Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048582611> ?p ?o ?g. }
- W3048582611 endingPage "8962" @default.
- W3048582611 startingPage "8953" @default.
- W3048582611 abstract "Slow feature analysis (SFA) is an unsupervised learning method that extracts the latent variables from a time series dataset based on the temporal slowness aspect. Neural networks, owing to their ability to model complex nonlinearities, can be used to extract slow features (SFs) from a dataset obtained from a complicated process. Siamese neural networks can be used for this purpose. Siamese neural networks have a provision of handling two samples at a time and this aspect helps in extracting SFs. For supervised learning applications, the extracted SFs should help predict the outputs. In this article, we present two approaches that extract SFs using Siamese neural networks. The output relevance aspect is brought into feature extraction as a regularization term in the objective function of the Siamese neural network. Such regularization improves the performance of the neural network model. The proposed approaches are implemented on three datasets to demonstrate their effectiveness." @default.
- W3048582611 created "2020-08-18" @default.
- W3048582611 creator A5017597087 @default.
- W3048582611 creator A5071540194 @default.
- W3048582611 date "2021-09-01" @default.
- W3048582611 modified "2023-10-05" @default.
- W3048582611 title "Siamese Neural Network-Based Supervised Slow Feature Extraction for Soft Sensor Application" @default.
- W3048582611 cites W1542775463 @default.
- W3048582611 cites W1836533770 @default.
- W3048582611 cites W1977814411 @default.
- W3048582611 cites W2000651380 @default.
- W3048582611 cites W2036706046 @default.
- W3048582611 cites W2051453543 @default.
- W3048582611 cites W2054177534 @default.
- W3048582611 cites W2057815930 @default.
- W3048582611 cites W2062368510 @default.
- W3048582611 cites W2065231433 @default.
- W3048582611 cites W2074093043 @default.
- W3048582611 cites W2076423279 @default.
- W3048582611 cites W2085862958 @default.
- W3048582611 cites W2111637385 @default.
- W3048582611 cites W2127589108 @default.
- W3048582611 cites W2136295067 @default.
- W3048582611 cites W2136922672 @default.
- W3048582611 cites W2138621090 @default.
- W3048582611 cites W2141863509 @default.
- W3048582611 cites W2145038566 @default.
- W3048582611 cites W2146444479 @default.
- W3048582611 cites W2158863190 @default.
- W3048582611 cites W2159291644 @default.
- W3048582611 cites W2539756354 @default.
- W3048582611 cites W2737248315 @default.
- W3048582611 cites W2742763523 @default.
- W3048582611 cites W2759373267 @default.
- W3048582611 cites W2788805965 @default.
- W3048582611 cites W2891488123 @default.
- W3048582611 cites W2902182735 @default.
- W3048582611 cites W2919115771 @default.
- W3048582611 cites W2920714358 @default.
- W3048582611 cites W2959967836 @default.
- W3048582611 cites W2962728572 @default.
- W3048582611 cites W2971407654 @default.
- W3048582611 cites W2988720209 @default.
- W3048582611 cites W3015966228 @default.
- W3048582611 doi "https://doi.org/10.1109/tie.2020.3014574" @default.
- W3048582611 hasPublicationYear "2021" @default.
- W3048582611 type Work @default.
- W3048582611 sameAs 3048582611 @default.
- W3048582611 citedByCount "13" @default.
- W3048582611 countsByYear W30485826112021 @default.
- W3048582611 countsByYear W30485826112022 @default.
- W3048582611 countsByYear W30485826112023 @default.
- W3048582611 crossrefType "journal-article" @default.
- W3048582611 hasAuthorship W3048582611A5017597087 @default.
- W3048582611 hasAuthorship W3048582611A5071540194 @default.
- W3048582611 hasConcept C11940443 @default.
- W3048582611 hasConcept C119857082 @default.
- W3048582611 hasConcept C121332964 @default.
- W3048582611 hasConcept C138885662 @default.
- W3048582611 hasConcept C153180895 @default.
- W3048582611 hasConcept C154945302 @default.
- W3048582611 hasConcept C2776135515 @default.
- W3048582611 hasConcept C2776401178 @default.
- W3048582611 hasConcept C41008148 @default.
- W3048582611 hasConcept C41895202 @default.
- W3048582611 hasConcept C50644808 @default.
- W3048582611 hasConcept C52622490 @default.
- W3048582611 hasConcept C62520636 @default.
- W3048582611 hasConceptScore W3048582611C11940443 @default.
- W3048582611 hasConceptScore W3048582611C119857082 @default.
- W3048582611 hasConceptScore W3048582611C121332964 @default.
- W3048582611 hasConceptScore W3048582611C138885662 @default.
- W3048582611 hasConceptScore W3048582611C153180895 @default.
- W3048582611 hasConceptScore W3048582611C154945302 @default.
- W3048582611 hasConceptScore W3048582611C2776135515 @default.
- W3048582611 hasConceptScore W3048582611C2776401178 @default.
- W3048582611 hasConceptScore W3048582611C41008148 @default.
- W3048582611 hasConceptScore W3048582611C41895202 @default.
- W3048582611 hasConceptScore W3048582611C50644808 @default.
- W3048582611 hasConceptScore W3048582611C52622490 @default.
- W3048582611 hasConceptScore W3048582611C62520636 @default.
- W3048582611 hasFunder F4320334593 @default.
- W3048582611 hasIssue "9" @default.
- W3048582611 hasLocation W30485826111 @default.
- W3048582611 hasOpenAccess W3048582611 @default.
- W3048582611 hasPrimaryLocation W30485826111 @default.
- W3048582611 hasRelatedWork W1964120219 @default.
- W3048582611 hasRelatedWork W2000165426 @default.
- W3048582611 hasRelatedWork W2114557664 @default.
- W3048582611 hasRelatedWork W2144059113 @default.
- W3048582611 hasRelatedWork W2146076056 @default.
- W3048582611 hasRelatedWork W2385132419 @default.
- W3048582611 hasRelatedWork W2546942002 @default.
- W3048582611 hasRelatedWork W2772780115 @default.
- W3048582611 hasRelatedWork W2811390910 @default.
- W3048582611 hasRelatedWork W3003836766 @default.
- W3048582611 hasVolume "68" @default.
- W3048582611 isParatext "false" @default.