Imputation Model of the Link Travel Speed Data for Incident Detection System

This paper describes an imputation model that uses the multiple regression to accurately estimate average roadway link travel speeds for the incident detection algorithm and Intelligent Transportation System (ITS). This model predicts link travel speeds using a robust data imputation method based on available information for neighbor links and the adjacent time periods. A field test showed that the variance of the percent errors of link travel speeds was reduced when they were measured using the new model. Therefore, it can be concluded that the proposed model significantly improves the accuracy of travel speed measurement