Estimation of urban crowd flux based on mobile phone location data: A case study of Beijing, China

Abstract In previous urban planning research, the fine-grained population was considered a crucial factor. However, this population, which is generated from census data, represents only the number of people who live in a region. This static figure cannot indicate the underlying number of people and their temporal variation. Therefore, any decision-making based on the static population may be separated from reality. To overcome this difficulty, in this paper, the urban crowd flux is initially proposed and defined as the number of individuals flowing into or out of a region per unit time interval. Then, the urban crowd flux is estimated using an approach of human trajectory gridding reconstruction based on mobile phone location data. This approach is divided into three steps. First, the trajectory of each individual is extracted from sparse sampling of mobile phone location data after data cleansing. Then, combining with a road network, the trajectory of each individual is reconstructed by network interpolation based on the shortest path algorithm in regular grids. Third, we use the velocities of each user's trajectory record to estimate the urban crowd flux on spatio-temporal grids at each time slice. Finally, urban crowd flux in Beijing, China were estimated using our method and the spatio-temporal characteristics of flux is analyzed.

[1]  Daqing Zhang,et al.  Where is the Largest Market: Ranking Areas by Popularity from Location Based Social Networks , 2013, 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing.

[2]  Ambuj K. Singh,et al.  FCCF: forecasting citywide crowd flows based on big data , 2016, SIGSPATIAL/GIS.

[3]  S I Hay,et al.  Determining global population distribution: methods, applications and data. , 2006, Advances in parasitology.

[4]  Huidong Jin,et al.  PutMode: prediction of uncertain trajectories in moving objects databases , 2010, Applied Intelligence.

[5]  Petter Holme,et al.  Predictability of population displacement after the 2010 Haiti earthquake , 2012, Proceedings of the National Academy of Sciences.

[6]  Carlo Ratti,et al.  Eigenplaces: Analysing Cities Using the Space–Time Structure of the Mobile Phone Network , 2009 .

[7]  Simone Vantini,et al.  Analysis of spatio-temporal mobile phone data: a case study in the metropolitan area of Milan , 2015, Statistical Methods & Applications.

[8]  Cecilia Mascolo,et al.  Geo-spotting: mining online location-based services for optimal retail store placement , 2013, KDD.

[9]  P. Nijkamp,et al.  Data from mobile phone operators , 2015 .

[10]  A. Tatem,et al.  Dynamic population mapping using mobile phone data , 2014, Proceedings of the National Academy of Sciences.

[11]  Xiaomin Qiu,et al.  Population Estimation Methods in GIS and Remote Sensing: A Review , 2005 .

[12]  Shaojie Qiao,et al.  A Self-Adaptive Parameter Selection Trajectory Prediction Approach via Hidden Markov Models , 2015, IEEE Transactions on Intelligent Transportation Systems.

[13]  Lei Zou,et al.  Detecting urban black holes based on human mobility data , 2015, SIGSPATIAL/GIS.

[14]  F. Calabrese,et al.  Urban gravity: a model for inter-city telecommunication flows , 2009, 0905.0692.

[15]  Eric Delmelle,et al.  Mapping collective human activity in an urban environment based on mobile phone data , 2014 .

[16]  Stefano Secci,et al.  Estimating human trajectories and hotspots through mobile phone data , 2014, Comput. Networks.

[17]  A. Tatem,et al.  Quantifying seasonal population fluxes driving rubella transmission dynamics using mobile phone data , 2015, Proceedings of the National Academy of Sciences.

[18]  A. Bolignano,et al.  A dynamic urban air pollution population exposure assessment study using model and population density data derived by mobile phone traffic , 2016 .

[19]  Margaret Martonosi,et al.  Human mobility modeling at metropolitan scales , 2012, MobiSys '12.

[20]  Tao Zhang,et al.  Understanding Spatiotemporal Patterns of Human Convergence and Divergence Using Mobile Phone Location Data , 2016, ISPRS Int. J. Geo Inf..

[21]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[22]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[23]  Yuan Tian,et al.  Understanding intra-urban trip patterns from taxi trajectory data , 2012, J. Geogr. Syst..

[24]  Fengli Xu,et al.  Context-aware real-time population estimation for metropolis , 2016, UbiComp.

[25]  Yu Liu,et al.  Towards Estimating Urban Population Distributions from Mobile Call Data , 2012 .

[26]  Catherine Linard,et al.  Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data , 2015, PloS one.