File(s) under permanent embargo
Multi-attention 3D residual neural network for origin-destination crowd flow prediction
conference contribution
posted on 2020-02-09, 00:00 authored by J Ma, J Chan, Sutharshan RajasegararSutharshan Rajasegarar, G Ristanoski, C LeckieTo 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.
History
Event
ICDM2020. Data Mining. IEEE International Conference (2020 : Sorrento, Italy)Pagination
1160 - 1165Publisher
Institute of Electrical and Electronics Engineers (IEEE)Location
Online : Sorrento, ItalyPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2020-11-17End date
2020-11-20ISSN
1550-4786ISBN-13
9781728183169Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2020, IEEETitle of proceedings
ICDM2020 : Proceedings of IEEE's International Conference on Data MiningUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC