Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312899164> ?p ?o ?g. }
- W4312899164 endingPage "9268" @default.
- W4312899164 startingPage "9254" @default.
- W4312899164 abstract "Spatio-temporal forecasting has a wide range of applications in smart city efforts, such as traffic forecasting and air quality prediction. Graph Convolutional Recurrent Neural Networks (GCRNN) are the state-of-the-art methods for this problem, which learn temporal dependencies by RNNs and exploit pairwise node proximity to model spatial dependencies. However, the spatial relations in real data are not simply pairwise but sometimes in a higher order among multiple nodes. Moreover, spatio-temporal sequences deriving from nature are often regulated by known or unknown physical laws. GCRNNs rarely take into account the underlying physics in real-world systems, which may result in degenerated performance. To address these issues, we devise a general model called Mixed-Order Relation-Aware RNN (MixRNN+) for spatio-temporal forecasting. Specifically, our MixRNN+ captures the complex mixed-order spatial relations of nodes through a newly proposed building block called Mixer, and simultaneously addressing the underlying physics by the integration of a new residual update strategy. Experimental results on three forecasting tasks in smart city applications (including traffic speed, taxi flow, and air quality prediction) demonstrate the superiority of our model against the state-of-the-art methods. We have also deployed a cloud-based system using our method as the bedrock model to show its practicality." @default.
- W4312899164 created "2023-01-05" @default.
- W4312899164 creator A5008473103 @default.
- W4312899164 creator A5018828723 @default.
- W4312899164 creator A5026844462 @default.
- W4312899164 creator A5034900443 @default.
- W4312899164 creator A5041046639 @default.
- W4312899164 creator A5049486408 @default.
- W4312899164 creator A5058575315 @default.
- W4312899164 creator A5082962427 @default.
- W4312899164 creator A5085037426 @default.
- W4312899164 creator A5087854367 @default.
- W4312899164 date "2023-09-01" @default.
- W4312899164 modified "2023-10-14" @default.
- W4312899164 title "Mixed-Order Relation-Aware Recurrent Neural Networks for Spatio-Temporal Forecasting" @default.
- W4312899164 cites W1969865391 @default.
- W4312899164 cites W1971189895 @default.
- W4312899164 cites W1986564346 @default.
- W4312899164 cites W2016287239 @default.
- W4312899164 cites W2046932810 @default.
- W4312899164 cites W2064675550 @default.
- W4312899164 cites W2095938982 @default.
- W4312899164 cites W2098015929 @default.
- W4312899164 cites W2110242546 @default.
- W4312899164 cites W2157331557 @default.
- W4312899164 cites W2164825878 @default.
- W4312899164 cites W2170057991 @default.
- W4312899164 cites W2194775991 @default.
- W4312899164 cites W2767894694 @default.
- W4312899164 cites W2788134583 @default.
- W4312899164 cites W2808535700 @default.
- W4312899164 cites W2809035759 @default.
- W4312899164 cites W2892880750 @default.
- W4312899164 cites W2899283552 @default.
- W4312899164 cites W2901504064 @default.
- W4312899164 cites W2903871660 @default.
- W4312899164 cites W2904832339 @default.
- W4312899164 cites W2962790412 @default.
- W4312899164 cites W2964319113 @default.
- W4312899164 cites W2965341826 @default.
- W4312899164 cites W2965399951 @default.
- W4312899164 cites W2966587068 @default.
- W4312899164 cites W2974916071 @default.
- W4312899164 cites W2995511918 @default.
- W4312899164 cites W2996451395 @default.
- W4312899164 cites W2997513934 @default.
- W4312899164 cites W2997848713 @default.
- W4312899164 cites W3026400623 @default.
- W4312899164 cites W3035580605 @default.
- W4312899164 cites W3080253043 @default.
- W4312899164 cites W3080403679 @default.
- W4312899164 cites W3080930191 @default.
- W4312899164 cites W3081111942 @default.
- W4312899164 cites W3081304929 @default.
- W4312899164 cites W3098011980 @default.
- W4312899164 cites W3102272367 @default.
- W4312899164 cites W3103720336 @default.
- W4312899164 cites W3177043771 @default.
- W4312899164 cites W4210257598 @default.
- W4312899164 doi "https://doi.org/10.1109/tkde.2022.3222373" @default.
- W4312899164 hasPublicationYear "2023" @default.
- W4312899164 type Work @default.
- W4312899164 citedByCount "1" @default.
- W4312899164 countsByYear W43128991642023 @default.
- W4312899164 crossrefType "journal-article" @default.
- W4312899164 hasAuthorship W4312899164A5008473103 @default.
- W4312899164 hasAuthorship W4312899164A5018828723 @default.
- W4312899164 hasAuthorship W4312899164A5026844462 @default.
- W4312899164 hasAuthorship W4312899164A5034900443 @default.
- W4312899164 hasAuthorship W4312899164A5041046639 @default.
- W4312899164 hasAuthorship W4312899164A5049486408 @default.
- W4312899164 hasAuthorship W4312899164A5058575315 @default.
- W4312899164 hasAuthorship W4312899164A5082962427 @default.
- W4312899164 hasAuthorship W4312899164A5085037426 @default.
- W4312899164 hasAuthorship W4312899164A5087854367 @default.
- W4312899164 hasConcept C111919701 @default.
- W4312899164 hasConcept C11413529 @default.
- W4312899164 hasConcept C119857082 @default.
- W4312899164 hasConcept C124101348 @default.
- W4312899164 hasConcept C132525143 @default.
- W4312899164 hasConcept C154945302 @default.
- W4312899164 hasConcept C155512373 @default.
- W4312899164 hasConcept C165696696 @default.
- W4312899164 hasConcept C184898388 @default.
- W4312899164 hasConcept C2524010 @default.
- W4312899164 hasConcept C25343380 @default.
- W4312899164 hasConcept C2777210771 @default.
- W4312899164 hasConcept C33923547 @default.
- W4312899164 hasConcept C38652104 @default.
- W4312899164 hasConcept C41008148 @default.
- W4312899164 hasConcept C79974875 @default.
- W4312899164 hasConcept C80444323 @default.
- W4312899164 hasConceptScore W4312899164C111919701 @default.
- W4312899164 hasConceptScore W4312899164C11413529 @default.
- W4312899164 hasConceptScore W4312899164C119857082 @default.
- W4312899164 hasConceptScore W4312899164C124101348 @default.
- W4312899164 hasConceptScore W4312899164C132525143 @default.
- W4312899164 hasConceptScore W4312899164C154945302 @default.