Freeway traffic flow prediction based on hidden Markov model

Jiyang Jiang; Tangyi Guo; Weipeng Pan; Yi Lu

doi:10.1117/12.2627779

14 March 2022 Freeway traffic flow prediction based on hidden Markov model

Jiyang Jiang, Tangyi Guo, Weipeng Pan, Yi Lu

Proceedings Volume 12165, International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021); 121651L (2022) https://doi.org/10.1117/12.2627779
Event: 2021 International Conference on Intelligent Traffic Systems and Smart City, 2021, Zhengzhou, China

Abstract

Nowadays, scientific and reasonable traffic volume prediction plays an important role especially in the traffic infrastructure planning. In the recent research, establishing a robust mathematical model for traffic volume prediction becomes a challenging problem. In our research, Hidden Markov Model (HMM) is constructed based on the numeral characteristics of monthly traffic volume for each freeway in Jiangsu Province. By analyzing the Markov property of the monthly flat peak traffic volume and the nonlinear effect of the monthly peak traffic volume, we further predict the future monthly traffic volume. Compared with the traditional models, our proposed model has significant advantages in some evaluation indicator, such as MRE, MAE, RMSE. Further more, The construction of this model only depends on the numerical characteristics of historical traffic volume data, which has the advantages of convenience as well as broad application prospects.

Citation Download Citation

Jiyang Jiang, Tangyi Guo, Weipeng Pan, and Yi Lu "Freeway traffic flow prediction based on hidden Markov model", Proc. SPIE 12165, International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021), 121651L (14 March 2022); https://doi.org/10.1117/12.2627779

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