Abstract
Work zone accidents are important concerns for transportation decision-makers. Therefore, knowledge of driving behaviors and traffic patterns are essential for identifying significant risk factors (RF) in work zones. Such knowledge can be difficult obtain in a field study without introducing new risks or driving hazards. This research uses integrated data mining and multi-criteria decision-making (MCDM) methods as part of a simulator-based case study of work zone logistics along a highway in Missouri. The research design incorporates k-mean clustering to cluster driving behavior trends, analytic network process (ANP) to determine weights for criteria that are most likely to impact work zones, and the Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method to rank the alternatives (clusters). Transportation engineers and decision makers can use results from this case study to identify driving populations most likely to engage in risky driving behaviors within work zones, and to provide guidance on effective work zone management.