Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386886764> ?p ?o ?g. }
- W4386886764 endingPage "121701" @default.
- W4386886764 startingPage "121701" @default.
- W4386886764 abstract "The use of LSTM models for forecasting has increased substantially because they have proven to yield excellent performance in numerous applications involving time series consisting of normal observations. However, LSTM models tend to perform poorly in forecasting extreme events in imbalanced time series due to the lack of representative extreme event data during training. This study introduces a breakthrough Circular-Shift Epoch Training (CSET) strategy for LSTMs that makes the accurate forecasting of extreme events no more difficult than predicting events in normal time series with similar accuracies. CSET is (a) specifically designed to preserve the natural ordering of observations in epochs during training without any attempt to balance extreme and normal observations, (b) formulated for both univariate and multivariate time series forecasting, (c) applicable to scaler and vector forecasting for the multivariate case and can handle upward, downward, and mixed extremes without any modification, and (d) universal because it can be applied to train LSTMs to forecast events in normal time series or in imbalanced time series in exactly the same manner. Most importantly, the forecasting of normal time series and imbalanced time series do not have to be treated as separate problems. The results from an extensive set of experiments involving forecasting events in simulated and real imbalanced time series confirm that LSTM models trained using CSET dramatically outperform the standard fixed-epoch trained baseline models in (a) forecasting both extreme and normal events and (b) classifying extreme events. Given the ubiquitous use of LSTMs for forecasting, the accurate forecasting of extreme events through the incorporation of the innovative CSET strategy can have a major impact in decreasing the disastrous consequences of dangerous extreme events." @default.
- W4386886764 created "2023-09-21" @default.
- W4386886764 creator A5027853768 @default.
- W4386886764 creator A5055462963 @default.
- W4386886764 date "2024-03-01" @default.
- W4386886764 modified "2023-10-15" @default.
- W4386886764 title "Training LSTMS with circular-shift epochs for accurate event forecasting in imbalanced time series" @default.
- W4386886764 cites W1124213845 @default.
- W4386886764 cites W1979575715 @default.
- W4386886764 cites W1999996900 @default.
- W4386886764 cites W2064675550 @default.
- W4386886764 cites W2082137964 @default.
- W4386886764 cites W2098148222 @default.
- W4386886764 cites W2122016003 @default.
- W4386886764 cites W2122585011 @default.
- W4386886764 cites W2137387582 @default.
- W4386886764 cites W2143612262 @default.
- W4386886764 cites W2148143831 @default.
- W4386886764 cites W2152804254 @default.
- W4386886764 cites W2178225550 @default.
- W4386886764 cites W2293634267 @default.
- W4386886764 cites W2402268235 @default.
- W4386886764 cites W2472223596 @default.
- W4386886764 cites W2598525681 @default.
- W4386886764 cites W2792365086 @default.
- W4386886764 cites W2885195348 @default.
- W4386886764 cites W2892035503 @default.
- W4386886764 cites W2919115771 @default.
- W4386886764 cites W2936415163 @default.
- W4386886764 cites W2944851425 @default.
- W4386886764 cites W2950418200 @default.
- W4386886764 cites W2992803536 @default.
- W4386886764 cites W3000500483 @default.
- W4386886764 cites W3007066689 @default.
- W4386886764 cites W3016053201 @default.
- W4386886764 cites W3024761859 @default.
- W4386886764 cites W3120411288 @default.
- W4386886764 cites W3129433613 @default.
- W4386886764 cites W3137262131 @default.
- W4386886764 cites W3157175643 @default.
- W4386886764 cites W3159378048 @default.
- W4386886764 cites W4220954082 @default.
- W4386886764 cites W4281632444 @default.
- W4386886764 cites W4308488186 @default.
- W4386886764 cites W4309072407 @default.
- W4386886764 cites W4312561388 @default.
- W4386886764 cites W4315853073 @default.
- W4386886764 cites W4322743373 @default.
- W4386886764 cites W4382600492 @default.
- W4386886764 doi "https://doi.org/10.1016/j.eswa.2023.121701" @default.
- W4386886764 hasPublicationYear "2024" @default.
- W4386886764 type Work @default.
- W4386886764 citedByCount "0" @default.
- W4386886764 crossrefType "journal-article" @default.
- W4386886764 hasAuthorship W4386886764A5027853768 @default.
- W4386886764 hasAuthorship W4386886764A5055462963 @default.
- W4386886764 hasConcept C119857082 @default.
- W4386886764 hasConcept C121332964 @default.
- W4386886764 hasConcept C124101348 @default.
- W4386886764 hasConcept C143724316 @default.
- W4386886764 hasConcept C151406439 @default.
- W4386886764 hasConcept C151730666 @default.
- W4386886764 hasConcept C154945302 @default.
- W4386886764 hasConcept C161584116 @default.
- W4386886764 hasConcept C199163554 @default.
- W4386886764 hasConcept C2779662365 @default.
- W4386886764 hasConcept C2780150128 @default.
- W4386886764 hasConcept C41008148 @default.
- W4386886764 hasConcept C50644808 @default.
- W4386886764 hasConcept C62520636 @default.
- W4386886764 hasConcept C86803240 @default.
- W4386886764 hasConceptScore W4386886764C119857082 @default.
- W4386886764 hasConceptScore W4386886764C121332964 @default.
- W4386886764 hasConceptScore W4386886764C124101348 @default.
- W4386886764 hasConceptScore W4386886764C143724316 @default.
- W4386886764 hasConceptScore W4386886764C151406439 @default.
- W4386886764 hasConceptScore W4386886764C151730666 @default.
- W4386886764 hasConceptScore W4386886764C154945302 @default.
- W4386886764 hasConceptScore W4386886764C161584116 @default.
- W4386886764 hasConceptScore W4386886764C199163554 @default.
- W4386886764 hasConceptScore W4386886764C2779662365 @default.
- W4386886764 hasConceptScore W4386886764C2780150128 @default.
- W4386886764 hasConceptScore W4386886764C41008148 @default.
- W4386886764 hasConceptScore W4386886764C50644808 @default.
- W4386886764 hasConceptScore W4386886764C62520636 @default.
- W4386886764 hasConceptScore W4386886764C86803240 @default.
- W4386886764 hasLocation W43868867641 @default.
- W4386886764 hasOpenAccess W4386886764 @default.
- W4386886764 hasPrimaryLocation W43868867641 @default.
- W4386886764 hasRelatedWork W1828158523 @default.
- W4386886764 hasRelatedWork W1985848810 @default.
- W4386886764 hasRelatedWork W2000145235 @default.
- W4386886764 hasRelatedWork W2049578243 @default.
- W4386886764 hasRelatedWork W2122079181 @default.
- W4386886764 hasRelatedWork W2399195672 @default.
- W4386886764 hasRelatedWork W2748838164 @default.
- W4386886764 hasRelatedWork W2889939530 @default.
- W4386886764 hasRelatedWork W3121881699 @default.