Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction
Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this art...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9207934/ |
| _version_ | 1818446415560441856 |
|---|---|
| author | Ken Chen Fei Chen Baisheng Lai Zhongming Jin Yong Liu Kai Li Long Wei Pengfei Wang Yandong Tang Jianqiang Huang Xian-Sheng Hua |
| author_facet | Ken Chen Fei Chen Baisheng Lai Zhongming Jin Yong Liu Kai Li Long Wei Pengfei Wang Yandong Tang Jianqiang Huang Xian-Sheng Hua |
| author_sort | Ken Chen |
| collection | DOAJ |
| description | Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this article, we present dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatio-temporal structures and predict future traffic flows from surveillance video data. In particular, DST-GCNN is a two stream network. In the flow prediction stream, we present a novel graph-based spatio-temporal convolutional layer to extract features from a graph representation of traffic flows. Then several such layers are stacked together to predict future flows over time. Meanwhile, the relations between traffic flows in the graph are often time variant as the traffic condition changes over time. To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream. Experiments on real datasets demonstrate that the proposed model achieves competitive performances compared with the other state-of-the-art methods. |
| first_indexed | 2024-12-14T19:47:22Z |
| format | Article |
| id | doaj.art-7483b45facbb4bb8ac8f9cb5a511b94c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T19:47:22Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-7483b45facbb4bb8ac8f9cb5a511b94c2022-12-21T22:49:31ZengIEEEIEEE Access2169-35362020-01-01818513618514510.1109/ACCESS.2020.30273759207934Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow PredictionKen Chen0https://orcid.org/0000-0003-2569-0071Fei Chen1https://orcid.org/0000-0001-6076-5353Baisheng Lai2https://orcid.org/0000-0001-8939-041XZhongming Jin3https://orcid.org/0000-0002-2341-2978Yong Liu4https://orcid.org/0000-0002-5162-3211Kai Li5https://orcid.org/0000-0002-0106-0617Long Wei6https://orcid.org/0000-0003-4021-1083Pengfei Wang7https://orcid.org/0000-0003-1075-0684Yandong Tang8https://orcid.org/0000-0001-6306-0033Jianqiang Huang9https://orcid.org/0000-0001-5735-2910Xian-Sheng Hua10https://orcid.org/0000-0002-8232-5049Sichuan Highway Transportation and Communication Project Company Ltd., Chengdu, ChinaSichuan Highway Transportation and Communication Project Company Ltd., Chengdu, ChinaAlibaba Damo Academy, Alibaba Group, Hangzhou, ChinaAlibaba Damo Academy, Alibaba Group, Hangzhou, ChinaAlibaba Cloud, Alibaba Group, Hangzhou, ChinaSichuan Highway Transportation and Communication Project Company Ltd., Chengdu, ChinaSichuan Highway Transportation and Communication Project Company Ltd., Chengdu, ChinaAlibaba Damo Academy, Alibaba Group, Hangzhou, ChinaSichuan Highway Transportation and Communication Project Company Ltd., Chengdu, ChinaAlibaba Damo Academy, Alibaba Group, Hangzhou, ChinaAlibaba Damo Academy, Alibaba Group, Hangzhou, ChinaForecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this article, we present dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatio-temporal structures and predict future traffic flows from surveillance video data. In particular, DST-GCNN is a two stream network. In the flow prediction stream, we present a novel graph-based spatio-temporal convolutional layer to extract features from a graph representation of traffic flows. Then several such layers are stacked together to predict future flows over time. Meanwhile, the relations between traffic flows in the graph are often time variant as the traffic condition changes over time. To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream. Experiments on real datasets demonstrate that the proposed model achieves competitive performances compared with the other state-of-the-art methods.https://ieeexplore.ieee.org/document/9207934/Graph neural networksspatio-temporal graphconvolutional neural networktraffic forecastingtime series regression |
| spellingShingle | Ken Chen Fei Chen Baisheng Lai Zhongming Jin Yong Liu Kai Li Long Wei Pengfei Wang Yandong Tang Jianqiang Huang Xian-Sheng Hua Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction IEEE Access Graph neural networks spatio-temporal graph convolutional neural network traffic forecasting time series regression |
| title | Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction |
| title_full | Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction |
| title_fullStr | Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction |
| title_full_unstemmed | Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction |
| title_short | Dynamic Spatio-Temporal Graph-Based CNNs for Traffic Flow Prediction |
| title_sort | dynamic spatio temporal graph based cnns for traffic flow prediction |
| topic | Graph neural networks spatio-temporal graph convolutional neural network traffic forecasting time series regression |
| url | https://ieeexplore.ieee.org/document/9207934/ |
| work_keys_str_mv | AT kenchen dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT feichen dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT baishenglai dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT zhongmingjin dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT yongliu dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT kaili dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT longwei dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT pengfeiwang dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT yandongtang dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT jianqianghuang dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction AT xianshenghua dynamicspatiotemporalgraphbasedcnnsfortrafficflowprediction |