A data-driven approach to characterize the impact of connected and autonomous vehicles on traffic flow

This study presents a model to characterize changes in network traffic flows as a result of implementing connected and autonomous vehicle (CAV) technology based on traffic network and built-environment characteristics. To develop such a model, first, the POLARIS agent-based modeling platform is used...

Full description

Saved in:
Bibliographic Details
Published in:Transportation letters 2021-11, Vol.13 (10), p.687-695
Main Authors: Parsa, Amir Bahador, Shabanpour, Ramin, Mohammadian, Abolfazl (Kouros), Auld, Joshua, Stephens, Thomas
Format: Article
Language:English
Subjects:
Connected and autonomous vehicles
machine learning
POLARIS
traffic flow
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393
cites cdi_FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393
container_end_page 695
container_issue 10
container_start_page 687
container_title Transportation letters
container_volume 13
creator Parsa, Amir Bahador
Shabanpour, Ramin
Mohammadian, Abolfazl (Kouros)
Auld, Joshua
Stephens, Thomas
description This study presents a model to characterize changes in network traffic flows as a result of implementing connected and autonomous vehicle (CAV) technology based on traffic network and built-environment characteristics. To develop such a model, first, the POLARIS agent-based modeling platform is used to predict changes in average daily traffic (ADT) under CAV scenario in the road network of Chicago metropolitan area as the dependent variable of the model. Second, a comprehensive set of variables and indicators representing network characteristics and urban structure patterns are generated. Finally, three machine learning techniques, namely, K-Nearest neighbors, Random Forest, and eXtreme Gradient Boosting, are used to characterize changes in ADT based on network characteristics under a CAV scenario. The estimated models are validated and are found to yield acceptable performance. In addition, SHapley Additive exPlanations (SHAP) analysis tool is employed to investigate the impact of important features on changes in ADT.
doi_str_mv 10.1080/19427867.2020.1776956
format article
fullrecord <record><control><sourceid>crossref_infor</sourceid><recordid>TN_cdi_crossref_primary_10_1080_19427867_2020_1776956</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1080_19427867_2020_1776956</sourcerecordid><originalsourceid>FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393</originalsourceid><addsrcrecordid>eNp9kM1qwzAQhEVpoWnaRyjoBZzKv5JuDaF_EOgldyGvtVjFloKkJKRPX4ekPfaw7M4sM4ePkMecLXIm2FMuq4KLhi8KVkwW542smysyO_kZF7y-_rsbfkvuYvxirGkEy2cEl7TTSWddsHvjqN5ug9fQ0-Qp9DpoSCbYb0NTb6gdt5OmHil458z06qh20-ySd370u0j3prcwmEi9oyloRAsUB3-4Jzeoh2geLntONq8vm9V7tv58-1gt1xmUNU9ZLRlUnWwFIgoBvJJVXoLsOmEqlAxbXUpsu0qU3LTIigoACmhB5ICslOWc1OdaCD7GYFBtgx11OKqcqRMr9ctKnVipC6sp93zOWYc-jPrgw9CppI-DDxi0AxtV-X_FD7Mec28</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A data-driven approach to characterize the impact of connected and autonomous vehicles on traffic flow</title><source>Taylor and Francis:Jisc Collections:Taylor and Francis Read and Publish Agreement 2024-2025:Science and Technology Collection (Reading list)</source><creator>Parsa, Amir Bahador ; Shabanpour, Ramin ; Mohammadian, Abolfazl (Kouros) ; Auld, Joshua ; Stephens, Thomas</creator><creatorcontrib>Parsa, Amir Bahador ; Shabanpour, Ramin ; Mohammadian, Abolfazl (Kouros) ; Auld, Joshua ; Stephens, Thomas</creatorcontrib><description>This study presents a model to characterize changes in network traffic flows as a result of implementing connected and autonomous vehicle (CAV) technology based on traffic network and built-environment characteristics. To develop such a model, first, the POLARIS agent-based modeling platform is used to predict changes in average daily traffic (ADT) under CAV scenario in the road network of Chicago metropolitan area as the dependent variable of the model. Second, a comprehensive set of variables and indicators representing network characteristics and urban structure patterns are generated. Finally, three machine learning techniques, namely, K-Nearest neighbors, Random Forest, and eXtreme Gradient Boosting, are used to characterize changes in ADT based on network characteristics under a CAV scenario. The estimated models are validated and are found to yield acceptable performance. In addition, SHapley Additive exPlanations (SHAP) analysis tool is employed to investigate the impact of important features on changes in ADT.</description><identifier>ISSN: 1942-7867</identifier><identifier>EISSN: 1942-7875</identifier><identifier>DOI: 10.1080/19427867.2020.1776956</identifier><language>eng</language><publisher>Taylor &amp; Francis</publisher><subject>Connected and autonomous vehicles ; machine learning ; POLARIS ; traffic flow</subject><ispartof>Transportation letters, 2021-11, Vol.13 (10), p.687-695</ispartof><rights>2020 Informa UK Limited, trading as Taylor &amp; Francis Group 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393</citedby><cites>FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393</cites><orcidid>0000-0001-7142-0457 ; 0000-0003-3595-3664</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27903,27904</link.rule.ids></links><search><creatorcontrib>Parsa, Amir Bahador</creatorcontrib><creatorcontrib>Shabanpour, Ramin</creatorcontrib><creatorcontrib>Mohammadian, Abolfazl (Kouros)</creatorcontrib><creatorcontrib>Auld, Joshua</creatorcontrib><creatorcontrib>Stephens, Thomas</creatorcontrib><title>A data-driven approach to characterize the impact of connected and autonomous vehicles on traffic flow</title><title>Transportation letters</title><description>This study presents a model to characterize changes in network traffic flows as a result of implementing connected and autonomous vehicle (CAV) technology based on traffic network and built-environment characteristics. To develop such a model, first, the POLARIS agent-based modeling platform is used to predict changes in average daily traffic (ADT) under CAV scenario in the road network of Chicago metropolitan area as the dependent variable of the model. Second, a comprehensive set of variables and indicators representing network characteristics and urban structure patterns are generated. Finally, three machine learning techniques, namely, K-Nearest neighbors, Random Forest, and eXtreme Gradient Boosting, are used to characterize changes in ADT based on network characteristics under a CAV scenario. The estimated models are validated and are found to yield acceptable performance. In addition, SHapley Additive exPlanations (SHAP) analysis tool is employed to investigate the impact of important features on changes in ADT.</description><subject>Connected and autonomous vehicles</subject><subject>machine learning</subject><subject>POLARIS</subject><subject>traffic flow</subject><issn>1942-7867</issn><issn>1942-7875</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kM1qwzAQhEVpoWnaRyjoBZzKv5JuDaF_EOgldyGvtVjFloKkJKRPX4ekPfaw7M4sM4ePkMecLXIm2FMuq4KLhi8KVkwW542smysyO_kZF7y-_rsbfkvuYvxirGkEy2cEl7TTSWddsHvjqN5ug9fQ0-Qp9DpoSCbYb0NTb6gdt5OmHil458z06qh20-ySd370u0j3prcwmEi9oyloRAsUB3-4Jzeoh2geLntONq8vm9V7tv58-1gt1xmUNU9ZLRlUnWwFIgoBvJJVXoLsOmEqlAxbXUpsu0qU3LTIigoACmhB5ICslOWc1OdaCD7GYFBtgx11OKqcqRMr9ctKnVipC6sp93zOWYc-jPrgw9CppI-DDxi0AxtV-X_FD7Mec28</recordid><startdate>20211126</startdate><enddate>20211126</enddate><creator>Parsa, Amir Bahador</creator><creator>Shabanpour, Ramin</creator><creator>Mohammadian, Abolfazl (Kouros)</creator><creator>Auld, Joshua</creator><creator>Stephens, Thomas</creator><general>Taylor &amp; Francis</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-7142-0457</orcidid><orcidid>https://orcid.org/0000-0003-3595-3664</orcidid></search><sort><creationdate>20211126</creationdate><title>A data-driven approach to characterize the impact of connected and autonomous vehicles on traffic flow</title><author>Parsa, Amir Bahador ; Shabanpour, Ramin ; Mohammadian, Abolfazl (Kouros) ; Auld, Joshua ; Stephens, Thomas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Connected and autonomous vehicles</topic><topic>machine learning</topic><topic>POLARIS</topic><topic>traffic flow</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Parsa, Amir Bahador</creatorcontrib><creatorcontrib>Shabanpour, Ramin</creatorcontrib><creatorcontrib>Mohammadian, Abolfazl (Kouros)</creatorcontrib><creatorcontrib>Auld, Joshua</creatorcontrib><creatorcontrib>Stephens, Thomas</creatorcontrib><collection>CrossRef</collection><jtitle>Transportation letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Parsa, Amir Bahador</au><au>Shabanpour, Ramin</au><au>Mohammadian, Abolfazl (Kouros)</au><au>Auld, Joshua</au><au>Stephens, Thomas</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A data-driven approach to characterize the impact of connected and autonomous vehicles on traffic flow</atitle><jtitle>Transportation letters</jtitle><date>2021-11-26</date><risdate>2021</risdate><volume>13</volume><issue>10</issue><spage>687</spage><epage>695</epage><pages>687-695</pages><issn>1942-7867</issn><eissn>1942-7875</eissn><abstract>This study presents a model to characterize changes in network traffic flows as a result of implementing connected and autonomous vehicle (CAV) technology based on traffic network and built-environment characteristics. To develop such a model, first, the POLARIS agent-based modeling platform is used to predict changes in average daily traffic (ADT) under CAV scenario in the road network of Chicago metropolitan area as the dependent variable of the model. Second, a comprehensive set of variables and indicators representing network characteristics and urban structure patterns are generated. Finally, three machine learning techniques, namely, K-Nearest neighbors, Random Forest, and eXtreme Gradient Boosting, are used to characterize changes in ADT based on network characteristics under a CAV scenario. The estimated models are validated and are found to yield acceptable performance. In addition, SHapley Additive exPlanations (SHAP) analysis tool is employed to investigate the impact of important features on changes in ADT.</abstract><pub>Taylor &amp; Francis</pub><doi>10.1080/19427867.2020.1776956</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0001-7142-0457</orcidid><orcidid>https://orcid.org/0000-0003-3595-3664</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1942-7867
ispartof Transportation letters, 2021-11, Vol.13 (10), p.687-695
issn 1942-7867
1942-7875
language eng
recordid cdi_crossref_primary_10_1080_19427867_2020_1776956
source Taylor and Francis:Jisc Collections:Taylor and Francis Read and Publish Agreement 2024-2025:Science and Technology Collection (Reading list)
subjects Connected and autonomous vehicles
machine learning
POLARIS
traffic flow
title A data-driven approach to characterize the impact of connected and autonomous vehicles on traffic flow
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T16%3A06%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_infor&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20data-driven%20approach%20to%20characterize%20the%20impact%20of%20connected%20and%20autonomous%20vehicles%20on%20traffic%20flow&rft.jtitle=Transportation%20letters&rft.au=Parsa,%20Amir%20Bahador&rft.date=2021-11-26&rft.volume=13&rft.issue=10&rft.spage=687&rft.epage=695&rft.pages=687-695&rft.issn=1942-7867&rft.eissn=1942-7875&rft_id=info:doi/10.1080/19427867.2020.1776956&rft_dat=%3Ccrossref_infor%3E10_1080_19427867_2020_1776956%3C/crossref_infor%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c357t-590c4d9b8fff88c749413c9dd8e4f90fba39fbd4837ebf024ccc2cbc81cf0393%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true