Traffic state recognition of urban expressway based on K-means clustering and AdaBoost-DS

Abstract

In order to identify the traffic state of urban expressway more accurately, a traffic state recognition model based on K-means clustering algorithm and AdaBoost integrated with multiple decision stump classifiers (AdaBoost-DS) is proposed. Taking the traffic flow, velocity and occupancy as the basic parameters, combined with the existing research results, the expressway traffic state is divided into four categories, and the K-means clustering algorithm is used to classify the traffic state; then, the classified traffic flow data are used to train the AdaBoost-DS model. The example verification and comparative analysis of the measured data of urban expressway show that the method in this paper is effective and feasible, and its recognition accuracy is 93.2%, which is 7.6% higher than that of BPNN.