Effects of built environment on bicycle wrong Way riding behavior: A data-driven approach.

Bicycle wrong way riding (WWR) is a dangerous and often neglected behavior that engenders threats to traffic safety. Owing to the lack of exposure data, the detection of WWR and its relationship with the built environment (BE) factors remain unclear. Accordingly, this study fills the research gaps by proposing a WWR detection framework based on bike-sharing trajectories collected from Chengdu, China. Moreover, this study adopts Negative Binomial-based Additive Decision Tree to investigate the impacts of built environment on WWR frequencies. Results reveal that (1) WWR distribution is unaffected by different periods in a day; (2) road length is more influential than road level and road direction in WWR occurrence; (3) company, bus stop, subway station, residence, and catering facility are primary contributors affecting WWR behavior during peak hours, whereas education becomes an emerging influential variable during nonpeak hours; and most importantly, (4) these variables clearly present non-linear effects on the WWR frequencies. Therefore, geographically differentiated policies should be adopted for bicycle safety improvement.

[1]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[2]  Feng Wei,et al.  An empirical tool to evaluate the safety of cyclists: Community based, macro-level collision prediction models using negative binomial regression. , 2013, Accident; analysis and prevention.

[3]  Lee D. Han,et al.  Modeling Route Choice of Utilitarian Bikeshare Users with GPS Data , 2016 .

[4]  Brian Casey Langford,et al.  Risky riding: Naturalistic methods comparing safety behavior from conventional bicycle riders and electric bike riders. , 2015, Accident; analysis and prevention.

[5]  Chandra R. Bhat,et al.  On Accommodating Spatial Dependence in Bicycle and Pedestrian Injury Counts by Severity Level , 2013 .

[6]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[7]  Yi-Shih Chung,et al.  Factor complexity of crash occurrence: An empirical demonstration using boosted regression trees. , 2013, Accident; analysis and prevention.

[8]  Yanhua Li,et al.  Planning Bike Lanes based on Sharing-Bikes' Trajectories , 2017, KDD.

[9]  Robert N. Stewart,et al.  Exploring the impact of walk–bike infrastructure, safety perception, and built-environment on active transportation mode choice: a random parameter model using New York City commuter data , 2018 .

[10]  Kara M Kockelman,et al.  A Poisson-lognormal conditional-autoregressive model for multivariate spatial analysis of pedestrian crash counts across neighborhoods. , 2013, Accident; analysis and prevention.

[11]  Greg P. Griffin,et al.  Planning for Bike Share Connectivity to Rail Transit. , 2016, Journal of public transportation.

[12]  Alan Wachtel,et al.  Risk Factors for Bicycle-Motor Vehicle Collisions at Intersections * , 1994 .

[13]  K. Krizek,et al.  Proximity to Trails and Retail: Effects on Urban Cycling and Walking , 2006 .

[14]  Luc Int Panis,et al.  Predicting cycling accident risk in Brussels: a spatial case-control approach. , 2014, Accident; analysis and prevention.

[15]  Dirk Lauwers,et al.  A spatio-temporal mapping to assess bicycle collision risks on high-risk areas (Bridges) - A case study from Taipei (Taiwan) , 2019, Journal of Transport Geography.

[16]  Peng Chen,et al.  Effects of the Built Environment on Automobile-Involved Pedestrian Crash Frequency and Risk , 2016 .

[17]  L. Miranda-Moreno,et al.  Cyclist activity and injury risk analysis at signalized intersections: a Bayesian modelling approach. , 2013, Accident; analysis and prevention.

[18]  Srinivas S Pulugurtha,et al.  Pedestrian crash estimation models for signalized intersections. , 2011, Accident; analysis and prevention.

[19]  Giancarlo Bacchieri,et al.  Cycling to work in Brazil: users profile, risk behaviors, and traffic accident occurrence. , 2010, Accident; analysis and prevention.

[20]  Jen-Jia Lin,et al.  Associations of built environments with spatiotemporal patterns of public bicycle use , 2019, Journal of Transport Geography.

[21]  Patrick Morency,et al.  The link between built environment, pedestrian activity and pedestrian-vehicle collision occurrence at signalized intersections. , 2011, Accident; analysis and prevention.

[22]  Chandra R. Bhat,et al.  An analysis of bicycle route choice preferences in Texas, US , 2009 .

[23]  Billy Charlton,et al.  A GPS-based bicycle route choice model for San Francisco, California , 2011 .

[24]  Sarath C. Joshua,et al.  Estimating truck accident rate and involvements using linear and poisson regression models , 1990 .

[25]  Marilyn Johnson,et al.  Bicycle train intermodality: Effects of demography, station characteristics and the built environment , 2019, Journal of Transport Geography.

[26]  Greg Lindsey,et al.  Exposure to Risk and the Built Environment, an Empirical Study of Bicycle Crashes in Minneapolis , 2017 .

[27]  Mohamed Abdel-Aty,et al.  Macro-level pedestrian and bicycle crash analysis: Incorporating spatial spillover effects in dual state count models. , 2016, Accident; analysis and prevention.

[28]  Satish V. Ukkusuri,et al.  Random Parameter Model Used to Explain Effects of Built-Environment Characteristics on Pedestrian Crash Frequency , 2011 .

[29]  J. Gutiérrez,et al.  Optimizing the location of stations in bike-sharing programs: A GIS approach , 2012 .

[30]  Mohamed Abdel-Aty,et al.  Macroscopic spatial analysis of pedestrian and bicycle crashes. , 2012, Accident; analysis and prevention.

[31]  Raghavan Srinivasan,et al.  Evaluating the safety effects of bicycle lanes in New York City. , 2012, American journal of public health.

[32]  Peng Chen,et al.  Built environment effects on bike crash frequency and risk in Beijing. , 2017, Journal of safety research.

[33]  Mohamed Abdel-Aty,et al.  Application of Poisson random effect models for highway network screening. , 2014, Accident; analysis and prevention.

[34]  Peng Chen,et al.  Built environment factors in explaining the automobile-involved bicycle crash frequencies: a spatial statistic approach , 2015 .

[35]  Daniel A. Rodriguez,et al.  Objective correlates and determinants of bicycle commuting propensity in an urban environment , 2015 .

[36]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[37]  Benjamin Hofner,et al.  Model-based boosting in R: a hands-on tutorial using the R package mboost , 2012, Computational Statistics.

[38]  Fernando A Wilson,et al.  Bicyclists found at fault for bicycle crashes in California. , 2016, The American journal of emergency medicine.

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

[40]  Chuan Ding,et al.  Non-linear effects of the built environment on automobile-involved pedestrian crash frequency: A machine learning approach. , 2018, Accident; analysis and prevention.

[41]  Chao Tian,et al.  Detecting Vehicle Illegal Parking Events using Sharing Bikes' Trajectories , 2018, KDD.

[42]  Xing Xie,et al.  An Interactive-Voting Based Map Matching Algorithm , 2010, 2010 Eleventh International Conference on Mobile Data Management.

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

[44]  Ta-Hui Yang,et al.  A hub location inventory model for bicycle sharing system design: Formulation and solution , 2013, Comput. Ind. Eng..

[45]  Ziwen Ling,et al.  Using CyclePhilly data to assess wrong-way riding of cyclists in Philadelphia. , 2018, Journal of safety research.

[46]  Chuan Ding,et al.  Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method , 2017, IEEE Transactions on Intelligent Transportation Systems.

[47]  Luis F. Miranda-Moreno,et al.  Disaggregate Exposure Measures and Injury Frequency Models of Cyclist Safety at Signalized Intersections , 2011 .

[48]  Xiaolei Ma,et al.  Impacts of free-floating bikesharing system on public transit ridership , 2019, Transportation Research Part D: Transport and Environment.

[49]  Federico Fraboni,et al.  Using data mining techniques to predict the severity of bicycle crashes. , 2017, Accident; analysis and prevention.