Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A hybrid machine-learning and optimization method for contraflow design in post-disaster cases and traffic management scenarios
KTH, School of Electrical Engineering and Computer Science (EECS), Automatic Control.ORCID iD: 0000-0001-9940-5929
2019 (English)In: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 124, p. 67-81Article in journal (Refereed) Published
Abstract [en]

The growing number of man-made and natural disasters in recent years has made the disaster management a focal point of interest and research. To assist and streamline emergency evacuation, changing the directions of the roads (called contraflow, a traffic control measure) is proven to be an effective, quick and affordable scheme in the action list of the disaster management. The contraflow is computationally a challenging problem (known as NP-hard), hence developing an efficient method applicable to real-world and large-sized cases is a significant challenge in the literature. To cope with its complexities and to tailor to practical applications, a hybrid heuristic method based on a machine-learning model and bilevel optimization is developed. The idea is to try and test several contraflow scenarios providing a training dataset for a supervised learning (regression) model which is then used in an optimization framework to find a better scenario in an iterative process. This method is coded as a single computer program synchronized with GAMS (for optimization), MATLAB (for machine learning), EMME3 (for traffic simulation), MS-Access (for data storage) and MS-Excel (as an interface), and it is tested using a real dataset from Winnipeg, and Sioux-Falls as benchmarks. The algorithm managed to find globally optimal solutions for the Sioux-Falls example and improved accessibility to the dense and congested central areas of Winnipeg just by changing the direction of some roads.

Place, publisher, year, edition, pages
Elsevier, 2019. Vol. 124, p. 67-81
Keywords [en]
Contraflow, Disaster management, Emergency evacuation, Machine-learning, Post-disaster
National Category
Vehicle Engineering
Identifiers
URN: urn:nbn:se:kth:diva-246405DOI: 10.1016/j.eswa.2019.01.042ISI: 000461529600006Scopus ID: 2-s2.0-85060331157OAI: oai:DiVA.org:kth-246405DiVA, id: diva2:1297342
Note

QC 20190319

Available from: 2019-03-19 Created: 2019-03-19 Last updated: 2019-04-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Johansson, Karl H.

Search in DiVA

By author/editor
Johansson, Karl H.
By organisation
Automatic Control
In the same journal
Expert systems with applications
Vehicle Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 322 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf