Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network
Online car-hailing has brought convenience to daily travel, whose accurate prediction benefits drivers and helps managers to grasp the characteristics of urban travel, so as to facilitate decisions. Spatiotemporal prediction in the transportation field has usually been based on a recurrent neural ne...
Gespeichert in:
| Veröffentlicht in: | Sustainability 2022-10, Vol.14 (20), p.13568 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 20 |
| container_start_page | 13568 |
| container_title | Sustainability |
| container_volume | 14 |
| creator | Bi, Shuoben Yuan, Cong Liu, Shaoli Wang, Luye Zhang, Lili |
| description | Online car-hailing has brought convenience to daily travel, whose accurate prediction benefits drivers and helps managers to grasp the characteristics of urban travel, so as to facilitate decisions. Spatiotemporal prediction in the transportation field has usually been based on a recurrent neural network (RNN), which has problems such as lengthy computation and backpropagation. This paper describes a model based on a Transformer, which has shown success in computer vision. The study area is divided into grids, and the structure of travel data is converted into video frames by time period, based on predicted spatiotemporal travel demand. The predictions of the model are closest to the real data in terms of spatial distribution and travel demand when the data are divided into 10 min intervals, and the travel demand in the first two hours is used to predict demand in the next hour. We experimentally compare the proposed model with the three most commonly used spatiotemporal prediction models, and the results show that our model has the best accuracy and training speed. |
| doi_str_mv | 10.3390/su142013568 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2728547539</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A747158822</galeid><sourcerecordid>A747158822</sourcerecordid><originalsourceid>FETCH-LOGICAL-c371t-57acfa6312583d0aad5253eec0a8acc037c3a9ca2cc7c9017c3d01f9b001c15a3</originalsourceid><addsrcrecordid>eNpVkU1PwkAQhhujiQQ5-Qc28WRMcT9Ytj0ifkBCxAic67CdkmK7i7utH__eNXiAmcPMvHnemcNE0SWjfSFSeutbNuCUCTlMTqIOp4rFjEp6etCfRz3vtzSEECxlw070tthBU9oG6511UJEXh3mpg2KILcjKrcGQualKg2QMLp5AGfoNWTr4xIrcYw0mJ3fgMSfBEmTjC-tqdOQZmy_r3i-iswIqj73_2o1Wjw_L8SSezZ-m49Es1kKxJpYKdAFDwbhMRE4BcsmlQNQUEtCaCqUFpBq41kqnlIUxp6xI15QyzSSIbnS137tz9qNF32Rb2zoTTmZc8UQOlBRpoPp7agMVZqUpbONAh8yxLrU1WJRBH6mBYjJJOA-G6yNDYBr8bjbQep9NF6_H7M2e1c5677DIdq6swf1kjGZ_L8oOXiR-Ad2jgms</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2728547539</pqid></control><display><type>article</type><title>Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Bi, Shuoben ; Yuan, Cong ; Liu, Shaoli ; Wang, Luye ; Zhang, Lili</creator><creatorcontrib>Bi, Shuoben ; Yuan, Cong ; Liu, Shaoli ; Wang, Luye ; Zhang, Lili</creatorcontrib><description>Online car-hailing has brought convenience to daily travel, whose accurate prediction benefits drivers and helps managers to grasp the characteristics of urban travel, so as to facilitate decisions. Spatiotemporal prediction in the transportation field has usually been based on a recurrent neural network (RNN), which has problems such as lengthy computation and backpropagation. This paper describes a model based on a Transformer, which has shown success in computer vision. The study area is divided into grids, and the structure of travel data is converted into video frames by time period, based on predicted spatiotemporal travel demand. The predictions of the model are closest to the real data in terms of spatial distribution and travel demand when the data are divided into 10 min intervals, and the travel demand in the first two hours is used to predict demand in the next hour. We experimentally compare the proposed model with the three most commonly used spatiotemporal prediction models, and the results show that our model has the best accuracy and training speed.</description><identifier>ISSN: 2071-1050</identifier><identifier>EISSN: 2071-1050</identifier><identifier>DOI: 10.3390/su142013568</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Back propagation ; Back propagation networks ; Computational linguistics ; Computer vision ; Coronaviruses ; COVID-19 ; Deep learning ; Forecasts and trends ; Language processing ; Machine vision ; Natural language interfaces ; Neural networks ; Online travel services ; Prediction models ; Public transportation ; Recurrent neural networks ; Ridesharing ; Spatial distribution ; Supply and demand ; Time series ; Traffic congestion ; Traffic flow ; Transportation networks ; Transportation services ; Travel ; Travel demand ; Urban transportation</subject><ispartof>Sustainability, 2022-10, Vol.14 (20), p.13568</ispartof><rights>COPYRIGHT 2022 MDPI AG</rights><rights>2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c371t-57acfa6312583d0aad5253eec0a8acc037c3a9ca2cc7c9017c3d01f9b001c15a3</citedby><cites>FETCH-LOGICAL-c371t-57acfa6312583d0aad5253eec0a8acc037c3a9ca2cc7c9017c3d01f9b001c15a3</cites><orcidid>0000-0002-7295-1716</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Bi, Shuoben</creatorcontrib><creatorcontrib>Yuan, Cong</creatorcontrib><creatorcontrib>Liu, Shaoli</creatorcontrib><creatorcontrib>Wang, Luye</creatorcontrib><creatorcontrib>Zhang, Lili</creatorcontrib><title>Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network</title><title>Sustainability</title><description>Online car-hailing has brought convenience to daily travel, whose accurate prediction benefits drivers and helps managers to grasp the characteristics of urban travel, so as to facilitate decisions. Spatiotemporal prediction in the transportation field has usually been based on a recurrent neural network (RNN), which has problems such as lengthy computation and backpropagation. This paper describes a model based on a Transformer, which has shown success in computer vision. The study area is divided into grids, and the structure of travel data is converted into video frames by time period, based on predicted spatiotemporal travel demand. The predictions of the model are closest to the real data in terms of spatial distribution and travel demand when the data are divided into 10 min intervals, and the travel demand in the first two hours is used to predict demand in the next hour. We experimentally compare the proposed model with the three most commonly used spatiotemporal prediction models, and the results show that our model has the best accuracy and training speed.</description><subject>Accuracy</subject><subject>Back propagation</subject><subject>Back propagation networks</subject><subject>Computational linguistics</subject><subject>Computer vision</subject><subject>Coronaviruses</subject><subject>COVID-19</subject><subject>Deep learning</subject><subject>Forecasts and trends</subject><subject>Language processing</subject><subject>Machine vision</subject><subject>Natural language interfaces</subject><subject>Neural networks</subject><subject>Online travel services</subject><subject>Prediction models</subject><subject>Public transportation</subject><subject>Recurrent neural networks</subject><subject>Ridesharing</subject><subject>Spatial distribution</subject><subject>Supply and demand</subject><subject>Time series</subject><subject>Traffic congestion</subject><subject>Traffic flow</subject><subject>Transportation networks</subject><subject>Transportation services</subject><subject>Travel</subject><subject>Travel demand</subject><subject>Urban transportation</subject><issn>2071-1050</issn><issn>2071-1050</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpVkU1PwkAQhhujiQQ5-Qc28WRMcT9Ytj0ifkBCxAic67CdkmK7i7utH__eNXiAmcPMvHnemcNE0SWjfSFSeutbNuCUCTlMTqIOp4rFjEp6etCfRz3vtzSEECxlw070tthBU9oG6511UJEXh3mpg2KILcjKrcGQualKg2QMLp5AGfoNWTr4xIrcYw0mJ3fgMSfBEmTjC-tqdOQZmy_r3i-iswIqj73_2o1Wjw_L8SSezZ-m49Es1kKxJpYKdAFDwbhMRE4BcsmlQNQUEtCaCqUFpBq41kqnlIUxp6xI15QyzSSIbnS137tz9qNF32Rb2zoTTmZc8UQOlBRpoPp7agMVZqUpbONAh8yxLrU1WJRBH6mBYjJJOA-G6yNDYBr8bjbQep9NF6_H7M2e1c5677DIdq6swf1kjGZ_L8oOXiR-Ad2jgms</recordid><startdate>20221001</startdate><enddate>20221001</enddate><creator>Bi, Shuoben</creator><creator>Yuan, Cong</creator><creator>Liu, Shaoli</creator><creator>Wang, Luye</creator><creator>Zhang, Lili</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>4U-</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><orcidid>https://orcid.org/0000-0002-7295-1716</orcidid></search><sort><creationdate>20221001</creationdate><title>Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network</title><author>Bi, Shuoben ; Yuan, Cong ; Liu, Shaoli ; Wang, Luye ; Zhang, Lili</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c371t-57acfa6312583d0aad5253eec0a8acc037c3a9ca2cc7c9017c3d01f9b001c15a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Accuracy</topic><topic>Back propagation</topic><topic>Back propagation networks</topic><topic>Computational linguistics</topic><topic>Computer vision</topic><topic>Coronaviruses</topic><topic>COVID-19</topic><topic>Deep learning</topic><topic>Forecasts and trends</topic><topic>Language processing</topic><topic>Machine vision</topic><topic>Natural language interfaces</topic><topic>Neural networks</topic><topic>Online travel services</topic><topic>Prediction models</topic><topic>Public transportation</topic><topic>Recurrent neural networks</topic><topic>Ridesharing</topic><topic>Spatial distribution</topic><topic>Supply and demand</topic><topic>Time series</topic><topic>Traffic congestion</topic><topic>Traffic flow</topic><topic>Transportation networks</topic><topic>Transportation services</topic><topic>Travel</topic><topic>Travel demand</topic><topic>Urban transportation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bi, Shuoben</creatorcontrib><creatorcontrib>Yuan, Cong</creatorcontrib><creatorcontrib>Liu, Shaoli</creatorcontrib><creatorcontrib>Wang, Luye</creatorcontrib><creatorcontrib>Zhang, Lili</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>University Readers</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central Korea</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Sustainability</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bi, Shuoben</au><au>Yuan, Cong</au><au>Liu, Shaoli</au><au>Wang, Luye</au><au>Zhang, Lili</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network</atitle><jtitle>Sustainability</jtitle><date>2022-10-01</date><risdate>2022</risdate><volume>14</volume><issue>20</issue><spage>13568</spage><pages>13568-</pages><issn>2071-1050</issn><eissn>2071-1050</eissn><abstract>Online car-hailing has brought convenience to daily travel, whose accurate prediction benefits drivers and helps managers to grasp the characteristics of urban travel, so as to facilitate decisions. Spatiotemporal prediction in the transportation field has usually been based on a recurrent neural network (RNN), which has problems such as lengthy computation and backpropagation. This paper describes a model based on a Transformer, which has shown success in computer vision. The study area is divided into grids, and the structure of travel data is converted into video frames by time period, based on predicted spatiotemporal travel demand. The predictions of the model are closest to the real data in terms of spatial distribution and travel demand when the data are divided into 10 min intervals, and the travel demand in the first two hours is used to predict demand in the next hour. We experimentally compare the proposed model with the three most commonly used spatiotemporal prediction models, and the results show that our model has the best accuracy and training speed.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/su142013568</doi><orcidid>https://orcid.org/0000-0002-7295-1716</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2071-1050 |
| ispartof | Sustainability, 2022-10, Vol.14 (20), p.13568 |
| issn | 2071-1050 2071-1050 |
| language | eng |
| recordid | cdi_proquest_journals_2728547539 |
| source | MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Accuracy Back propagation Back propagation networks Computational linguistics Computer vision Coronaviruses COVID-19 Deep learning Forecasts and trends Language processing Machine vision Natural language interfaces Neural networks Online travel services Prediction models Public transportation Recurrent neural networks Ridesharing Spatial distribution Supply and demand Time series Traffic congestion Traffic flow Transportation networks Transportation services Travel Travel demand Urban transportation |
| title | Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T14%3A48%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Spatiotemporal%20Prediction%20of%20Urban%20Online%20Car-Hailing%20Travel%20Demand%20Based%20on%20Transformer%20Network&rft.jtitle=Sustainability&rft.au=Bi,%20Shuoben&rft.date=2022-10-01&rft.volume=14&rft.issue=20&rft.spage=13568&rft.pages=13568-&rft.issn=2071-1050&rft.eissn=2071-1050&rft_id=info:doi/10.3390/su142013568&rft_dat=%3Cgale_proqu%3EA747158822%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2728547539&rft_id=info:pmid/&rft_galeid=A747158822&rfr_iscdi=true |