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

Mengyuan Gao; Xiufeng Chen; Ziyu Chen; Ruicong Wang

doi:10.1117/12.2668638

16 February 2023 Traffic state recognition of urban expressway based on K-means clustering and AdaBoost-DS

Mengyuan Gao, Xiufeng Chen, Ziyu Chen, Ruicong Wang

Proceedings Volume 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022); 125911A (2023) https://doi.org/10.1117/12.2668638
Event: 6th International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 2022, Guangzhou, China

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.

Citation Download Citation

Mengyuan Gao, Xiufeng Chen, Ziyu Chen, and Ruicong Wang "Traffic state recognition of urban expressway based on K-means clustering and AdaBoost-DS", Proc. SPIE 12591, Sixth International Conference on Traffic Engineering and Transportation System (ICTETS 2022), 125911A (16 February 2023); https://doi.org/10.1117/12.2668638

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available