File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Hexagon-Based Convolutional Neural Network for Supply-Demand Forecasting of Ride-Sourcing Services

TitleHexagon-Based Convolutional Neural Network for Supply-Demand Forecasting of Ride-Sourcing Services
Authors
Keywordsdeep learning (DL)
hexagon-based convolutional neural network (H-CNN)
on-demand ride service
ride-sourcing service
Short-term supply-demand forecasting
Issue Date2019
Citation
IEEE Transactions on Intelligent Transportation Systems, 2019, v. 20, n. 11, p. 4160-4173 How to Cite?
AbstractRide-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy. To capture the spatio-temporal characteristics in a hexagonal manner, we propose three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps. Moreover, a hexagon-based ensemble mechanism is developed to enhance the prediction performance. Validated by a 3-week real-world ride-sourcing dataset in Guangzhou, China, the H-CNN models are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness. Our approaches can be further extended to a broad range of spatio-temporal forecasting problems in the domain of shared mobility and urban computing.
Persistent Identifierhttp://hdl.handle.net/10722/308775
ISSN
2023 Impact Factor: 7.9
2023 SCImago Journal Rankings: 2.580
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorKe, Jintao-
dc.contributor.authorYang, Hai-
dc.contributor.authorZheng, Hongyu-
dc.contributor.authorChen, Xiqun-
dc.contributor.authorJia, Yitian-
dc.contributor.authorGong, Pinghua-
dc.contributor.authorYe, Jieping-
dc.date.accessioned2021-12-08T07:50:06Z-
dc.date.available2021-12-08T07:50:06Z-
dc.date.issued2019-
dc.identifier.citationIEEE Transactions on Intelligent Transportation Systems, 2019, v. 20, n. 11, p. 4160-4173-
dc.identifier.issn1524-9050-
dc.identifier.urihttp://hdl.handle.net/10722/308775-
dc.description.abstractRide-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy. To capture the spatio-temporal characteristics in a hexagonal manner, we propose three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps. Moreover, a hexagon-based ensemble mechanism is developed to enhance the prediction performance. Validated by a 3-week real-world ride-sourcing dataset in Guangzhou, China, the H-CNN models are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness. Our approaches can be further extended to a broad range of spatio-temporal forecasting problems in the domain of shared mobility and urban computing.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Intelligent Transportation Systems-
dc.subjectdeep learning (DL)-
dc.subjecthexagon-based convolutional neural network (H-CNN)-
dc.subjecton-demand ride service-
dc.subjectride-sourcing service-
dc.subjectShort-term supply-demand forecasting-
dc.titleHexagon-Based Convolutional Neural Network for Supply-Demand Forecasting of Ride-Sourcing Services-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TITS.2018.2882861-
dc.identifier.scopuseid_2-s2.0-85058174929-
dc.identifier.volume20-
dc.identifier.issue11-
dc.identifier.spage4160-
dc.identifier.epage4173-
dc.identifier.eissn1558-0016-
dc.identifier.isiWOS:000497800700014-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats