Enhanced road information representation in graph recurrent network for traffic speed prediction
Abstract Correctly capturing the spatial‐temporal correlation of traffic sequences will benefit to make accurate predictions of the future traffic states. In the paper, the methods of enhancing road spatial and temporal information representation are proposed. Firstly, the parameter matrix of each r...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | IET Intelligent Transport Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/itr2.12334 |
| _version_ | 1797777611834785792 |
|---|---|
| author | Lei Chang Cheng Ma Kai Sun Zhijian Qu Chongguang Ren |
| author_facet | Lei Chang Cheng Ma Kai Sun Zhijian Qu Chongguang Ren |
| author_sort | Lei Chang |
| collection | DOAJ |
| description | Abstract Correctly capturing the spatial‐temporal correlation of traffic sequences will benefit to make accurate predictions of the future traffic states. In the paper, the methods of enhancing road spatial and temporal information representation are proposed. Firstly, the parameter matrix of each road is constructed to represent the road‐specific traffic patterns for the graph convolution neural network and the recurrent neural network. Then, the node embedding, and matrix factorization are used to reduce the scale of the parameter matrix. Secondly, the node embedding‐based Data Adaptive Graph Generation model was introduced to infer the indirect relationship of each node, and the gating mechanism is designed to control the weights of the direct spatial information and the indirect spatial information. Thirdly, to enhance the traffic sequence representation, the time tag and peak tag for the sequences are designed at each sampling moment. At last, the Enhanced Road Information Representation in Graph Recurrent Network (En‐GRN) is proposed to predict traffic speed, and the prediction performance is tested on SZ‐taxi and Los‐loop dataset. The experimental results show that the presented works are effective for improving traffic prediction accuracy. |
| first_indexed | 2024-03-12T23:06:19Z |
| format | Article |
| id | doaj.art-16046be862af4073a8c54a6b06a6cb6d |
| institution | Directory Open Access Journal |
| issn | 1751-956X 1751-9578 |
| language | English |
| last_indexed | 2024-03-12T23:06:19Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Intelligent Transport Systems |
| spelling | doaj.art-16046be862af4073a8c54a6b06a6cb6d2023-07-18T15:38:52ZengWileyIET Intelligent Transport Systems1751-956X1751-95782023-07-011771434145310.1049/itr2.12334Enhanced road information representation in graph recurrent network for traffic speed predictionLei Chang0Cheng Ma1Kai Sun2Zhijian Qu3Chongguang Ren4School of Computer Science and Technology Shandong University of Technology, Xin Cun Xi Lu Zibo Shandong ChinaSchool of Computer Science and Technology Shandong University of Technology, Xin Cun Xi Lu Zibo Shandong ChinaZibo Special Equipment Inspection Institute Zibo ChinaSchool of Computer Science and Technology Shandong University of Technology, Xin Cun Xi Lu Zibo Shandong ChinaSchool of Computer Science and Technology Shandong University of Technology, Xin Cun Xi Lu Zibo Shandong ChinaAbstract Correctly capturing the spatial‐temporal correlation of traffic sequences will benefit to make accurate predictions of the future traffic states. In the paper, the methods of enhancing road spatial and temporal information representation are proposed. Firstly, the parameter matrix of each road is constructed to represent the road‐specific traffic patterns for the graph convolution neural network and the recurrent neural network. Then, the node embedding, and matrix factorization are used to reduce the scale of the parameter matrix. Secondly, the node embedding‐based Data Adaptive Graph Generation model was introduced to infer the indirect relationship of each node, and the gating mechanism is designed to control the weights of the direct spatial information and the indirect spatial information. Thirdly, to enhance the traffic sequence representation, the time tag and peak tag for the sequences are designed at each sampling moment. At last, the Enhanced Road Information Representation in Graph Recurrent Network (En‐GRN) is proposed to predict traffic speed, and the prediction performance is tested on SZ‐taxi and Los‐loop dataset. The experimental results show that the presented works are effective for improving traffic prediction accuracy.https://doi.org/10.1049/itr2.12334management and controlneural netsrecurrent neural netsroad trafficsmart citiestime series |
| spellingShingle | Lei Chang Cheng Ma Kai Sun Zhijian Qu Chongguang Ren Enhanced road information representation in graph recurrent network for traffic speed prediction IET Intelligent Transport Systems management and control neural nets recurrent neural nets road traffic smart cities time series |
| title | Enhanced road information representation in graph recurrent network for traffic speed prediction |
| title_full | Enhanced road information representation in graph recurrent network for traffic speed prediction |
| title_fullStr | Enhanced road information representation in graph recurrent network for traffic speed prediction |
| title_full_unstemmed | Enhanced road information representation in graph recurrent network for traffic speed prediction |
| title_short | Enhanced road information representation in graph recurrent network for traffic speed prediction |
| title_sort | enhanced road information representation in graph recurrent network for traffic speed prediction |
| topic | management and control neural nets recurrent neural nets road traffic smart cities time series |
| url | https://doi.org/10.1049/itr2.12334 |
| work_keys_str_mv | AT leichang enhancedroadinformationrepresentationingraphrecurrentnetworkfortrafficspeedprediction AT chengma enhancedroadinformationrepresentationingraphrecurrentnetworkfortrafficspeedprediction AT kaisun enhancedroadinformationrepresentationingraphrecurrentnetworkfortrafficspeedprediction AT zhijianqu enhancedroadinformationrepresentationingraphrecurrentnetworkfortrafficspeedprediction AT chongguangren enhancedroadinformationrepresentationingraphrecurrentnetworkfortrafficspeedprediction |