Files
Abstract
Decision makers working to improve transportation systems must constantly balance the need
to improve roadway safety through infrastructure investment with constraints of available
resources. We have explored the additional information available to transportation decision
makers by integrating two independent datasets, traffic accident and roadway pavement
condition data. The roadway condition data are collected by the Alabama Department of
Transportation. The traffic accident data are available in the University of Alabama’s Critical
Analysis Reporting Environment (CARE) system. The Algorithm Development and Mining
(ADaM) [Rushing] system, a data mining toolkit developed by the University of Alabama in
Huntsville (UAH) Information Technology and Systems Center (ITSC) was used to examine
the possible relationships between roadway data and traffic safety data. The preliminary
study showed that discernable and predictable associations can be identified through analysis
of the roadway condition and reported traffic accident events. The analysis results indicate
that data mining is a successful method to perform advanced analysis to improve
infrastructure investment decisions.