Multi-attention 3D residual neural network for origin-destination crowd flow prediction

Ma, Jiaman, Chan, Jeffrey, Rajasegarar, Sutharshan, Ristanoski, Goce and Leckie, Christopher 2020, Multi-attention 3D residual neural network for origin-destination crowd flow prediction, in ICDM2020 : Proceedings of IEEE's International Conference on Data Mining, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, N.J., pp. 1160-1165, doi: 10.1109/ICDM50108.2020.00142.

Attached Files
Name Description MIMEType Size Downloads

Title Multi-attention 3D residual neural network for origin-destination crowd flow prediction
Author(s) Ma, Jiaman
Chan, Jeffrey
Rajasegarar, SutharshanORCID iD for Rajasegarar, Sutharshan orcid.org/0000-0002-6559-6736
Ristanoski, Goce
Leckie, Christopher
Conference name ICDM2020. Data Mining. IEEE International Conference (2020 : Sorrento, Italy)
Conference location Online : Sorrento, Italy
Conference dates 17 - 20 Nov. 2020
Title of proceedings ICDM2020 : Proceedings of IEEE's International Conference on Data Mining
Publication date 2020
Start page 1160
End page 1165
Total pages 6
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Place of publication Piscataway, N.J.
Keyword(s) crowd flow prediction
origin-destination
global attention
3D convolutional networks
CORE2020 A*
Summary To provide effective services for intelligent transportation systems (ITS), such as optimizing ride services and recommending trips, it is important to predict the distributions of passenger flows from various origins to destinations. However, existing crowd flow prediction models have not sufficiently addressed this problem, and most methods have only focused on in and out flows of individual regions. The main challenges of origin-destination (OD) crowd flow prediction are diverse flow patterns across city networks and data sparsity. To solve these problems, we propose a Multi Attention 3D Residual Network (MAThR) to predict city-wide OD crowd flows. In particular, we develop a multi-component 3D residual structure with a novel global self-attention mechanism to dynamically aggregate the OD spatial-temporal dependencies, by modeling three components: contextual information of the region, and long and short term periodic crowd flows. For each component, we design a tensor criss-cross self-attention block, which can simultaneously discover the global and local correlation of spatial (where), temporal (when) and contextual (which) information between all OD pairs. Evaluation on real-world crowd flow data demonstrates the advantages of our MAThR method on prediction accuracy, compared to other existing state-of-the-art methods.
ISBN 9781728183169
ISSN 1550-4786
Language eng
DOI 10.1109/ICDM50108.2020.00142
Indigenous content off
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2020, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30148663

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 10 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Tue, 09 Mar 2021, 07:56:38 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.