A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting

Traffic volume forecasting is a key objective in Intelligent Transportation Systems (ITS) since its importance for both the general public and authorities in decision making, optimizing navigation strategies and avoid traffic congestions. Various research projects have been conducted for identifying...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the XXth Conference of Open Innovations Association FRUCT 2021-01, Vol.28 (2), p.564-570
Main Authors: Bhanuka Dissanayake, Osanda Hemachandra, Nuwan Lakshitha, Dilantha Haputhanthri, Adeesha Wijayasiri
Format: Article
Language:English
Subjects:
arimax
lstm
multivariate time series forecasting
short term traffic forecasting
var
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 570
container_issue 2
container_start_page 564
container_title Proceedings of the XXth Conference of Open Innovations Association FRUCT
container_volume 28
creator Bhanuka Dissanayake
Osanda Hemachandra
Nuwan Lakshitha
Dilantha Haputhanthri
Adeesha Wijayasiri
description Traffic volume forecasting is a key objective in Intelligent Transportation Systems (ITS) since its importance for both the general public and authorities in decision making, optimizing navigation strategies and avoid traffic congestions. Various research projects have been conducted for identifying the best approach to solve that issue. This paper proposes a comparison of statistical learning models, Vector Auto Regression, ARIMAX and a deep learning model, LSTM neural network, in the context of multivariate short-term (24 hours) time series forecasting using traffic volume, speed, and average waiting time, integrating weather attributes in Austin city, Texas. Models were evaluated using rolling forecast origin method for three main feature sets generated utilizing feature selection. VAR model produced the best performance with an accuracy of 91.459% and proved to be used successfully in short term traffic forecasting in ITS applications.
doi_str_mv 10.5281/zenodo.4514955
format article
fullrecord <record><control><sourceid>doaj</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea8</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea8</doaj_id><sourcerecordid>oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea8</sourcerecordid><originalsourceid>FETCH-doaj_primary_oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea83</originalsourceid><addsrcrecordid>eNqtjMFKw0AURQdRsGi3rt8HmDpJZsxkGYrFgtm0oYib8DJ5qVOSvDKZCvr1VvETXN3LuYcrxF0sFzox8cMXjdzyQulY5VpfiFmSqjSSWZpd_nSpoyzR6lrMp-kgpUyMfszzbCbeCljycETvJh6BOyg267J4vYddsQEcW3jZViWcp_LUB_dx9jAQbN_Zh6giP0DlseuchR33p4FgxZ4sTsGN-1tx1WE_0fwvb8R69VQtn6OW8VAfvRvQf9aMrv4F7Pc1-uBsT3WLXZyZpCHZpKohaxqLhqSRBnMiNOl_fn0DRjNkNQ</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting</title><source>IEEE Xplore All Conference Series</source><creator>Bhanuka Dissanayake ; Osanda Hemachandra ; Nuwan Lakshitha ; Dilantha Haputhanthri ; Adeesha Wijayasiri</creator><creatorcontrib>Bhanuka Dissanayake ; Osanda Hemachandra ; Nuwan Lakshitha ; Dilantha Haputhanthri ; Adeesha Wijayasiri</creatorcontrib><description>Traffic volume forecasting is a key objective in Intelligent Transportation Systems (ITS) since its importance for both the general public and authorities in decision making, optimizing navigation strategies and avoid traffic congestions. Various research projects have been conducted for identifying the best approach to solve that issue. This paper proposes a comparison of statistical learning models, Vector Auto Regression, ARIMAX and a deep learning model, LSTM neural network, in the context of multivariate short-term (24 hours) time series forecasting using traffic volume, speed, and average waiting time, integrating weather attributes in Austin city, Texas. Models were evaluated using rolling forecast origin method for three main feature sets generated utilizing feature selection. VAR model produced the best performance with an accuracy of 91.459% and proved to be used successfully in short term traffic forecasting in ITS applications.</description><identifier>ISSN: 2305-7254</identifier><identifier>EISSN: 2343-0737</identifier><identifier>DOI: 10.5281/zenodo.4514955</identifier><language>eng</language><publisher>FRUCT</publisher><subject>arimax ; lstm ; multivariate time series forecasting ; short term traffic forecasting ; var</subject><ispartof>Proceedings of the XXth Conference of Open Innovations Association FRUCT, 2021-01, Vol.28 (2), p.564-570</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Bhanuka Dissanayake</creatorcontrib><creatorcontrib>Osanda Hemachandra</creatorcontrib><creatorcontrib>Nuwan Lakshitha</creatorcontrib><creatorcontrib>Dilantha Haputhanthri</creatorcontrib><creatorcontrib>Adeesha Wijayasiri</creatorcontrib><title>A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting</title><title>Proceedings of the XXth Conference of Open Innovations Association FRUCT</title><description>Traffic volume forecasting is a key objective in Intelligent Transportation Systems (ITS) since its importance for both the general public and authorities in decision making, optimizing navigation strategies and avoid traffic congestions. Various research projects have been conducted for identifying the best approach to solve that issue. This paper proposes a comparison of statistical learning models, Vector Auto Regression, ARIMAX and a deep learning model, LSTM neural network, in the context of multivariate short-term (24 hours) time series forecasting using traffic volume, speed, and average waiting time, integrating weather attributes in Austin city, Texas. Models were evaluated using rolling forecast origin method for three main feature sets generated utilizing feature selection. VAR model produced the best performance with an accuracy of 91.459% and proved to be used successfully in short term traffic forecasting in ITS applications.</description><subject>arimax</subject><subject>lstm</subject><subject>multivariate time series forecasting</subject><subject>short term traffic forecasting</subject><subject>var</subject><issn>2305-7254</issn><issn>2343-0737</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNqtjMFKw0AURQdRsGi3rt8HmDpJZsxkGYrFgtm0oYib8DJ5qVOSvDKZCvr1VvETXN3LuYcrxF0sFzox8cMXjdzyQulY5VpfiFmSqjSSWZpd_nSpoyzR6lrMp-kgpUyMfszzbCbeCljycETvJh6BOyg267J4vYddsQEcW3jZViWcp_LUB_dx9jAQbN_Zh6giP0DlseuchR33p4FgxZ4sTsGN-1tx1WE_0fwvb8R69VQtn6OW8VAfvRvQf9aMrv4F7Pc1-uBsT3WLXZyZpCHZpKohaxqLhqSRBnMiNOl_fn0DRjNkNQ</recordid><startdate>20210101</startdate><enddate>20210101</enddate><creator>Bhanuka Dissanayake</creator><creator>Osanda Hemachandra</creator><creator>Nuwan Lakshitha</creator><creator>Dilantha Haputhanthri</creator><creator>Adeesha Wijayasiri</creator><general>FRUCT</general><scope>DOA</scope></search><sort><creationdate>20210101</creationdate><title>A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting</title><author>Bhanuka Dissanayake ; Osanda Hemachandra ; Nuwan Lakshitha ; Dilantha Haputhanthri ; Adeesha Wijayasiri</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-doaj_primary_oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>arimax</topic><topic>lstm</topic><topic>multivariate time series forecasting</topic><topic>short term traffic forecasting</topic><topic>var</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bhanuka Dissanayake</creatorcontrib><creatorcontrib>Osanda Hemachandra</creatorcontrib><creatorcontrib>Nuwan Lakshitha</creatorcontrib><creatorcontrib>Dilantha Haputhanthri</creatorcontrib><creatorcontrib>Adeesha Wijayasiri</creatorcontrib><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Proceedings of the XXth Conference of Open Innovations Association FRUCT</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bhanuka Dissanayake</au><au>Osanda Hemachandra</au><au>Nuwan Lakshitha</au><au>Dilantha Haputhanthri</au><au>Adeesha Wijayasiri</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting</atitle><jtitle>Proceedings of the XXth Conference of Open Innovations Association FRUCT</jtitle><date>2021-01-01</date><risdate>2021</risdate><volume>28</volume><issue>2</issue><spage>564</spage><epage>570</epage><pages>564-570</pages><issn>2305-7254</issn><eissn>2343-0737</eissn><abstract>Traffic volume forecasting is a key objective in Intelligent Transportation Systems (ITS) since its importance for both the general public and authorities in decision making, optimizing navigation strategies and avoid traffic congestions. Various research projects have been conducted for identifying the best approach to solve that issue. This paper proposes a comparison of statistical learning models, Vector Auto Regression, ARIMAX and a deep learning model, LSTM neural network, in the context of multivariate short-term (24 hours) time series forecasting using traffic volume, speed, and average waiting time, integrating weather attributes in Austin city, Texas. Models were evaluated using rolling forecast origin method for three main feature sets generated utilizing feature selection. VAR model produced the best performance with an accuracy of 91.459% and proved to be used successfully in short term traffic forecasting in ITS applications.</abstract><pub>FRUCT</pub><doi>10.5281/zenodo.4514955</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2305-7254
ispartof Proceedings of the XXth Conference of Open Innovations Association FRUCT, 2021-01, Vol.28 (2), p.564-570
issn 2305-7254
2343-0737
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea8
source IEEE Xplore All Conference Series
subjects arimax
lstm
multivariate time series forecasting
short term traffic forecasting
var
title A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T04%3A47%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-doaj&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Comparison%20of%20ARIMAX,%20VAR%20and%20LSTM%20on%20Multivariate%20Short-Term%20Traffic%20Volume%20Forecasting&rft.jtitle=Proceedings%20of%20the%20XXth%20Conference%20of%20Open%20Innovations%20Association%20FRUCT&rft.au=Bhanuka%20Dissanayake&rft.date=2021-01-01&rft.volume=28&rft.issue=2&rft.spage=564&rft.epage=570&rft.pages=564-570&rft.issn=2305-7254&rft.eissn=2343-0737&rft_id=info:doi/10.5281/zenodo.4514955&rft_dat=%3Cdoaj%3Eoai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea8%3C/doaj%3E%3Cgrp_id%3Ecdi_FETCH-doaj_primary_oai_doaj_org_article_daf1782be0b34bec8bca8e0808a9eea83%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