Show simple item record

dc.contributor.author
Pun, Lilian
dc.contributor.author
Zhao, Pengxiang
dc.contributor.author
Liu, Xintao
dc.date.accessioned
2019-04-03T08:50:03Z
dc.date.available
2019-04-03T08:22:34Z
dc.date.available
2019-04-03T08:50:03Z
dc.date.issued
2019-03-12
dc.identifier.issn
2169-3536
dc.identifier.other
10.1109/access.2019.2904645
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/335763
dc.description.abstract
Traffic flow information is of great importance for transport planning and related research. The conventional methods of automated data collection, such as annual average daily traffic (AADT) data, are often restricted by limited installation, while the state-of-the-art sensing technologies (e.g., GPS) only reflect some types of traffic flow (e.g., taxi and bus). Complete coverage of traffic flow is still lacking, thus demanding a rigorous estimation model. Most studies dedicated to estimating the traffic flow of the entire road network rely on single to only a few properties of the road network and the results may not be promising. This paper presents an idea of integrating five topological measures and road length to estimate traffic flow based on a multiple regression approach. An empirical study in Hong Kong has been conducted with three types of traffic datasets, namely floating car, public transport route, and AADT. Six measures, namely degree, betweenness, closeness, page rank, clustering coefficient, and road length, are used for traffic flow estimation. It is found that each measure correlates differently for the three types of traffic data. Multiple regression approach is then conducted, including multiple linear regression and random forest. The results show that a combination of various topological and geometrical measures has proved to have a better performance in estimating traffic flow than that of a single measure. This paper is especially helpful for transport planners to estimate traffic flow based on correlation available but limited flow data with road network characteristics.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.subject
TRAFFIC FLOW (TRANSPORTATION AND TRAFFIC)
en_US
dc.subject
Complex Network Analysis
en_US
dc.subject
Geographic Information System
en_US
dc.title
A Multiple Regression Approach for Traffic Flow Estimation
en_US
dc.type
Journal Article
ethz.journal.title
IEEE Access
ethz.journal.volume
7
en_US
ethz.pages.start
35998
en_US
ethz.pages.end
36009
en_US
ethz.identifier.wos
ethz.publication.place
Piscataway, NJ
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02648 - Inst. f. Kartografie und Geoinformation / Institute of Cartography&Geoinformation::03901 - Raubal, Martin / Raubal, Martin
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02115 - Dep. Bau, Umwelt und Geomatik / Dep. of Civil, Env. and Geomatic Eng.::02648 - Inst. f. Kartografie und Geoinformation / Institute of Cartography&Geoinformation::03901 - Raubal, Martin / Raubal, Martin
en_US
ethz.date.deposited
2019-04-03T08:22:46Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2019-04-03T08:50:10Z
ethz.rosetta.lastUpdated
2021-02-15T04:14:32Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=A%20Multiple%20Regression%20Approach%20for%20Traffic%20Flow%20Estimation&rft.jtitle=IEEE%20Access&rft.date=2019-03-12&rft.volume=7&rft.spage=35998&rft.epage=36009&rft.issn=2169-3536&rft.au=Pun,%20Lilian&Zhao,%20Pengxiang&Liu,%20Xintao&rft.genre=article&rft_id=info:doi/10.1109/access.2019.2904645&
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record