Sorry, you need to enable JavaScript to visit this website.

Structural Recurrent Neural Network for Traffic Speed Prediction

Citation Author(s):
Youngjoo Kim, Peng Wang, Lyudmila Mihaylova
Submitted by:
Lyudmila Mihaylova
Last updated:
6 May 2019 - 6:41pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters:
Lyudmila Mihaylova
Paper Code:
2899
 

Deep neural networks have recently demonstrated the traffic prediction capability with the time series data obtained by sensors mounted on road segments. However, capturing spatio-temporal features of the traffic data often requires a significant number of parameters to train, increasing computational burden. In this work we demonstrate that embedding topological information of the road network improves the process of learning traffic features. We use a graph of a vehicular road network with recurrent neural networks (RNNs) to infer the interaction between adjacent road segments as well as the temporal dynamics. The topology of the road network is converted into a spatio-temporal graph to form a structural RNN (SRNN). The proposed approach is validated over traffic speed data from the road network of the city of Santander in Spain. The experiment shows that the graph-based method outperforms the state-of-the-art methods based on spatio-temporal images, requiring much fewer parameters to train.

up
0 users have voted: