Modeling Individuals' Largest Daily Trip Displacement using Extreme Value Theory

As a significant factor in urban planning and traffic forecasting, human mobility draws intensive attentions in recent years with the emergence of geo-related data. In this paper, we build models for human mobility with regards to individuals’ largest daily displacement using Extreme Value Theory (EVT) based on nearly 40 million individuals’ trajectories. It is found that the largest daily displacement can be well fitted by the Generalized Pareto Distribution (GPD) and is not heavy tailed compared to the exponential distribution. Besides, we also explored differences in distribution of the largest daily displacement according to gender and weekday. The analysis results indicate that male tend to have a larger displacement and individuals tend to travel longer on weekends.

[1]  Dino Pedreschi,et al.  Returners and explorers dichotomy in human mobility , 2015, Nature Communications.

[2]  Richard L. Smith.  Estimating tails of probability distributions , 1987 .

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

[4]  T. Geisel,et al.  The scaling laws of human travel , 2006, Nature.

[5]  Stuart G. Coles,et al.  Bayesian methods in extreme value modelling: a review and new developments. , 1996 .

[6]  Shunjiang Ni,et al.  Impact of travel patterns on epidemic dynamics in heterogeneous spatial metapopulation networks. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Abas Md Said,et al.  Predicting Traffic Bursts Using Extreme Value Theory , 2009, 2009 International Conference on Signal Acquisition and Processing.

[8]  Kyunghan Lee,et al.  On the Levy-Walk Nature of Human Mobility , 2008, IEEE INFOCOM 2008 - The 27th Conference on Computer Communications.

[9]  Xing Xie,et al.  Urban computing with taxicabs , 2011, UbiComp '11.

[10]  Faustino Prieto,et al.  Modelling road accident blackspots data with the discrete generalized Pareto distribution. , 2013, Accident; analysis and prevention.

[11]  Tao Zhou,et al.  Diversity of individual mobility patterns and emergence of aggregated scaling laws , 2012, Scientific Reports.

[12]  Sabrina Gaito,et al.  Extracting human mobility patterns from GPS-based traces , 2010, 2010 IFIP Wireless Days.

[13]  Yan Zhang,et al.  Towards Maximizing Timely Content Delivery in Delay Tolerant Networks , 2015, IEEE Transactions on Mobile Computing.

[14]  J. Pickands.  Statistical Inference Using Extreme Order Statistics , 1975 .

[15]  M. Y. Choi,et al.  Modification of the gravity model and application to the metropolitan Seoul subway system. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  On extremal theory for self-similar processes , 1998 .

[17]  Alessandro Vespignani,et al.  Modeling human mobility responses to the large-scale spreading of infectious diseases , 2011, Scientific reports.

[18]  Xing Xie,et al.  Discovering regions of different functions in a city using human mobility and POIs , 2012, KDD.

[19]  Maxi San Miguel,et al.  Influence of sociodemographics on human mobility , 2015 .

[20]  Xiao Liang,et al.  The scaling of human mobility by taxis is exponential , 2011, ArXiv.

[21]  Sasu Tarkoma,et al.  Accelerometer-based transportation mode detection on smartphones , 2013, SenSys '13.