FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3001458159> ?p ?o ?g. }

• W3001458159 endingPage "115509" @default.
• W3001458159 startingPage "115509" @default.
• W3001458159 abstract "Deep learning-based soft sensor has been a hot topic for quality variable prediction in modern industrial processes. Feature representation with deep learning is the key step to build an accurate and reliable soft sensor model from massive process data. To deal with the limited labeled data and abundant unlabeled data, a semi-supervised pre-training strategy is proposed for deep learning network in this paper, which is based on semi-supervised stacked autoencoder (SS-SAE). For traditional deep networks like SAE, the pre-training procedure is unsupervised and may discard important information in the labeled data. Different from them, SS-SAE automatically adjusts the training strategy according to the given data type. For unlabeled data, it learns the shape of the input distribution layer by layer. While for labeled data, it additionally learns quality-related features with the guidance of quality information. The proposed method is validated on two refining industries of a debutanizer column and a hydrocracking process. The results show that SS-SAE can utilize both labeled and unlabeled data to extract quality-relevant features for soft sensor modeling, which is superior to multi-layer neural network, traditional SAE and DBN." @default.
• W3001458159 created "2020-01-30" @default.
• W3001458159 creator A5019075429 @default.
• W3001458159 creator A5040314307 @default.
• W3001458159 creator A5045634957 @default.
• W3001458159 creator A5067558148 @default.
• W3001458159 creator A5069168079 @default.
• W3001458159 date "2020-05-01" @default.
• W3001458159 modified "2023-10-14" @default.
• W3001458159 title "A novel semi-supervised pre-training strategy for deep networks and its application for quality variable prediction in industrial processes" @default.
• W3001458159 cites W1546200464 @default.
• W3001458159 cites W1806891645 @default.
• W3001458159 cites W1975656893 @default.
• W3001458159 cites W1986759966 @default.
• W3001458159 cites W1989194685 @default.
• W3001458159 cites W1990384678 @default.
• W3001458159 cites W1997175832 @default.
• W3001458159 cites W1999798000 @default.
• W3001458159 cites W2000651380 @default.
• W3001458159 cites W2004555759 @default.
• W3001458159 cites W2016794826 @default.
• W3001458159 cites W2024539003 @default.
• W3001458159 cites W2040825652 @default.
• W3001458159 cites W2054177534 @default.
• W3001458159 cites W2076423279 @default.
• W3001458159 cites W2080378379 @default.
• W3001458159 cites W2085862958 @default.
• W3001458159 cites W2136922672 @default.
• W3001458159 cites W2137722086 @default.
• W3001458159 cites W2316323201 @default.
• W3001458159 cites W2322097696 @default.
• W3001458159 cites W2327480380 @default.
• W3001458159 cites W2463821062 @default.
• W3001458159 cites W2516637094 @default.
• W3001458159 cites W2520634214 @default.
• W3001458159 cites W2560627706 @default.
• W3001458159 cites W2741800562 @default.
• W3001458159 cites W2742763523 @default.
• W3001458159 cites W2750575765 @default.
• W3001458159 cites W2753962721 @default.
• W3001458159 cites W2754296605 @default.
• W3001458159 cites W2765448293 @default.
• W3001458159 cites W2788805965 @default.
• W3001458159 cites W2791758405 @default.
• W3001458159 cites W2793663825 @default.
• W3001458159 cites W2801232586 @default.
• W3001458159 cites W2890579411 @default.
• W3001458159 cites W2899253355 @default.
• W3001458159 cites W2913982144 @default.
• W3001458159 cites W2920714358 @default.
• W3001458159 cites W2921477502 @default.
• W3001458159 cites W2942496699 @default.
• W3001458159 cites W2971407654 @default.
• W3001458159 cites W2980088075 @default.
• W3001458159 cites W2984764063 @default.
• W3001458159 cites W2998450902 @default.
• W3001458159 doi "https://doi.org/10.1016/j.ces.2020.115509" @default.
• W3001458159 hasPublicationYear "2020" @default.
• W3001458159 type Work @default.
• W3001458159 sameAs 3001458159 @default.
• W3001458159 citedByCount "52" @default.
• W3001458159 countsByYear W30014581592020 @default.
• W3001458159 countsByYear W30014581592021 @default.
• W3001458159 countsByYear W30014581592022 @default.
• W3001458159 countsByYear W30014581592023 @default.
• W3001458159 crossrefType "journal-article" @default.
• W3001458159 hasAuthorship W3001458159A5019075429 @default.
• W3001458159 hasAuthorship W3001458159A5040314307 @default.
• W3001458159 hasAuthorship W3001458159A5045634957 @default.
• W3001458159 hasAuthorship W3001458159A5067558148 @default.
• W3001458159 hasAuthorship W3001458159A5069168079 @default.
• W3001458159 hasConcept C101738243 @default.
• W3001458159 hasConcept C108583219 @default.
• W3001458159 hasConcept C111472728 @default.
• W3001458159 hasConcept C111919701 @default.
• W3001458159 hasConcept C115575686 @default.
• W3001458159 hasConcept C119857082 @default.
• W3001458159 hasConcept C124101348 @default.
• W3001458159 hasConcept C134306372 @default.
• W3001458159 hasConcept C136389625 @default.
• W3001458159 hasConcept C138885662 @default.
• W3001458159 hasConcept C153180895 @default.
• W3001458159 hasConcept C154945302 @default.
• W3001458159 hasConcept C17744445 @default.
• W3001458159 hasConcept C178790620 @default.
• W3001458159 hasConcept C182365436 @default.
• W3001458159 hasConcept C185592680 @default.
• W3001458159 hasConcept C199539241 @default.
• W3001458159 hasConcept C2776359362 @default.
• W3001458159 hasConcept C2776401178 @default.
• W3001458159 hasConcept C2779227376 @default.
• W3001458159 hasConcept C2779530757 @default.
• W3001458159 hasConcept C33923547 @default.
• W3001458159 hasConcept C41008148 @default.
• W3001458159 hasConcept C41895202 @default.
• W3001458159 hasConcept C50644808 @default.
• W3001458159 hasConcept C59404180 @default.
• W3001458159 hasConcept C94625758 @default.

• next