Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003166104> ?p ?o ?g. }
- W3003166104 endingPage "269" @default.
- W3003166104 startingPage "260" @default.
- W3003166104 abstract "Soft-sensing techniques are of great significance in industrial processes for monitoring and prediction of key performance indicators. Due to the effectiveness of nonlinear feature extraction and strong expansibility, an autoencoder (AE) and its extensions have been widely developed for industrial applications. Nevertheless, an AE commonly uses the last hidden layer for regression modeling with the output, which seems to be a kind of information waste as the shallow layers are also abstractions of input data. Besides, when there are excessive unlabeled samples, AE-based models are less likely to make full use of them or even degrade the performance. To deal with these issues, a method called ensemble semi-supervised gated stacked AE (ES <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sup> GSAE) is proposed in this article. Gate units are used to develop connections between different layers and the output layer, which also help quantify the contribution of different hidden layers. Moreover, the idea of ensemble learning is combined with semi-supervised learning, in which different unlabeled datasets are used for training different submodels to ensure their diversities. In this way, unlabeled samples can be utilized more efficiently and help enhance the model performance. The effectiveness and superiority are verified in a real industrial process by comparing the proposed method with other typical AE-based models." @default.
- W3003166104 created "2020-02-07" @default.
- W3003166104 creator A5018742950 @default.
- W3003166104 creator A5067726465 @default.
- W3003166104 date "2021-01-01" @default.
- W3003166104 modified "2023-10-09" @default.
- W3003166104 title "Deep Learning for Industrial KPI Prediction: When Ensemble Learning Meets Semi-Supervised Data" @default.
- W3003166104 cites W2001494200 @default.
- W3003166104 cites W2076063813 @default.
- W3003166104 cites W2085862958 @default.
- W3003166104 cites W2136922672 @default.
- W3003166104 cites W2261061938 @default.
- W3003166104 cites W2637726872 @default.
- W3003166104 cites W2742763523 @default.
- W3003166104 cites W2759373267 @default.
- W3003166104 cites W2765774435 @default.
- W3003166104 cites W2770168992 @default.
- W3003166104 cites W2774636206 @default.
- W3003166104 cites W2788805965 @default.
- W3003166104 cites W2789440825 @default.
- W3003166104 cites W2889017122 @default.
- W3003166104 cites W2891020080 @default.
- W3003166104 cites W2895868598 @default.
- W3003166104 cites W2896731226 @default.
- W3003166104 cites W2902166189 @default.
- W3003166104 cites W2916182456 @default.
- W3003166104 cites W2919115771 @default.
- W3003166104 cites W2920714358 @default.
- W3003166104 cites W2924593154 @default.
- W3003166104 cites W2945509102 @default.
- W3003166104 cites W2964356616 @default.
- W3003166104 cites W2965835972 @default.
- W3003166104 cites W2966742700 @default.
- W3003166104 cites W2971407654 @default.
- W3003166104 cites W2980472264 @default.
- W3003166104 cites W2982252423 @default.
- W3003166104 doi "https://doi.org/10.1109/tii.2020.2969709" @default.
- W3003166104 hasPublicationYear "2021" @default.
- W3003166104 type Work @default.
- W3003166104 sameAs 3003166104 @default.
- W3003166104 citedByCount "72" @default.
- W3003166104 countsByYear W30031661042020 @default.
- W3003166104 countsByYear W30031661042021 @default.
- W3003166104 countsByYear W30031661042022 @default.
- W3003166104 countsByYear W30031661042023 @default.
- W3003166104 crossrefType "journal-article" @default.
- W3003166104 hasAuthorship W3003166104A5018742950 @default.
- W3003166104 hasAuthorship W3003166104A5067726465 @default.
- W3003166104 hasConcept C101738243 @default.
- W3003166104 hasConcept C108583219 @default.
- W3003166104 hasConcept C111919701 @default.
- W3003166104 hasConcept C119857082 @default.
- W3003166104 hasConcept C119898033 @default.
- W3003166104 hasConcept C124101348 @default.
- W3003166104 hasConcept C136389625 @default.
- W3003166104 hasConcept C138885662 @default.
- W3003166104 hasConcept C153180895 @default.
- W3003166104 hasConcept C154945302 @default.
- W3003166104 hasConcept C178790620 @default.
- W3003166104 hasConcept C185592680 @default.
- W3003166104 hasConcept C2776401178 @default.
- W3003166104 hasConcept C2779227376 @default.
- W3003166104 hasConcept C41008148 @default.
- W3003166104 hasConcept C41895202 @default.
- W3003166104 hasConcept C45942800 @default.
- W3003166104 hasConcept C50644808 @default.
- W3003166104 hasConcept C52622490 @default.
- W3003166104 hasConcept C98045186 @default.
- W3003166104 hasConceptScore W3003166104C101738243 @default.
- W3003166104 hasConceptScore W3003166104C108583219 @default.
- W3003166104 hasConceptScore W3003166104C111919701 @default.
- W3003166104 hasConceptScore W3003166104C119857082 @default.
- W3003166104 hasConceptScore W3003166104C119898033 @default.
- W3003166104 hasConceptScore W3003166104C124101348 @default.
- W3003166104 hasConceptScore W3003166104C136389625 @default.
- W3003166104 hasConceptScore W3003166104C138885662 @default.
- W3003166104 hasConceptScore W3003166104C153180895 @default.
- W3003166104 hasConceptScore W3003166104C154945302 @default.
- W3003166104 hasConceptScore W3003166104C178790620 @default.
- W3003166104 hasConceptScore W3003166104C185592680 @default.
- W3003166104 hasConceptScore W3003166104C2776401178 @default.
- W3003166104 hasConceptScore W3003166104C2779227376 @default.
- W3003166104 hasConceptScore W3003166104C41008148 @default.
- W3003166104 hasConceptScore W3003166104C41895202 @default.
- W3003166104 hasConceptScore W3003166104C45942800 @default.
- W3003166104 hasConceptScore W3003166104C50644808 @default.
- W3003166104 hasConceptScore W3003166104C52622490 @default.
- W3003166104 hasConceptScore W3003166104C98045186 @default.
- W3003166104 hasFunder F4320321001 @default.
- W3003166104 hasFunder F4320338464 @default.
- W3003166104 hasIssue "1" @default.
- W3003166104 hasLocation W30031661041 @default.
- W3003166104 hasOpenAccess W3003166104 @default.
- W3003166104 hasPrimaryLocation W30031661041 @default.
- W3003166104 hasRelatedWork W2592385986 @default.
- W3003166104 hasRelatedWork W2772780115 @default.
- W3003166104 hasRelatedWork W2785535669 @default.
- W3003166104 hasRelatedWork W3136979370 @default.