Implementing partial least squares regression in high dimensional road capacity calibration

Abstract

In this paper, a new calibration method for road capacities in urban networks is presented. The method relies on partial least squares (PLS) regression, which combines calibration and dimensionality reduction capabilities. A sampling strategy is implemented to further improve the calibration efficiency and accuracy. Moreover, influences of different parameters on calibration results are investigated. This method is demonstrated to be feasible and efficient in an urban road network (Stockholm, Sweden).