Next Direction Route Choice Model for Cyclist Using Panel Data

Travel demand forecasting has been one of the major areas of interest in transportation research. In many urban cities in North America, bike sharing is a popular and heavily used mode of transport for many commuters downtown [1], [2]. When planning new infrastructures and facilities, these bike sharing services need to decide how to best improve level of service, user satisfaction and reliability. In literature on bike sharing models, the main objective is to describe a model which will explain the extent the relation between trip, environment variables and demand, such that the goal will be to improve transport operations and infrastructure design of new bike sharing services. Some papers have investigated the planning of new bike stations, impact on public transport and data analysis of GPS trackers in bikes [1], [3], [4].

[1]  Eran Ben-Elia,et al.  Which road do I take? A learning-based model of route-choice behavior with real-time information , 2010 .

[2]  Kay W. Axhausen,et al.  Route choice of cyclists in Zurich , 2010 .

[3]  David M Levinson,et al.  Valuation of travel time reliability from a GPS-based experimental design , 2013 .

[4]  Jennifer Dill,et al.  Where do cyclists ride? A route choice model developed with revealed preference GPS data , 2012 .

[5]  M. Bierlaire,et al.  Sampling of Alternatives for Route Choice Modeling , 2009 .

[6]  Hema Swetha Koppula,et al.  Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Ahmed M El-Geneidy,et al.  Who cycles more? Determining cycling frequency through a segmentation approach in Montreal, Canada , 2015 .

[8]  Felipe González,et al.  A combined destination and route choice model for a bicycle sharing system , 2016 .

[9]  Michel Bierlaire,et al.  BIOGEME: a free package for the estimation of discrete choice models , 2003 .

[10]  Nobuhiro Uno,et al.  Experimental Study of Effects of Travel Time Distribution Information on Dynamic Route Choice Behavior , 2014, J. Intell. Transp. Syst..

[11]  Adam Astrid Kemperman,et al.  Vacation length choice : a dynamic mixed multinomial logit model , 2014 .

[12]  Ahmed M El-Geneidy,et al.  A travel behavior analysis of urban cycling facilities in Montréal, Canada , 2011 .

[13]  Ching-Fu Chen,et al.  Estimating recreational cyclists’ preferences for bicycle routes – Evidence from Taiwan , 2013 .

[14]  Michael Keane,et al.  Panel Data Discrete Choice Models of Consumer Demand , 2013 .

[15]  Anders Karlström,et al.  A link based network route choice model with unrestricted choice set , 2013 .

[16]  Naveen Eluru,et al.  Analysing bicycle-sharing system user destination choice preferences: Chicago’s Divvy system , 2015 .

[17]  Ta-Hui Yang,et al.  Strategic design of public bicycle sharing systems with service level constraints , 2011 .

[18]  Hirokatsu Kataoka,et al.  Predicting driving behavior using inverse reinforcement learning with multiple reward functions towards environmental diversity , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[19]  Daniel Fuller,et al.  Impact evaluation of a public bicycle share program on cycling: a case example of BIXI in Montreal, Quebec. , 2013, American journal of public health.

[20]  Ralph Buehler,et al.  Bike Lanes and Other Determinants of Capital Bikeshare Trips , 2012 .

[21]  Michel Bierlaire,et al.  Destination Choice Model including panel data using WiFi localization in a pedestrian facility , 2015 .