Short term traffic flow prediction research based on chaotic local model

Huan Wang; Qingyuan Meng; Chongfu Zhang

doi:10.1117/12.2519930

14 February 2019 Short term traffic flow prediction research based on chaotic local model

Huan Wang, Qingyuan Meng, Chongfu Zhang

Proceedings Volume 11048, 17th International Conference on Optical Communications and Networks (ICOCN2018); 1104815 (2019) https://doi.org/10.1117/12.2519930
Event: 17th International Conference on Optical Communications and Networks (ICOCN2018), 2018, Zhuhai, China

Abstract

Short term traffic flow prediction is of great significance for easing traffic congestion and maximizing road carrying capacity. This paper proposes an effective algorithm for traffic flow prediction. Firstly, the algorithm analyzes the characteristics of daily traffic flow. According to the difference, the daily traffic flows are divided into workday type, and holiday type, and each type of data is integrated to predict the corresponding day type traffic flow. Then based on phase space reconstruction, a chaotic local prediction algorithm is proposed. The algorithm uses Euclidean distance to select phase space reference neighborhood successively, and support vector machine is used to establish the mapping relationship between neighboring points. This algorithm is used to predict the data of an intersection in Guangzhou, and satisfactory prediction accuracy has been achieved.

Citation Download Citation

Huan Wang, Qingyuan Meng, and Chongfu Zhang "Short term traffic flow prediction research based on chaotic local model", Proc. SPIE 11048, 17th International Conference on Optical Communications and Networks (ICOCN2018), 1104815 (14 February 2019); https://doi.org/10.1117/12.2519930

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