Application of Bayesian Networks to Analyze in Analyzing Incidents and Decision-making

Incident management requires a full understanding of the characteristics of incidents to accurately estimate incident durations and to help make more efficient decisions, reducing the impact of non-recurring congestion. The goal of this paper is to have an articulate description of incident clearance patterns and to represent these findings with formalisms based on Bayesian Networks (BNs). BNs can be an innovative tool for incident management practice and can be used to create dynamic estimation trees that are extracted in the presence of an incident, enabling operators to create case-specific incident management strategies. We introduce the use of BNs to the transportation field to better understand the prevailing circumstances of incidents. This can only be accomplished by considering the stochastic variation of the data and bi-directional induction in decision-making. After a comprehensive review of the application of BNs to our problem, the dependency relations among all variables in a BN that can be used for quantitative and qualitative analysis are also presented.