An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network
Traffic flow prediction is an important part of intelligent transportation systems. In recent years, most methods have considered only the feature relationships of spatial dimensions of traffic flow data, and ignored the feature fusion of spatial and temporal aspects. Traffic flow has the features o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/14/7010 |
| _version_ | 1797407676819308544 |
|---|---|
| author | Xing Xu Hao Mao Yun Zhao Xiaoshu Lü |
| author_facet | Xing Xu Hao Mao Yun Zhao Xiaoshu Lü |
| author_sort | Xing Xu |
| collection | DOAJ |
| description | Traffic flow prediction is an important part of intelligent transportation systems. In recent years, most methods have considered only the feature relationships of spatial dimensions of traffic flow data, and ignored the feature fusion of spatial and temporal aspects. Traffic flow has the features of periodicity, nonlinearity and complexity. There are many relatively isolated points in the nodes of traffic flow, resulting in the features usually being accompanied by high-frequency noise. The previous methods directly used the graph convolution network for feature extraction. A polynomial approximation graph convolution network is essentially a convolution operation to enhance the weight of high-frequency signals, which lead to excessive high-frequency noise and reduce prediction accuracy to a certain extent. In this paper, a deep learning framework is proposed for a causal gated low-pass graph convolution neural network (CGLGCN) for traffic flow prediction. The full convolution structure adopted by the causal convolution gated linear unit (C-GLU) extracts the time features of traffic flow to avoid the problem of long running time associated with recursive networks. The reduction of running parameters and running time greatly improved the efficiency of the model. The new graph convolution neural network with self-designed low-pass filter was able to extract spatial features, enhance the weight of low-frequency signal features, suppress the influence of high-frequency noise, extract the spatial features of each node more comprehensively, and improve the prediction accuracy of the framework. Several experiments were carried out on two real-world real data sets. Compared with the existing models, our model achieved better results for short-term and long-term prediction. |
| first_indexed | 2024-03-09T03:46:02Z |
| format | Article |
| id | doaj.art-f9cfc766c3a442c9a7871af56dd5f811 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T03:46:02Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f9cfc766c3a442c9a7871af56dd5f8112023-12-03T14:35:49ZengMDPI AGApplied Sciences2076-34172022-07-011214701010.3390/app12147010An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution NetworkXing Xu0Hao Mao1Yun Zhao2Xiaoshu Lü3School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Mechanical and Energy Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaDepartment of Electrical Engineering and Energy Technology, University of Vaasa, 65380 Vaasa, FinlandTraffic flow prediction is an important part of intelligent transportation systems. In recent years, most methods have considered only the feature relationships of spatial dimensions of traffic flow data, and ignored the feature fusion of spatial and temporal aspects. Traffic flow has the features of periodicity, nonlinearity and complexity. There are many relatively isolated points in the nodes of traffic flow, resulting in the features usually being accompanied by high-frequency noise. The previous methods directly used the graph convolution network for feature extraction. A polynomial approximation graph convolution network is essentially a convolution operation to enhance the weight of high-frequency signals, which lead to excessive high-frequency noise and reduce prediction accuracy to a certain extent. In this paper, a deep learning framework is proposed for a causal gated low-pass graph convolution neural network (CGLGCN) for traffic flow prediction. The full convolution structure adopted by the causal convolution gated linear unit (C-GLU) extracts the time features of traffic flow to avoid the problem of long running time associated with recursive networks. The reduction of running parameters and running time greatly improved the efficiency of the model. The new graph convolution neural network with self-designed low-pass filter was able to extract spatial features, enhance the weight of low-frequency signal features, suppress the influence of high-frequency noise, extract the spatial features of each node more comprehensively, and improve the prediction accuracy of the framework. Several experiments were carried out on two real-world real data sets. Compared with the existing models, our model achieved better results for short-term and long-term prediction.https://www.mdpi.com/2076-3417/12/14/7010traffic flow forecastinggraph convolution networkdeep learningsmart city |
| spellingShingle | Xing Xu Hao Mao Yun Zhao Xiaoshu Lü An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network Applied Sciences traffic flow forecasting graph convolution network deep learning smart city |
| title | An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network |
| title_full | An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network |
| title_fullStr | An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network |
| title_full_unstemmed | An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network |
| title_short | An Urban Traffic Flow Fusion Network Based on a Causal Spatiotemporal Graph Convolution Network |
| title_sort | urban traffic flow fusion network based on a causal spatiotemporal graph convolution network |
| topic | traffic flow forecasting graph convolution network deep learning smart city |
| url | https://www.mdpi.com/2076-3417/12/14/7010 |
| work_keys_str_mv | AT xingxu anurbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT haomao anurbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT yunzhao anurbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT xiaoshulu anurbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT xingxu urbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT haomao urbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT yunzhao urbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork AT xiaoshulu urbantrafficflowfusionnetworkbasedonacausalspatiotemporalgraphconvolutionnetwork |