Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367056871> ?p ?o ?g. }
- W4367056871 endingPage "108264" @default.
- W4367056871 startingPage "108264" @default.
- W4367056871 abstract "Deep learning models such as the long short-term memory (LSTM) network have been applied for dynamic inferential modeling. However, many studies apply LSTM as a black-box approach without examining the necessity and usefulness of the internal LSTM gates for inferential modeling. In this paper, we use LSTM as a state space realization and compare it with linear state space modeling and statistical learning methods, including N4SID, partial least squares, the Lasso, and support vector regression. Two case studies on an industrial 660 MW boiler and a debutanizer column process indicate that LSTM underperforms all other methods. LSTM is shown to be capable of outperforming linear methods for a simulated reactor process with severely excited nonlinearity in the data. By dissecting the sub-components of a simple LSTM model, the effectiveness of the LSTM gates and nonlinear activation functions is scrutinized." @default.
- W4367056871 created "2023-04-27" @default.
- W4367056871 creator A5055812626 @default.
- W4367056871 creator A5056937548 @default.
- W4367056871 date "2023-07-01" @default.
- W4367056871 modified "2023-10-18" @default.
- W4367056871 title "Applying and dissecting LSTM neural networks and regularized learning for dynamic inferential modeling" @default.
- W4367056871 cites W1494235660 @default.
- W4367056871 cites W1689711448 @default.
- W4367056871 cites W1969450892 @default.
- W4367056871 cites W1985888716 @default.
- W4367056871 cites W1995601908 @default.
- W4367056871 cites W2005708641 @default.
- W4367056871 cites W2016043834 @default.
- W4367056871 cites W2030844532 @default.
- W4367056871 cites W2033791852 @default.
- W4367056871 cites W2034487019 @default.
- W4367056871 cites W2054177534 @default.
- W4367056871 cites W2064675550 @default.
- W4367056871 cites W2075136904 @default.
- W4367056871 cites W2083682440 @default.
- W4367056871 cites W2088651206 @default.
- W4367056871 cites W2094704399 @default.
- W4367056871 cites W2109869845 @default.
- W4367056871 cites W2110485445 @default.
- W4367056871 cites W2148087508 @default.
- W4367056871 cites W2150355110 @default.
- W4367056871 cites W2158863190 @default.
- W4367056871 cites W2626923521 @default.
- W4367056871 cites W2750884108 @default.
- W4367056871 cites W2777815485 @default.
- W4367056871 cites W2789634333 @default.
- W4367056871 cites W2801599031 @default.
- W4367056871 cites W2920714358 @default.
- W4367056871 cites W2925872868 @default.
- W4367056871 cites W2941089296 @default.
- W4367056871 cites W2980736546 @default.
- W4367056871 cites W2983671399 @default.
- W4367056871 cites W3004690717 @default.
- W4367056871 cites W3010673643 @default.
- W4367056871 cites W3015966228 @default.
- W4367056871 cites W3087736720 @default.
- W4367056871 cites W3088069012 @default.
- W4367056871 cites W3123899295 @default.
- W4367056871 cites W4214676882 @default.
- W4367056871 cites W4289877961 @default.
- W4367056871 cites W4289878135 @default.
- W4367056871 doi "https://doi.org/10.1016/j.compchemeng.2023.108264" @default.
- W4367056871 hasPublicationYear "2023" @default.
- W4367056871 type Work @default.
- W4367056871 citedByCount "0" @default.
- W4367056871 crossrefType "journal-article" @default.
- W4367056871 hasAuthorship W4367056871A5055812626 @default.
- W4367056871 hasAuthorship W4367056871A5056937548 @default.
- W4367056871 hasConcept C105795698 @default.
- W4367056871 hasConcept C108583219 @default.
- W4367056871 hasConcept C111919701 @default.
- W4367056871 hasConcept C11413529 @default.
- W4367056871 hasConcept C119857082 @default.
- W4367056871 hasConcept C121332964 @default.
- W4367056871 hasConcept C154945302 @default.
- W4367056871 hasConcept C158622935 @default.
- W4367056871 hasConcept C2781089630 @default.
- W4367056871 hasConcept C33923547 @default.
- W4367056871 hasConcept C41008148 @default.
- W4367056871 hasConcept C50644808 @default.
- W4367056871 hasConcept C62520636 @default.
- W4367056871 hasConcept C94966114 @default.
- W4367056871 hasConcept C98045186 @default.
- W4367056871 hasConceptScore W4367056871C105795698 @default.
- W4367056871 hasConceptScore W4367056871C108583219 @default.
- W4367056871 hasConceptScore W4367056871C111919701 @default.
- W4367056871 hasConceptScore W4367056871C11413529 @default.
- W4367056871 hasConceptScore W4367056871C119857082 @default.
- W4367056871 hasConceptScore W4367056871C121332964 @default.
- W4367056871 hasConceptScore W4367056871C154945302 @default.
- W4367056871 hasConceptScore W4367056871C158622935 @default.
- W4367056871 hasConceptScore W4367056871C2781089630 @default.
- W4367056871 hasConceptScore W4367056871C33923547 @default.
- W4367056871 hasConceptScore W4367056871C41008148 @default.
- W4367056871 hasConceptScore W4367056871C50644808 @default.
- W4367056871 hasConceptScore W4367056871C62520636 @default.
- W4367056871 hasConceptScore W4367056871C94966114 @default.
- W4367056871 hasConceptScore W4367056871C98045186 @default.
- W4367056871 hasLocation W43670568711 @default.
- W4367056871 hasOpenAccess W4367056871 @default.
- W4367056871 hasPrimaryLocation W43670568711 @default.
- W4367056871 hasRelatedWork W3014300295 @default.
- W4367056871 hasRelatedWork W3164822677 @default.
- W4367056871 hasRelatedWork W4223943233 @default.
- W4367056871 hasRelatedWork W4225161397 @default.
- W4367056871 hasRelatedWork W4309045103 @default.
- W4367056871 hasRelatedWork W4312200629 @default.
- W4367056871 hasRelatedWork W4360585206 @default.
- W4367056871 hasRelatedWork W4364306694 @default.
- W4367056871 hasRelatedWork W4380075502 @default.
- W4367056871 hasRelatedWork W4380086463 @default.
- W4367056871 hasVolume "175" @default.