A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data
| dc.contributor.author | Bogaerts, Toon | |
| dc.contributor.author | Masegosa Arredondo, Antonio David | |
| dc.contributor.author | Angarita Zapata, Juan S. | |
| dc.contributor.author | Onieva Caracuel, Enrique | |
| dc.contributor.author | Hellinckx, Peter | |
| dc.date.accessioned | 2024-11-22T07:35:37Z | |
| dc.date.available | 2024-11-22T07:35:37Z | |
| dc.date.issued | 2020-03 | |
| dc.date.updated | 2024-11-22T07:35:37Z | |
| dc.description.abstract | Traffic forecasting is an important research area in Intelligent Transportation Systems that is focused on anticipating traffic in order to mitigate congestion. In this work we propose a deep neural network that simultaneously extracts the spatial features of traffic, using graph convolution, and its temporal features by means of Long Short Term Memory (LSTM) cells to make both short-term and long-term predictions. The model is trained and tested using sparse trajectory (GPS) data coming from the ride-hailing service of DiDi in the cities of Xi'an and Chengdu in China. Besides, presenting the deep neural network, we also propose a data-reduction technique based on temporal correlation to select the most relevant road links to be used as input. Combining the suggested approaches, our model obtains better results compared to high-performance algorithms for traffic forecasting, such as LSTM or the algorithms presented in the TRANSFOR19 forecasting competition. The model is capable of maintaining its performance over different time-horizons from 5 min to up to 4 h with multi-step predictions. | en |
| dc.description.sponsorship | This work was supported in part by the LOGISTAR and MOMENTUM projects, funded by the European Union Horizon 2020 Research and Innovation Programme grant agreements No. 769142 and No. 815069, respectively, and in part by the Marie Sklodoska-Curie Agreement 665959. | en |
| dc.identifier.citation | Bogaerts, T., Masegosa, A. D., Angarita-Zapata, J. S., Onieva, E., & Hellinckx, P. (2020). A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data. Transportation Research Part C: Emerging Technologies, 112, 62-77. https://doi.org/10.1016/J.TRC.2020.01.010 | |
| dc.identifier.doi | 10.1016/J.TRC.2020.01.010 | |
| dc.identifier.issn | 0968-090X | |
| dc.identifier.uri | http://hdl.handle.net/20.500.14454/2069 | |
| dc.language.iso | eng | |
| dc.publisher | Elsevier Ltd | |
| dc.subject.other | Deep learning | |
| dc.subject.other | GPS data | |
| dc.subject.other | Graph convolutional network | |
| dc.subject.other | ITS | |
| dc.subject.other | Long term | |
| dc.subject.other | LSTM | |
| dc.subject.other | Short term | |
| dc.subject.other | Traffic forecasting | |
| dc.subject.other | Trajectory data | |
| dc.title | A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data | en |
| dc.type | journal article | |
| dcterms.accessRights | metadata only access | |
| oaire.citation.endPage | 77 | |
| oaire.citation.startPage | 62 | |
| oaire.citation.title | Transportation Research Part C: Emerging Technologies | |
| oaire.citation.volume | 112 |