File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Analyzing walking route choice through built environments using random forests and discrete choice techniques

TitleAnalyzing walking route choice through built environments using random forests and discrete choice techniques
Authors
KeywordsWalkability
built environment
random forests
route choice
Issue Date2017
Citation
Environment and Planning B: Urban Analytics and City Science, 2017, v. 44, n. 6, p. 1145-1167 How to Cite?
Abstract© 2016, © The Author(s) 2016. Walking is a form of active transportation with numerous benefits, including better health outcomes, lower environmental impacts and stronger communities. Understanding built environmental associations with walking behavior is a key step towards identifying design features that support walking. Human mobility data available through GPS receivers and cell phones, combined with high resolution walkability data, provide a rich source of georeferenced data for analyzing environmental associations with walking behavior. However, traditional techniques such as route choice models have difficulty with highly dimensioned data. This paper develops a novel combination of a data-driven technique with route choice modeling for leveraging walkability audits. Using data from a study in Salt Lake City, UT, USA, we apply the data-driven technique of random forests to select variables for use in walking route choice models. We estimate data-driven route choice models and theory-driven models based on predefined walkability dimensions. Results indicate that the random forest technique selects variables that dramatically improve goodness of fit of walking route choice models relative to models based on predefined walkability dimensions. We compare the theory-driven and data-driven walking route choice models based on interpretability and policy relevance.
Persistent Identifierhttp://hdl.handle.net/10722/286950
ISSN
2023 Impact Factor: 2.6
2023 SCImago Journal Rankings: 0.929
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorTribby, Calvin P.-
dc.contributor.authorMiller, Harvey J.-
dc.contributor.authorBrown, Barbara B.-
dc.contributor.authorWerner, Carol M.-
dc.contributor.authorSmith, Ken R.-
dc.date.accessioned2020-09-07T11:46:06Z-
dc.date.available2020-09-07T11:46:06Z-
dc.date.issued2017-
dc.identifier.citationEnvironment and Planning B: Urban Analytics and City Science, 2017, v. 44, n. 6, p. 1145-1167-
dc.identifier.issn2399-8083-
dc.identifier.urihttp://hdl.handle.net/10722/286950-
dc.description.abstract© 2016, © The Author(s) 2016. Walking is a form of active transportation with numerous benefits, including better health outcomes, lower environmental impacts and stronger communities. Understanding built environmental associations with walking behavior is a key step towards identifying design features that support walking. Human mobility data available through GPS receivers and cell phones, combined with high resolution walkability data, provide a rich source of georeferenced data for analyzing environmental associations with walking behavior. However, traditional techniques such as route choice models have difficulty with highly dimensioned data. This paper develops a novel combination of a data-driven technique with route choice modeling for leveraging walkability audits. Using data from a study in Salt Lake City, UT, USA, we apply the data-driven technique of random forests to select variables for use in walking route choice models. We estimate data-driven route choice models and theory-driven models based on predefined walkability dimensions. Results indicate that the random forest technique selects variables that dramatically improve goodness of fit of walking route choice models relative to models based on predefined walkability dimensions. We compare the theory-driven and data-driven walking route choice models based on interpretability and policy relevance.-
dc.languageeng-
dc.relation.ispartofEnvironment and Planning B: Urban Analytics and City Science-
dc.subjectWalkability-
dc.subjectbuilt environment-
dc.subjectrandom forests-
dc.subjectroute choice-
dc.titleAnalyzing walking route choice through built environments using random forests and discrete choice techniques-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1177/0265813516659286-
dc.identifier.scopuseid_2-s2.0-85033480568-
dc.identifier.volume44-
dc.identifier.issue6-
dc.identifier.spage1145-
dc.identifier.epage1167-
dc.identifier.eissn2399-8091-
dc.identifier.isiWOS:000414907900008-
dc.identifier.issnl2399-8083-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats