Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387497913> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4387497913 endingPage "109667" @default.
- W4387497913 startingPage "109667" @default.
- W4387497913 abstract "Recently, transformer-based models have exhibited great performance in multi-horizon time series forecasting tasks. However, the core module of these models, the self-attention mechanism, is insensitive to the temporal order and suffers from attention dispersion over long time sequences. These limitations hinder the models from fully leveraging the features of time series data, particularly the periodicity. Furthermore, the lack of consideration for temporal order also hinders the identification of important temporal variables in transformers. To resolve these problems, this article develops an attention based deep learning model that can better utilize periodicity to improve prediction accuracy and enhance interpretability. We design a parallel skip LSTM module and a periodicity information utilization module to reinforce the connection between corresponding time steps within different periods and solve the problem of excessively sparse attention. An improved variable selection mechanism is embedded to the parallel skip LSTM such that temporal information can be considered when analyzing interpretability. The experimental findings on different types of real datasets show that the proposed model outperforms numerous baseline models in terms of prediction accuracy while obtaining certain interpretability." @default.
- W4387497913 created "2023-10-11" @default.
- W4387497913 creator A5007568345 @default.
- W4387497913 creator A5013582406 @default.
- W4387497913 creator A5021469909 @default.
- W4387497913 creator A5042597849 @default.
- W4387497913 creator A5054951713 @default.
- W4387497913 creator A5079521028 @default.
- W4387497913 date "2023-10-01" @default.
- W4387497913 modified "2023-10-12" @default.
- W4387497913 title "An attention-based deep learning model for multi-horizon time series forecasting by considering periodic characteristic" @default.
- W4387497913 cites W2090192376 @default.
- W4387497913 cites W2575125657 @default.
- W4387497913 cites W2604847698 @default.
- W4387497913 cites W2613328025 @default.
- W4387497913 cites W2791841214 @default.
- W4387497913 cites W2799109291 @default.
- W4387497913 cites W2890096158 @default.
- W4387497913 cites W2963374347 @default.
- W4387497913 cites W2966153025 @default.
- W4387497913 cites W2980994438 @default.
- W4387497913 cites W2992063672 @default.
- W4387497913 cites W3014191625 @default.
- W4387497913 cites W3015712039 @default.
- W4387497913 cites W3132191748 @default.
- W4387497913 cites W3157654875 @default.
- W4387497913 cites W3171884590 @default.
- W4387497913 cites W3184473617 @default.
- W4387497913 cites W3190174790 @default.
- W4387497913 cites W3194368906 @default.
- W4387497913 cites W3203725208 @default.
- W4387497913 cites W3208506476 @default.
- W4387497913 cites W3208774858 @default.
- W4387497913 cites W4229057996 @default.
- W4387497913 cites W4281857486 @default.
- W4387497913 cites W4286268167 @default.
- W4387497913 doi "https://doi.org/10.1016/j.cie.2023.109667" @default.
- W4387497913 hasPublicationYear "2023" @default.
- W4387497913 type Work @default.
- W4387497913 citedByCount "0" @default.
- W4387497913 crossrefType "journal-article" @default.
- W4387497913 hasAuthorship W4387497913A5007568345 @default.
- W4387497913 hasAuthorship W4387497913A5013582406 @default.
- W4387497913 hasAuthorship W4387497913A5021469909 @default.
- W4387497913 hasAuthorship W4387497913A5042597849 @default.
- W4387497913 hasAuthorship W4387497913A5054951713 @default.
- W4387497913 hasAuthorship W4387497913A5079521028 @default.
- W4387497913 hasConcept C108583219 @default.
- W4387497913 hasConcept C119599485 @default.
- W4387497913 hasConcept C119857082 @default.
- W4387497913 hasConcept C124101348 @default.
- W4387497913 hasConcept C126255220 @default.
- W4387497913 hasConcept C127413603 @default.
- W4387497913 hasConcept C143724316 @default.
- W4387497913 hasConcept C151406439 @default.
- W4387497913 hasConcept C151730666 @default.
- W4387497913 hasConcept C154945302 @default.
- W4387497913 hasConcept C165801399 @default.
- W4387497913 hasConcept C2781067378 @default.
- W4387497913 hasConcept C28761237 @default.
- W4387497913 hasConcept C33923547 @default.
- W4387497913 hasConcept C41008148 @default.
- W4387497913 hasConcept C66322947 @default.
- W4387497913 hasConcept C86803240 @default.
- W4387497913 hasConceptScore W4387497913C108583219 @default.
- W4387497913 hasConceptScore W4387497913C119599485 @default.
- W4387497913 hasConceptScore W4387497913C119857082 @default.
- W4387497913 hasConceptScore W4387497913C124101348 @default.
- W4387497913 hasConceptScore W4387497913C126255220 @default.
- W4387497913 hasConceptScore W4387497913C127413603 @default.
- W4387497913 hasConceptScore W4387497913C143724316 @default.
- W4387497913 hasConceptScore W4387497913C151406439 @default.
- W4387497913 hasConceptScore W4387497913C151730666 @default.
- W4387497913 hasConceptScore W4387497913C154945302 @default.
- W4387497913 hasConceptScore W4387497913C165801399 @default.
- W4387497913 hasConceptScore W4387497913C2781067378 @default.
- W4387497913 hasConceptScore W4387497913C28761237 @default.
- W4387497913 hasConceptScore W4387497913C33923547 @default.
- W4387497913 hasConceptScore W4387497913C41008148 @default.
- W4387497913 hasConceptScore W4387497913C66322947 @default.
- W4387497913 hasConceptScore W4387497913C86803240 @default.
- W4387497913 hasLocation W43874979131 @default.
- W4387497913 hasOpenAccess W4387497913 @default.
- W4387497913 hasPrimaryLocation W43874979131 @default.
- W4387497913 hasRelatedWork W2806259446 @default.
- W4387497913 hasRelatedWork W2905433371 @default.
- W4387497913 hasRelatedWork W4226258012 @default.
- W4387497913 hasRelatedWork W4310278675 @default.
- W4387497913 hasRelatedWork W4311431240 @default.
- W4387497913 hasRelatedWork W4312407344 @default.
- W4387497913 hasRelatedWork W4361193272 @default.
- W4387497913 hasRelatedWork W4383681494 @default.
- W4387497913 hasRelatedWork W4384115502 @default.
- W4387497913 hasRelatedWork W2963326959 @default.
- W4387497913 isParatext "false" @default.
- W4387497913 isRetracted "false" @default.
- W4387497913 workType "article" @default.