Artificial neural network speed profile model for construction work zones on high-speed highways

Speed profile models can be used as a diagnostic tool by highway engineers. Previous work has investigated relationships between operating speed and geometric roadway elements for permanent roadway conditions on predominantly two-lane rural roads. However, little research of this type has been directed specifically toward construction work zones. In this study, a speed profile model for construction work zones on high speed highways was developed using artificial neural networks and made available for use by practitioners through a MS EXCEL interface. The model inputs include horizontal and vertical alignment variables, cross section dimensions and traffic control features. A linear reference system is used for model input and output. Three categories of vehicles--cars, trucks, and all vehicles--were used in this study. Models for the 15th percentile speed, mean speed, and 85th percentile speed were developed. DOI: 10.1061(ASCE)0733-947X(2007)133:3(198) CE Database subject headings: Traffic speed; Highway construction; Neural network; Workspace; Models.