Research on expressway travel time prediction based on deep learning

Peijing Xi; Yuanli Gu

doi:10.1117/12.2620246

22 December 2021 Research on expressway travel time prediction based on deep learning

Peijing Xi, Yuanli Gu

Proceedings Volume 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021); 120581O (2021) https://doi.org/10.1117/12.2620246
Event: 5th International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 2021, Chongqing, China

Abstract

Accurate and efficient prediction of road travel time plays a significant role in the application of intelligent transportation system. In order to accurately predict travel time, a new attention-based CNN-BiGRU hybrid model is proposed, which can simultaneously capture the spatial-temporal features of travel time. In this model, convolutional neural network (CNN) and bi-directional gated recurrent unit (BiGRU) are used to collect the spatial and temporal characteristics of travel time separately. The attention mechanism was used for assigning different weights according to the importance of the data to further improve the prediction accuracy of the model. The model is verified by using the charging data of Guangzhou airport south line, and the experiment shows that the model can achieve accurate travel time prediction.

Citation Download Citation

Peijing Xi and Yuanli Gu "Research on expressway travel time prediction based on deep learning", Proc. SPIE 12058, Fifth International Conference on Traffic Engineering and Transportation System (ICTETS 2021), 120581O (22 December 2021); https://doi.org/10.1117/12.2620246

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