Accurate prediction results in the field of intelligent transportation systems are crucial. They enable commuters to make informed decisions regarding travel modes, routes, and departure times, which can significantly enhance travel efficiency. Due to the unique characteristics of road networks, accurate prediction is particularly important. This paper proposes a deep learning method combining graph convolutional neural network and bidirectional long short-term memory network. The model uses GCN to extract the topological structure features of the road network, learns the spatial correlation of the road, and uses BiLSTM to learn the temporal correlation of the road network speed data. Finally, non-traffic factors are integrated into the deep model to improve the accuracy of prediction. It is verified by real road network speed data. Experimental results show that compared with the traditional prediction model, the root mean square error of the GCN-BiLSTM combination model is 1.455, the mean absolute error is 1.283, the R2 of the coefficient of determination is 0.937, and the 95% confidence interval is [-2.866, 3.233], which are better than other models. The proposed model has higher accuracy and stability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.