Short-term traffic flow prediction based on improved imperial competition algorithm

Fengping Yin; Danhong Zhang; Wenhui Luo; Bin Gao

doi:10.1117/12.2653184

10 November 2022 Short-term traffic flow prediction based on improved imperial competition algorithm

Fengping Yin, Danhong Zhang, Wenhui Luo, Bin Gao

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123315Q (2022) https://doi.org/10.1117/12.2653184
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

Short term traffic flow prediction provides effective information and decision-making through the prediction of future traffic conditions, so as to improve people's travel efficiency and alleviate urban traffic pressure. Improving the accuracy of short-term traffic flow prediction has become a hot issue in current research. By introducing random factors, this paper improves the movement strategy of the colony of the imperial competition algorithm. In addition to the assimilation of colonies by the Empire, colonies have a certain probability of reform and inheritance. By constructing a Back Propagation (BP) neural network model for short-term traffic flow prediction, the improved algorithm is applied to solve the weight and threshold of the model. According to the simulation results, the Mean Absolute Percent Error (MAPE) of RICA-BP is only 4.15%, which achieves a good prediction accuracy.

Citation Download Citation

Fengping Yin, Danhong Zhang, Wenhui Luo, and Bin Gao "Short-term traffic flow prediction based on improved imperial competition algorithm", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123315Q (10 November 2022); https://doi.org/10.1117/12.2653184

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