File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TITS.2021.3117835
- Scopus: eid_2-s2.0-85124190226
- WOS: WOS:000751476700001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: A Novel STFSA-CNN-GRU Hybrid Model for Short-Term Traffic Speed Prediction
Title | A Novel STFSA-CNN-GRU Hybrid Model for Short-Term Traffic Speed Prediction |
---|---|
Authors | |
Keywords | convolutional neural network Correlation Data models deep learning model Feature extraction gated recurrent unit Intelligent transportation systems Prediction algorithms Predictive models Roads Short-term traffic speed prediction spatial-temporal analysis. |
Issue Date | 1-Apr-2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Citation | IEEE Transactions on Intelligent Transportation Systems, 2023, v. 24, n. 4, p. 3728-3737 How to Cite? |
Abstract | Short-term traffic speed prediction is fundamental to intelligent transportation systems (ITS), and the accuracy of the model largely determines the performance of real-time traffic control and management. In this study, a short-term traffic speed prediction method based on the spatial-temporal analysis of traffic flow and a combined deep-learning model, and a hybrid spatial-temporal feature selection algorithm (STFSA) of a convolutional neural network–gated recurrent unit (CNN-GRU)) is initially developed. Specifically, the STFSA is firstly employed to reconstruct the spatial-temporal matrix of traffic speed based on temporal continuity and spatial characteristics, and then this matrix is considered as the input feature of the prediction model. After this, the nonlinear fitting ability of the CNN is adopted to extract deep features from the convolutional and pooling layers for model training. Finally, by combining the timing and long-range dependence of the captured data with the forward GRU and the reverse GRU, the accuracy of the prediction result is further improved. The validity of the proposed model can be verified by comparing the prediction results with the actual traffic data. Accordingly, in the case study, the performance is compared with various benchmark methods under the same prediction scenario, verifying the superiority of the proposed model. |
Persistent Identifier | http://hdl.handle.net/10722/328479 |
ISSN | 2023 Impact Factor: 7.9 2023 SCImago Journal Rankings: 2.580 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ma, Changxi | - |
dc.contributor.author | Zhao, Yongpeng | - |
dc.contributor.author | Dai, Guowen | - |
dc.contributor.author | Xu, Xuecai | - |
dc.contributor.author | Wong, Sze Chun | - |
dc.date.accessioned | 2023-06-28T04:45:19Z | - |
dc.date.available | 2023-06-28T04:45:19Z | - |
dc.date.issued | 2023-04-01 | - |
dc.identifier.citation | IEEE Transactions on Intelligent Transportation Systems, 2023, v. 24, n. 4, p. 3728-3737 | - |
dc.identifier.issn | 1524-9050 | - |
dc.identifier.uri | http://hdl.handle.net/10722/328479 | - |
dc.description.abstract | <p>Short-term traffic speed prediction is fundamental to intelligent transportation systems (ITS), and the accuracy of the model largely determines the performance of real-time traffic control and management. In this study, a short-term traffic speed prediction method based on the spatial-temporal analysis of traffic flow and a combined deep-learning model, and a hybrid spatial-temporal feature selection algorithm (STFSA) of a convolutional neural network–gated recurrent unit (CNN-GRU)) is initially developed. Specifically, the STFSA is firstly employed to reconstruct the spatial-temporal matrix of traffic speed based on temporal continuity and spatial characteristics, and then this matrix is considered as the input feature of the prediction model. After this, the nonlinear fitting ability of the CNN is adopted to extract deep features from the convolutional and pooling layers for model training. Finally, by combining the timing and long-range dependence of the captured data with the forward GRU and the reverse GRU, the accuracy of the prediction result is further improved. The validity of the proposed model can be verified by comparing the prediction results with the actual traffic data. Accordingly, in the case study, the performance is compared with various benchmark methods under the same prediction scenario, verifying the superiority of the proposed model.<br></p> | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.relation.ispartof | IEEE Transactions on Intelligent Transportation Systems | - |
dc.subject | convolutional neural network | - |
dc.subject | Correlation | - |
dc.subject | Data models | - |
dc.subject | deep learning model | - |
dc.subject | Feature extraction | - |
dc.subject | gated recurrent unit | - |
dc.subject | Intelligent transportation systems | - |
dc.subject | Prediction algorithms | - |
dc.subject | Predictive models | - |
dc.subject | Roads | - |
dc.subject | Short-term traffic speed prediction | - |
dc.subject | spatial-temporal analysis. | - |
dc.title | A Novel STFSA-CNN-GRU Hybrid Model for Short-Term Traffic Speed Prediction | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TITS.2021.3117835 | - |
dc.identifier.scopus | eid_2-s2.0-85124190226 | - |
dc.identifier.volume | 24 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | 3728 | - |
dc.identifier.epage | 3737 | - |
dc.identifier.eissn | 1558-0016 | - |
dc.identifier.isi | WOS:000751476700001 | - |
dc.identifier.issnl | 1524-9050 | - |