Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308149818> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4308149818 endingPage "109132" @default.
- W4308149818 startingPage "109132" @default.
- W4308149818 abstract "Neural networks have been proven particularly accurate in univariate time series forecasting settings, requiring however a significant number of training samples to be effectively trained. In machine learning applications where available data are limited, data augmentation techniques have been successfully used to generate synthetic data that resemble and complement the original train set. Since the potential of data augmentation has been largely neglected in univariate time series forecasting, in this study we investigate nine data augmentation techniques, ranging from simple transformations and adjustments to sophisticated generative models and a novel upsampling approach. We empirically evaluate the impact of data augmentation on forecasting accuracy considering both shallow and deep feed-forward neural networks and time series data sets of different sizes from the M4 and the Tourism competitions. Our results suggest that certain data augmentation techniques that build on upsampling and time series combinations can improve forecasting performance, especially when deep networks are used. However, these improvements become less significant as the initial size of the train set increases." @default.
- W4308149818 created "2022-11-08" @default.
- W4308149818 creator A5015832946 @default.
- W4308149818 creator A5040442138 @default.
- W4308149818 creator A5085772089 @default.
- W4308149818 date "2023-02-01" @default.
- W4308149818 modified "2023-10-11" @default.
- W4308149818 title "Data augmentation for univariate time series forecasting with neural networks" @default.
- W4308149818 cites W1437335841 @default.
- W4308149818 cites W1966447062 @default.
- W4308149818 cites W1977698057 @default.
- W4308149818 cites W2016210396 @default.
- W4308149818 cites W2048665112 @default.
- W4308149818 cites W2053141315 @default.
- W4308149818 cites W2055311466 @default.
- W4308149818 cites W2068448163 @default.
- W4308149818 cites W2117829824 @default.
- W4308149818 cites W2146525523 @default.
- W4308149818 cites W2153787847 @default.
- W4308149818 cites W2260161590 @default.
- W4308149818 cites W2581984534 @default.
- W4308149818 cites W2787031726 @default.
- W4308149818 cites W2794778778 @default.
- W4308149818 cites W2901072570 @default.
- W4308149818 cites W2921275503 @default.
- W4308149818 cites W2954996726 @default.
- W4308149818 cites W2962752580 @default.
- W4308149818 cites W2963507686 @default.
- W4308149818 cites W2966607134 @default.
- W4308149818 cites W2980994438 @default.
- W4308149818 cites W3030907323 @default.
- W4308149818 cites W3046296398 @default.
- W4308149818 cites W3048247926 @default.
- W4308149818 cites W3080683114 @default.
- W4308149818 cites W3118078594 @default.
- W4308149818 cites W3181655313 @default.
- W4308149818 cites W3215409526 @default.
- W4308149818 cites W4226323522 @default.
- W4308149818 doi "https://doi.org/10.1016/j.patcog.2022.109132" @default.
- W4308149818 hasPublicationYear "2023" @default.
- W4308149818 type Work @default.
- W4308149818 citedByCount "9" @default.
- W4308149818 countsByYear W43081498182023 @default.
- W4308149818 crossrefType "journal-article" @default.
- W4308149818 hasAuthorship W4308149818A5015832946 @default.
- W4308149818 hasAuthorship W4308149818A5040442138 @default.
- W4308149818 hasAuthorship W4308149818A5085772089 @default.
- W4308149818 hasConcept C110384440 @default.
- W4308149818 hasConcept C115961682 @default.
- W4308149818 hasConcept C119857082 @default.
- W4308149818 hasConcept C124101348 @default.
- W4308149818 hasConcept C143724316 @default.
- W4308149818 hasConcept C151406439 @default.
- W4308149818 hasConcept C151730666 @default.
- W4308149818 hasConcept C154945302 @default.
- W4308149818 hasConcept C161584116 @default.
- W4308149818 hasConcept C177264268 @default.
- W4308149818 hasConcept C199163554 @default.
- W4308149818 hasConcept C199360897 @default.
- W4308149818 hasConcept C41008148 @default.
- W4308149818 hasConcept C50644808 @default.
- W4308149818 hasConcept C58489278 @default.
- W4308149818 hasConcept C86803240 @default.
- W4308149818 hasConceptScore W4308149818C110384440 @default.
- W4308149818 hasConceptScore W4308149818C115961682 @default.
- W4308149818 hasConceptScore W4308149818C119857082 @default.
- W4308149818 hasConceptScore W4308149818C124101348 @default.
- W4308149818 hasConceptScore W4308149818C143724316 @default.
- W4308149818 hasConceptScore W4308149818C151406439 @default.
- W4308149818 hasConceptScore W4308149818C151730666 @default.
- W4308149818 hasConceptScore W4308149818C154945302 @default.
- W4308149818 hasConceptScore W4308149818C161584116 @default.
- W4308149818 hasConceptScore W4308149818C177264268 @default.
- W4308149818 hasConceptScore W4308149818C199163554 @default.
- W4308149818 hasConceptScore W4308149818C199360897 @default.
- W4308149818 hasConceptScore W4308149818C41008148 @default.
- W4308149818 hasConceptScore W4308149818C50644808 @default.
- W4308149818 hasConceptScore W4308149818C58489278 @default.
- W4308149818 hasConceptScore W4308149818C86803240 @default.
- W4308149818 hasLocation W43081498181 @default.
- W4308149818 hasOpenAccess W4308149818 @default.
- W4308149818 hasPrimaryLocation W43081498181 @default.
- W4308149818 hasRelatedWork W189280425 @default.
- W4308149818 hasRelatedWork W2118640767 @default.
- W4308149818 hasRelatedWork W2262133315 @default.
- W4308149818 hasRelatedWork W2267219236 @default.
- W4308149818 hasRelatedWork W2350758509 @default.
- W4308149818 hasRelatedWork W2354804553 @default.
- W4308149818 hasRelatedWork W2375884488 @default.
- W4308149818 hasRelatedWork W2773554974 @default.
- W4308149818 hasRelatedWork W2912336747 @default.
- W4308149818 hasRelatedWork W4308149818 @default.
- W4308149818 hasVolume "134" @default.
- W4308149818 isParatext "false" @default.
- W4308149818 isRetracted "false" @default.
- W4308149818 workType "article" @default.