Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386473007> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4386473007 endingPage "18" @default.
- W4386473007 startingPage "1" @default.
- W4386473007 abstract "Uncertainty is an essential consideration for time series forecasting tasks. In this work, we focus on quantifying the uncertainty of traffic forecasting from a unified perspective. We develop a novel traffic forecasting framework, namely Deep Spatio-Temporal Uncertainty Quantification (DeepSTUQ), which can estimate both aleatoric and epistemic uncertainty. Specifically, we first leverage a spatio-temporal model to model the complex spatio-temporal correlations of traffic data. Subsequently, two independent sub-neural networks maximizing the heterogeneous log-likelihood are developed to estimate aleatoric uncertainty. To estimate epistemic uncertainty, we combine the merits of variational inference and deep ensembling by integrating the Monte Carlo dropout and the Adaptive Weight Averaging re-training methods, respectively. Furthermore, to relax the Gaussianity assumption, mitigate overfitting, and improve horizon-wise uncertainty quantification performance, we define a new calibration method called Multi-horizon Conformal Calibration (MHCC). Finally, we provide a theoretical analysis of the proposed unified approach based on the PAC-Bayes theory. Extensive experiments are conducted on four public datasets, and the empirical results suggest that the proposed method outperforms state-of-the-art methods in terms of both point prediction and uncertainty quantification." @default.
- W4386473007 created "2023-09-07" @default.
- W4386473007 creator A5002283678 @default.
- W4386473007 creator A5011384237 @default.
- W4386473007 creator A5051904305 @default.
- W4386473007 creator A5059854792 @default.
- W4386473007 creator A5060365518 @default.
- W4386473007 creator A5064333848 @default.
- W4386473007 date "2023-01-01" @default.
- W4386473007 modified "2023-10-01" @default.
- W4386473007 title "Towards a Unified Understanding of Uncertainty Quantification in Traffic Flow Forecasting" @default.
- W4386473007 doi "https://doi.org/10.1109/tkde.2023.3312261" @default.
- W4386473007 hasPublicationYear "2023" @default.
- W4386473007 type Work @default.
- W4386473007 citedByCount "0" @default.
- W4386473007 crossrefType "journal-article" @default.
- W4386473007 hasAuthorship W4386473007A5002283678 @default.
- W4386473007 hasAuthorship W4386473007A5011384237 @default.
- W4386473007 hasAuthorship W4386473007A5051904305 @default.
- W4386473007 hasAuthorship W4386473007A5059854792 @default.
- W4386473007 hasAuthorship W4386473007A5060365518 @default.
- W4386473007 hasAuthorship W4386473007A5064333848 @default.
- W4386473007 hasConcept C105795698 @default.
- W4386473007 hasConcept C119857082 @default.
- W4386473007 hasConcept C124101348 @default.
- W4386473007 hasConcept C153083717 @default.
- W4386473007 hasConcept C154945302 @default.
- W4386473007 hasConcept C165838908 @default.
- W4386473007 hasConcept C176147448 @default.
- W4386473007 hasConcept C177803969 @default.
- W4386473007 hasConcept C22019652 @default.
- W4386473007 hasConcept C2776214188 @default.
- W4386473007 hasConcept C32230216 @default.
- W4386473007 hasConcept C33923547 @default.
- W4386473007 hasConcept C41008148 @default.
- W4386473007 hasConcept C44154836 @default.
- W4386473007 hasConcept C50644808 @default.
- W4386473007 hasConceptScore W4386473007C105795698 @default.
- W4386473007 hasConceptScore W4386473007C119857082 @default.
- W4386473007 hasConceptScore W4386473007C124101348 @default.
- W4386473007 hasConceptScore W4386473007C153083717 @default.
- W4386473007 hasConceptScore W4386473007C154945302 @default.
- W4386473007 hasConceptScore W4386473007C165838908 @default.
- W4386473007 hasConceptScore W4386473007C176147448 @default.
- W4386473007 hasConceptScore W4386473007C177803969 @default.
- W4386473007 hasConceptScore W4386473007C22019652 @default.
- W4386473007 hasConceptScore W4386473007C2776214188 @default.
- W4386473007 hasConceptScore W4386473007C32230216 @default.
- W4386473007 hasConceptScore W4386473007C33923547 @default.
- W4386473007 hasConceptScore W4386473007C41008148 @default.
- W4386473007 hasConceptScore W4386473007C44154836 @default.
- W4386473007 hasConceptScore W4386473007C50644808 @default.
- W4386473007 hasLocation W43864730071 @default.
- W4386473007 hasOpenAccess W4386473007 @default.
- W4386473007 hasPrimaryLocation W43864730071 @default.
- W4386473007 hasRelatedWork W1996541855 @default.
- W4386473007 hasRelatedWork W2063356598 @default.
- W4386473007 hasRelatedWork W2604745134 @default.
- W4386473007 hasRelatedWork W2753840555 @default.
- W4386473007 hasRelatedWork W2795435272 @default.
- W4386473007 hasRelatedWork W2951851447 @default.
- W4386473007 hasRelatedWork W2989932438 @default.
- W4386473007 hasRelatedWork W3099765033 @default.
- W4386473007 hasRelatedWork W4210794429 @default.
- W4386473007 hasRelatedWork W4283732135 @default.
- W4386473007 isParatext "false" @default.
- W4386473007 isRetracted "false" @default.
- W4386473007 workType "article" @default.