Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks
Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation me...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/17/7/1501 |
| _version_ | 1817988279825334272 |
|---|---|
| author | Haiyang Yu Zhihai Wu Shuqin Wang Yunpeng Wang Xiaolei Ma |
| author_facet | Haiyang Yu Zhihai Wu Shuqin Wang Yunpeng Wang Xiaolei Ma |
| author_sort | Haiyang Yu |
| collection | DOAJ |
| description | Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. |
| first_indexed | 2024-04-14T00:32:20Z |
| format | Article |
| id | doaj.art-8ea856f1d64b46bdb6bd888f24fd71d9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T00:32:20Z |
| publishDate | 2017-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8ea856f1d64b46bdb6bd888f24fd71d92022-12-22T02:22:30ZengMDPI AGSensors1424-82202017-06-01177150110.3390/s17071501s17071501Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation NetworksHaiyang Yu0Zhihai Wu1Shuqin Wang2Yunpeng Wang3Xiaolei Ma4School of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control, Beihang University, Beijing 100191, ChinaSchool of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control, Beihang University, Beijing 100191, ChinaPassenger Vehicle EE Development Department, China FAW R&D Center, Changchun 130011, ChinaSchool of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control, Beihang University, Beijing 100191, ChinaSchool of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure System and Safety Control, Beihang University, Beijing 100191, ChinaPredicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.http://www.mdpi.com/1424-8220/17/7/1501traffic predictionconvolutional neural networklong short-term memoryspatiotemporal featurenetwork representation |
| spellingShingle | Haiyang Yu Zhihai Wu Shuqin Wang Yunpeng Wang Xiaolei Ma Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks Sensors traffic prediction convolutional neural network long short-term memory spatiotemporal feature network representation |
| title | Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks |
| title_full | Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks |
| title_fullStr | Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks |
| title_full_unstemmed | Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks |
| title_short | Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks |
| title_sort | spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks |
| topic | traffic prediction convolutional neural network long short-term memory spatiotemporal feature network representation |
| url | http://www.mdpi.com/1424-8220/17/7/1501 |
| work_keys_str_mv | AT haiyangyu spatiotemporalrecurrentconvolutionalnetworksfortrafficpredictionintransportationnetworks AT zhihaiwu spatiotemporalrecurrentconvolutionalnetworksfortrafficpredictionintransportationnetworks AT shuqinwang spatiotemporalrecurrentconvolutionalnetworksfortrafficpredictionintransportationnetworks AT yunpengwang spatiotemporalrecurrentconvolutionalnetworksfortrafficpredictionintransportationnetworks AT xiaoleima spatiotemporalrecurrentconvolutionalnetworksfortrafficpredictionintransportationnetworks |