Gaussian process-based predictive modeling for bus ridership

The dynamics of a city are characterized, among others, by the traveling patterns of its dwellers. Accurate knowledge of human mobility patterns would have applications, e.g., in urban design, in the optimization of public transportation operating costs, and in the improvement of public transportation services. The present paper combines a large scale bus transportation dataset with publicly available data sources to predict bus usage. We propose a Gaussian process-based approach for modeling and predicting bus ridership. To validate our approach we perform experiments on data collected from Lisbon, Portugal. The results demonstrate significant improvements in prediction accuracy compared to a probabilistic baseline predictor.

[1]  M. Hale,et al.  Public Transportation's Contribution to U.S. Greenhouse Gas Reduction , 2007 .

[2]  R. Cervero,et al.  Adaptive Transit: Enhancing Suburban Transit Services , 2000 .

[3]  Laura Ferrari,et al.  Measuring Public-Transport Accessibility Using Pervasive Mobility Data , 2013, IEEE Pervasive Computing.

[4]  Albin Andersson,et al.  Greenhouse gas reduction , 2005 .

[5]  Aki Vehtari,et al.  Robust Gaussian Process Regression with a Student-t Likelihood , 2011, J. Mach. Learn. Res..

[6]  Teodor Gabriel Crainic,et al.  Designing the master schedule for demand-adaptive transit systems , 2012, Ann. Oper. Res..

[7]  Andry Rakotonirainy,et al.  Pervasive Technology and Public Transport: Opportunities Beyond Telematics , 2013, IEEE Pervasive Computing.

[8]  John Zimmerman,et al.  Swarthmore College , 2012 .

[9]  Karl Kottenhoff,et al.  Dynamic at-stop real-time information displays for public transport: effects on customers , 2007 .

[10]  Fumitaka Kurauchi,et al.  Using Bus Probe Data for Analysis of Travel Time Variability , 2009, J. Intell. Transp. Syst..

[11]  Steven I-Jy Chien,et al.  ESTIMATION OF BUS ARRIVAL TIMES USING APC DATA , 2004 .

[12]  Alan Borning,et al.  OneBusAway: A Transit Traveler Information System , 2009, MobiCASE.

[13]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[14]  Aki Vehtari,et al.  Bayesian Modeling with Gaussian Processes using the GPstuff Toolbox , 2012, 1206.5754.

[15]  Alan Borning,et al.  OneBusAway : A Transit Traveller Information System , 2009 .

[16]  David Evans,et al.  Statistical modelling and analysis of sparse bus probe data in urban areas , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[17]  Kay W. Axhausen,et al.  Understanding Metropolitan Collective Encounter Patterns , 2013 .

[18]  Carlo Ratti,et al.  Space and time-dependant bus accessibility: A case study in Rome , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[19]  R Zito,et al.  Global positioning systems in the time domain: How useful a tool for intelligent vehicle-highway systems? , 1995 .