File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Time-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network

TitleTime-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network
Authors
KeywordsBike sharing planning
Demand prediction
Graph neural networks
Memory networks
Multi-task learning
Issue Date1-Jun-2024
PublisherElsevier
Citation
Information Fusion, 2024, v. 106 How to Cite?
Abstract

Due to its various social and environmental benefits, bike sharing has been gaining popularity worldwide and, in response, many cities have gradually expanded their bike sharing systems (BSSs). For a growing station-based BSS, it is essential to plan new stations based on existing ones, which requires predicting not only the overall trip intensity at each station but also its temporal distribution, an issue underexplored in the literature. To this end, this study investigates the problem of time-dependent trip generation for BSS planning (TTGP), which aims to forecast the number of trips generated by new stations at different time periods. This task, however, is challenging due to the lack of historical data for newly planned stations and complex spatiotemporal dependencies in bike sharing demand. To address these challenges, we propose a multi-task memory-augmented graph neural network for TTGP by leveraging its surrounding urban contexts and the historical demand features of nearby existing stations. Specifically, a feature extractor is developed, consisting of a graph neural network and a memory network to encode urban context and historical demand features, respectively, and a gate network to learn the reliability of different features. Furthermore, a multi-task demand predictor is designed to predict the daily trip intensity and its hourly distribution as two distinct tasks. Finally, extensive experiments on real-world data from New York City demonstrate the superior performance of our method compared with existing baselines.


Persistent Identifierhttp://hdl.handle.net/10722/340234
ISSN
2023 Impact Factor: 14.7
2023 SCImago Journal Rankings: 5.647
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLiang, Yuebing-
dc.contributor.authorZhao, Zhan-
dc.contributor.authorDing, Fangyi-
dc.contributor.authorTang, Yihong-
dc.contributor.authorHe, Zhengbing-
dc.date.accessioned2024-03-11T10:42:40Z-
dc.date.available2024-03-11T10:42:40Z-
dc.date.issued2024-06-01-
dc.identifier.citationInformation Fusion, 2024, v. 106-
dc.identifier.issn1566-2535-
dc.identifier.urihttp://hdl.handle.net/10722/340234-
dc.description.abstract<p>Due to its various social and environmental benefits, bike sharing has been gaining popularity worldwide and, in response, many cities have gradually expanded their bike sharing systems (BSSs). For a growing station-based BSS, it is essential to plan new stations based on existing ones, which requires predicting not only the overall trip intensity at each station but also its temporal distribution, an issue underexplored in the literature. To this end, this study investigates the problem of time-dependent trip generation for BSS planning (TTGP), which aims to forecast the number of trips generated by new stations at different time periods. This task, however, is challenging due to the lack of historical data for newly planned stations and complex spatiotemporal dependencies in bike sharing demand. To address these challenges, we propose a multi-task memory-augmented graph neural network for TTGP by leveraging its surrounding urban contexts and the historical demand features of nearby existing stations. Specifically, a feature extractor is developed, consisting of a graph neural network and a memory network to encode urban context and historical demand features, respectively, and a gate network to learn the reliability of different features. Furthermore, a multi-task demand predictor is designed to predict the daily trip intensity and its hourly distribution as two distinct tasks. Finally, extensive experiments on real-world data from New York City demonstrate the superior performance of our method compared with existing baselines.</p>-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofInformation Fusion-
dc.subjectBike sharing planning-
dc.subjectDemand prediction-
dc.subjectGraph neural networks-
dc.subjectMemory networks-
dc.subjectMulti-task learning-
dc.titleTime-dependent trip generation for bike sharing planning: A multi-task memory-augmented graph neural network-
dc.typeArticle-
dc.identifier.doi10.1016/j.inffus.2024.102294-
dc.identifier.scopuseid_2-s2.0-85185311924-
dc.identifier.volume106-
dc.identifier.eissn1872-6305-
dc.identifier.isiWOS:001184550800001-
dc.identifier.issnl1566-2535-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats