dc.contributor.author |
Kieu, Minh |
|
dc.contributor.author |
Nguyen, Hoang |
|
dc.contributor.author |
Ward, Jonathan A |
|
dc.contributor.author |
Malleson, Nick |
|
dc.date.accessioned |
2022-08-23T01:56:13Z |
|
dc.date.available |
2022-08-23T01:56:13Z |
|
dc.date.issued |
2022-06-05 |
|
dc.identifier.citation |
(2022). Journal of Simulation, 1-18. |
|
dc.identifier.issn |
1747-7778 |
|
dc.identifier.uri |
https://hdl.handle.net/2292/60912 |
|
dc.description.abstract |
The use of Agent-Based Models (ABMs) to make predictions in real-time is hindered by their high computation cost and the lack of detailed individual data. This paper proposes a new framework to enable the use of emulators, also referred to as surrogate models or meta-models, coupled with ABMs, to allow for real-time predictions of the behaviour of a complex system. The case study is that of pedestrian movements through an environment. We evaluate two different types of emulators: a regression emulator based on a Random Forest and a time-series emulator using a Long Short-Term Memory neural network. Both emulators perform well, but the time-series emulator proves to generalise better to cases where the number of agents in the system is not known a priori. The results have implications for the real-time modelling of human crowds, suggesting that emulation is a feasible approach to modelling crowds in real-time, where computational complexity prohibits the use of an ABM directly. |
|
dc.language |
en |
|
dc.publisher |
Taylor & Francis |
|
dc.relation.ispartofseries |
Journal of Simulation |
|
dc.rights |
Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. |
|
dc.rights.uri |
https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm |
|
dc.subject |
0102 Applied Mathematics |
|
dc.subject |
0802 Computation Theory and Mathematics |
|
dc.title |
Towards real-time predictions using emulators of agent-based models |
|
dc.type |
Journal Article |
|
dc.identifier.doi |
10.1080/17477778.2022.2080008 |
|
pubs.begin-page |
1 |
|
dc.date.updated |
2022-07-08T03:52:02Z |
|
dc.rights.holder |
Copyright: The authors |
en |
pubs.end-page |
18 |
|
pubs.publication-status |
Published online |
|
dc.rights.accessrights |
http://purl.org/eprint/accessRights/RestrictedAccess |
en |
pubs.subtype |
Journal Article |
|
pubs.elements-id |
907666 |
|
pubs.org-id |
Engineering |
|
pubs.org-id |
Civil and Environmental Eng |
|
dc.identifier.eissn |
1747-7786 |
|
pubs.record-created-at-source-date |
2022-07-08 |
|
pubs.online-publication-date |
2022-06-05 |
|