Conditionality and risk for the pedestrian: modelling with the Bayesian networks

The conditional script questionnaire (CSQ) makes possible to study the conditions under which drivers find it legitimate to transgress the Highway Code. In this paper, we propose to analyse conditional respect towards the pedestrian with a new methodology based on Bayesian networks (BN). This methodology is designed to give a useful decision support tool for the analyst. Starting from data encoded in the CSQ, we use structure learning algorithms in order to build a BN. Then, we exploit it for two purposes: to extract new knowledge about the main topics expressed in the CSQ and to make inferences. This methodology helps to better understand the behaviour of drivers interacting with pedestrians and what might be the cause of their decisions of legitimate transgressions. The efficiency of the methodology proposed here is illustrated and a context-dependent ‘mapping’ of the legitimate transgressions established.

[1]  Juan de Oña,et al.  Analysis of traffic accident injury severity on Spanish rural highways using Bayesian networks. , 2011, Accident; analysis and prevention.

[2]  Prabir Bhattacharya,et al.  A driver fatigue recognition model based on information fusion and dynamic Bayesian network , 2010, Inf. Sci..

[3]  Sandrine Gaymard,et al.  Les analyses canoniques simple et généralisée linéaires : applications à des données psycho-sociales , 2010 .

[4]  Nevin Lianwen Zhang,et al.  Exploiting Causal Independence in Bayesian Network Inference , 1996, J. Artif. Intell. Res..

[5]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[6]  George Yannis,et al.  Critical power two wheeler driving patterns at the emergence of an incident. , 2013, Accident; analysis and prevention.

[7]  V. Boucher,et al.  La perception des pietons par les conducteurs : correlations entre les donnees d'un œil electronique et le verbatim des conducteurs , 2013 .

[8]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[9]  Michael I. Jordan,et al.  An Introduction to Variational Methods for Graphical Models , 1999, Machine-mediated learning.

[10]  Helena Stigson,et al.  Literature review of pedestrian fatality risk as a function of car impact speed. , 2011, Accident; analysis and prevention.

[11]  Rosalind W. Picard,et al.  Modeling drivers' speech under stress , 2003, Speech Commun..

[12]  Xiaoping Zheng,et al.  Forecasting model for pedestrian distribution under emergency evacuation , 2010, Reliab. Eng. Syst. Saf..

[13]  Thomas L. Griffiths,et al.  Technical Introduction: A primer on probabilistic inference , 2005 .

[14]  F Mckenna,et al.  CRADLE ATTITUDES - GRAVE CONSEQUENCES - THE DEVELOPMENT OF GENDER DIFFERENCES IN RISKY ATTITUDES AND BEHAVIOUR IN ROAD USE , 2002 .

[15]  S. Gaymard,et al.  Conditional respect towards the pedestrian: difference between men and women and risk modeling by the Bayesian approach , 2014 .

[16]  John D. Lee,et al.  A hybrid Bayesian Network approach to detect driver cognitive distraction , 2014 .

[17]  H. Elffers,et al.  Rules for Breaking Formal Rules: Social Representations and Everyday Rule-Governed Behavior , 1994 .

[18]  Griselda López,et al.  Analysis of traffic accidents on rural highways using Latent Class Clustering and Bayesian Networks. , 2013, Accident; analysis and prevention.

[19]  Kevin Murphy,et al.  Bayes net toolbox for Matlab , 1999 .

[20]  Athanasios V. Vasilakos,et al.  Affectively intelligent and adaptive car interfaces , 2010, Inf. Sci..

[21]  F. Osiurak,et al.  The conditions of respect of rules in young and elderly drivers: an exploratory study , 2011 .

[22]  William D. Schafer,et al.  Gender differences in risk taking: A meta-analysis. , 1999 .

[23]  C. N. Liu,et al.  Approximating discrete probability distributions with dependence trees , 1968, IEEE Trans. Inf. Theory.

[24]  S Stradling,et al.  Behavioural characteristics and involvement in different types of traffic accident. , 1995, Accident; analysis and prevention.

[25]  P. Spirtes,et al.  Causation, Prediction, and Search, 2nd Edition , 2001 .

[26]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[27]  S. Gaymard.  The Theory of Conditionality: An Illustration of the Place of Norms in the Field of Social Thinking , 2014 .

[28]  Brian C Tefft,et al.  Impact speed and a pedestrian's risk of severe injury or death. , 2013, Accident; analysis and prevention.

[29]  S. Gaymard.  Pedestrian Representation Through the Analysis of Little Stories , 2012 .

[30]  Lakhmi C. Jain,et al.  Introduction to Bayesian Networks , 2008 .

[31]  Yuanchang Xie,et al.  Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis. , 2007, Accident; analysis and prevention.

[32]  S. Gaymard.  NORMS IN SOCIAL REPRESENTATIONS: TWO STUDIES WITH FRENCH YOUNG DRIVERS , 2009 .

[33]  F. Buschini,et al.  Penser la vie, le social, la nature. , 2001 .

[34]  Andy Shea,et al.  Traffic Safety and the Driver , 1992 .

[35]  Tom Burr,et al.  Causation, Prediction, and Search , 2003, Technometrics.

[36]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[37]  J. Doran,et al.  Experiments with the Graph Traverser program , 1966, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[38]  Kaan Ozbay,et al.  Estimation of incident clearance times using Bayesian Networks approach. , 2006, Accident; analysis and prevention.

[39]  David A. Bell,et al.  Learning Bayesian networks from data: An information-theory based approach , 2002, Artif. Intell..

[40]  Eleni I. Vlahogianni,et al.  Bayesian modeling of the microscopic traffic characteristics of overtaking in two-lane highways , 2012 .

[41]  Judea Pearl,et al.  A Theory of Inferred Causation , 1991, KR.

[42]  Ben J. M. Ale,et al.  Risk of human fatality in building fires: A decision tool using Bayesian networks , 2009 .

[43]  Moinul Hossain,et al.  A Bayesian network based framework for real-time crash prediction on the basic freeway segments of urban expressways. , 2012, Accident; analysis and prevention.

[44]  Carlos Arregui-Dalmases,et al.  Pedestrian injuries in eight European countries: an analysis of hospital discharge data. , 2010, Accident; analysis and prevention.