A Two-Stream Graph Convolutional Neural Network for Dynamic Traffic Flow Forecasting
Paper
Paper/Presentation Title | A Two-Stream Graph Convolutional Neural Network for Dynamic Traffic Flow Forecasting |
---|---|
Presentation Type | Paper |
Authors | Li, Zhaoyang (Author), Li, Lin (Author), Peng, Yuquan (Author) and Tao, Xiaohui (Author) |
Editors | Alamaniotis, Miltos and Pan, Shimei |
Journal or Proceedings Title | Proceedings of the 32nd IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2020) |
ERA Conference ID | 43564 |
Number of Pages | 8 |
Year | 2020 |
Place of Publication | Piscataway, United States |
ISBN | 9781728185361 |
9781728192284 | |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICTAI50040.2020.00063 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/9288187 |
Conference/Event | 32nd IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2020) |
International Conference on Tools with Artificial Intelligence | |
Event Details | International Conference on Tools with Artificial Intelligence ICTAI Rank B B B B B B B B B B B B B B B B B |
Event Details | 32nd IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2020) Event Date 09 to end of 11 Nov 2020 Event Location Baltimore, United States |
Abstract | Forecasting the traffic flow is a critical issue for researchers and practitioners in the field of transportation. Using the graph convolutional network (GCN) is widespread in traffic flow forecasting. Existing GCN-based methods mostly rely on undirected spatial correlations to represent the features of spatial-temporal graph. What's more, the traffic flow renders two types of spatial correlations, including the stable correlation constrained by the fixed road structure and the dynamic correlation influenced by the traffic fluctuation. In this paper, we propose a two-stream graph convolutional network by considering stable and dynamic correlations in parallel, which is an end-to-end deep learning framework for dynamic traffic forecasting. We present an auto-decomposing layer to decompose real-time traffic flow data into a stable component and a dynamic component with different spatial correlations. Specifically, the stable component is constrained by the physical road network, and the dynamic component represents fluctuations caused by changes in traffic conditions such as congestion and bad weather. Moreover, we extract stable and dynamic spatial correlations through our two-stream graph convolutional layer. Finally, we use parameterized skip connection to fuse spatial-temporal correlations as the input of output layer for forecasting. Extensive experiments are conducted on two real-world traffic datasets, and experimental results show that our proposed model is better than several popular baselines. |
Keywords | GCN; spatial-Temporal correlation; traffic flow forecasting |
ANZSRC Field of Research 2020 | 460207. Modelling and simulation |
460502. Data mining and knowledge discovery | |
460308. Pattern recognition | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Wuhan University of Technology, China |
School of Sciences | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q6z66/a-two-stream-graph-convolutional-neural-network-for-dynamic-traffic-flow-forecasting
93
total views6
total downloads4
views this month0
downloads this month