Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting
Accurate urban travel demand forecasting can help organize traffic flow, improve traffic utilization, reduce passenger waiting time, etc. It plays an important role in intelligent transportation systems. Most of the existing research methods construct static graphs from a single perspective or two p...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/16/2620 |
| _version_ | 1797410553397772288 |
|---|---|
| author | Zhi Liu Jixin Bian Deju Zhang Yang Chen Guojiang Shen Xiangjie Kong |
| author_facet | Zhi Liu Jixin Bian Deju Zhang Yang Chen Guojiang Shen Xiangjie Kong |
| author_sort | Zhi Liu |
| collection | DOAJ |
| description | Accurate urban travel demand forecasting can help organize traffic flow, improve traffic utilization, reduce passenger waiting time, etc. It plays an important role in intelligent transportation systems. Most of the existing research methods construct static graphs from a single perspective or two perspectives, without considering the dynamic impact of time changes and various factors on traffic demand. Moreover, travel demand is also affected by regional functions such as weather, etc. To address these issues, we propose an urban travel demand prediction framework based on dynamic multi-view coupled graph convolution (DMV-GCN). Specifically, we dynamically construct demand similarity graphs based on node features to model the dynamic correlation of demand. Then we combine it with the predefined geographic similarity graph, functional similarity graph, and road similarity graph. We use coupled graph convolution network and gated recurrent units (GRU), to model the spatio-temporal correlation in traffic. We conduct extensive experiments over two large real-world datasets. The results verify the superior performance of our proposed approach for the urban travel demand forecasting task. |
| first_indexed | 2024-03-09T04:31:42Z |
| format | Article |
| id | doaj.art-4efa2cf929f241d18540fb00f91090b8 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T04:31:42Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-4efa2cf929f241d18540fb00f91090b82023-12-03T13:34:42ZengMDPI AGElectronics2079-92922022-08-011116262010.3390/electronics11162620Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand ForecastingZhi Liu0Jixin Bian1Deju Zhang2Yang Chen3Guojiang Shen4Xiangjie Kong5College of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaCollege of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, ChinaAccurate urban travel demand forecasting can help organize traffic flow, improve traffic utilization, reduce passenger waiting time, etc. It plays an important role in intelligent transportation systems. Most of the existing research methods construct static graphs from a single perspective or two perspectives, without considering the dynamic impact of time changes and various factors on traffic demand. Moreover, travel demand is also affected by regional functions such as weather, etc. To address these issues, we propose an urban travel demand prediction framework based on dynamic multi-view coupled graph convolution (DMV-GCN). Specifically, we dynamically construct demand similarity graphs based on node features to model the dynamic correlation of demand. Then we combine it with the predefined geographic similarity graph, functional similarity graph, and road similarity graph. We use coupled graph convolution network and gated recurrent units (GRU), to model the spatio-temporal correlation in traffic. We conduct extensive experiments over two large real-world datasets. The results verify the superior performance of our proposed approach for the urban travel demand forecasting task.https://www.mdpi.com/2079-9292/11/16/2620urban travel demand predictioncoupled graph convolutional networkspatio-temporal datamulti-view fusion |
| spellingShingle | Zhi Liu Jixin Bian Deju Zhang Yang Chen Guojiang Shen Xiangjie Kong Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting Electronics urban travel demand prediction coupled graph convolutional network spatio-temporal data multi-view fusion |
| title | Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting |
| title_full | Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting |
| title_fullStr | Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting |
| title_full_unstemmed | Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting |
| title_short | Dynamic Multi-View Coupled Graph Convolution Network for Urban Travel Demand Forecasting |
| title_sort | dynamic multi view coupled graph convolution network for urban travel demand forecasting |
| topic | urban travel demand prediction coupled graph convolutional network spatio-temporal data multi-view fusion |
| url | https://www.mdpi.com/2079-9292/11/16/2620 |
| work_keys_str_mv | AT zhiliu dynamicmultiviewcoupledgraphconvolutionnetworkforurbantraveldemandforecasting AT jixinbian dynamicmultiviewcoupledgraphconvolutionnetworkforurbantraveldemandforecasting AT dejuzhang dynamicmultiviewcoupledgraphconvolutionnetworkforurbantraveldemandforecasting AT yangchen dynamicmultiviewcoupledgraphconvolutionnetworkforurbantraveldemandforecasting AT guojiangshen dynamicmultiviewcoupledgraphconvolutionnetworkforurbantraveldemandforecasting AT xiangjiekong dynamicmultiviewcoupledgraphconvolutionnetworkforurbantraveldemandforecasting |