01590695

Component

A serious roadway incident is defined as a motor-vehicle crash resulting in more than ten deaths. In this study, Bayesian networks were applied to analyze and prioritize the factors that influence serious roadway incidents in China. The Bayesian network structure was developed based on expert knowledge using Dempster-Shafer evidence theory, and the structure was modified based on a test for conditional independence. This paper collected 484 serious roadway incidents for the period 2000-2012 to calculate the posterior probability of each factor using the expectation-maximization learning algorithm. Results showed that the most influential factor contributing to serious roadway incidents was driver behavior, followed by vehicle condition, road condition and external environment. And compared to the other behaviors, speeding and mistaken adjustment had greater influence on serious roadway incidents. The findings in this study provide useful and valuable information for engineers to take corrective and preventative measures to reduce the probability for serious roadway incidents.

This paper was sponsored by TRB committee ANB20 Standing Committee on Safety Data, Analysis and Evaluation.

01584066

16-4787

English

20p

2016

Transportation Research Board 95th Annual Meeting

Web

Figures; Maps; References (22) ; Tables

Behavior; Crash causes; Crash characteristics; Drivers; Fatalities; Speeding

China

Highways; Safety and Human Factors; I80: Accident Studies; I82: Accidents and Transport Infrastructure; I83: Accidents and the Human Factor

Transportation Research Board Annual Meeting 2016 Paper #16-4787

TRIS, TRB, ATRI

Jan 12 2016 6:06PM