:mining temporal mobility patterns in London,Singapore and Beijing using smart-card data[J].PLoS One,2016,11:e01492222.
[6]Hasan S,Schneider C M,Ukkusuri S V,et al.Spatiotemporal patterns of urban human mobility[J].Journal of Statistical Physics,2013,151(1/2):304-318.
[7]Chakirov A,Erath A.Activity identification and primary location modelling based on smart card payment data for public transport[C]∥Proceedings of13th International Conference on Travel Behavior,Singapore:Research Institute for Transport Planning and Systems,2012:1-22.
[8]Ali A,Kim J,Lee S.Travel behavior analysis using smart card data[J].KSCE Journal of Civil Engineering,2016,20(4):1532-1539.
[9]Li G,Yu L,Ng W S,et al.Predicting home and work locations using public transport smart card data by spectral analysis[C]∥Proceedings of 2015IEEE 18th International Conference on Intelligent Transportation Systems,Washington:IEEE Computer Society,Las Palmas,2015:2788-2793.
[10]Jordan M I.Learning in Graphical Models[M].Massachusetts:MIT Press,1999.
[11]Koller D,Friedman N.概率图模型:原理与技术[M].北京:清华大学出版社,2015.
[12]Etienne C,Latifa O.Model-based count series clustering for bike sharing system usage mining:a case study with the velib system of Paris[J].ACM Transactions on Intelligent Systems&Technology,2014,5(3):1-21.
[13]Rau Andrea,Celeux Gilles,Martin-Magniette MarieLaure,et al.Clustering High-throughput Sequencing Data with Poisson Mixture Models[M].Paris:INRIA,2011.
[14]Hasan S,Schneider C M,Ukkusuri S V,et al.Spatiotemporal patterns of urban human mobility[J].Journal of Statistical Physics,2013,151(1/2):304-318.
[15]Bouman P,Lovric M,Li T,et al.Recognizing demand patterns from smart card data for agent-based micro-simulation of public transport[C]∥Proceedings of the 7th Workshop on Agents in Traffic and Transportation,Valencia,2012.
[16]Han G,Sohn K.Activity imputation for trip-chains elicited from smart-card data using a continuous hidden Markov model[J].Transportation Research Part B:Methodological,2016,83:121-135.
[17]北京市交通委员会.第五次北京城市交通综合调查报告[R].北京:北京市交通委员会,2016.
[18]谢留宏,路峰,张俊辉,等.北京实行错峰上下班解决交通拥堵问题的分析探讨[J].交通标准化,2011(增刊1):53-57.Xie Liu-hong,Lu Feng,Zhang Jun-hui,et al.Analysis and investigation on implementation of peak shifting to solve traffic congestion problem in Beijing[J].Transport Standardization,2011(Sup.1):53-57.