Traffic volume forecasting model based on composite neural network and regional approach

Yuxuan Liu; Qifeng Bao; Zhiqing Zhong

doi:10.1117/12.2653518

27 September 2022 Traffic volume forecasting model based on composite neural network and regional approach

Yuxuan Liu, Qifeng Bao, Zhiqing Zhong

Proceedings Volume 12346, 2nd International Conference on Information Technology and Intelligent Control (CITIC 2022); 123460J (2022) https://doi.org/10.1117/12.2653518
Event: 2nd International Conference on Information Technology and Intelligent Control (CITIC 2022), 2022, Kunming, China

Abstract

Traffic flow is one of the most important urban operation and land development indicators. Effective traffic flow prediction is of great significance for optimizing urban transit systems and the improvement of land use planning. In this paper, a method based on area aggregation combined with long and short-term memory neural network + graph convolutional neural network is proposed to overcome the situation that the traditional travel matrix with zero elements makes it impossible to use deep learning methods for prediction. Experimental results show that the method proposed in this paper effectively improves the situation that the direct use of deep learning methods makes the prediction fall into local optimum. In addition, this paper has essential references and implications for traffic volume prediction.

Citation Download Citation

Yuxuan Liu, Qifeng Bao, and Zhiqing Zhong "Traffic volume forecasting model based on composite neural network and regional approach", Proc. SPIE 12346, 2nd International Conference on Information Technology and Intelligent Control (CITIC 2022), 123460J (27 September 2022); https://doi.org/10.1117/12.2653518

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