FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387150709> ?p ?o ?g. }

• W4387150709 endingPage "285" @default.
• W4387150709 startingPage "274" @default.
• W4387150709 abstract "Deep Learning (DL) can diagnose faults and assess machine health from raw condition monitoring data without manually designed statistical features. However, practical manufacturing applications require robust and repeatable solutions that can be trusted in dynamic environments. Machine data is often unlabeled and from very few health conditions (e.g., only normal operating data). Furthermore, models often encounter shifts in domain as process parameters change and new categories of faults emerge. Traditional supervised learning may struggle to learn compact, discriminative representations that generalize to these unseen target domains since it depends on having plentiful classes to partition the feature space with decision boundaries. Transfer Learning (TL) with domain adaptation attempts to adapt these models to unlabeled target domains but assumes similar underlying structure that may not be present if new faults emerge. This study proposes focusing on maximizing the feature generality on the source domain and applying TL via weight transfer to copy the model to the target domain. Specifically, Self-Supervised Learning (SSL) with Barlow Twins may produce more discriminative features for monitoring health condition than supervised learning by focusing on semantic properties of the data. Furthermore, Federated Learning (FL) for distributed training may also improve generalization by efficiently expanding the effective size and diversity of training data by sharing information across multiple client machines. Results show that Barlow Twins outperforms supervised learning in an unlabeled target domain with emerging motor faults when the source training data contains very few distinct categories. Incorporating FL may also provide a slight advantage by diffusing knowledge of health conditions between machines. Future work should continue investigating SSL and FL performance in these realistic manufacturing scenarios." @default.
• W4387150709 created "2023-09-29" @default.
• W4387150709 creator A5022731352 @default.
• W4387150709 creator A5053225265 @default.
• W4387150709 date "2023-12-01" @default.
• W4387150709 modified "2023-10-06" @default.
• W4387150709 title "Maximizing model generalization for machine condition monitoring with Self-Supervised Learning and Federated Learning" @default.
• W4387150709 cites W2165698076 @default.
• W4387150709 cites W2556013418 @default.
• W4387150709 cites W2768753204 @default.
• W4387150709 cites W2810688721 @default.
• W4387150709 cites W2887782657 @default.
• W4387150709 cites W2898375427 @default.
• W4387150709 cites W2902985761 @default.
• W4387150709 cites W2907541186 @default.
• W4387150709 cites W2919115771 @default.
• W4387150709 cites W2991521245 @default.
• W4387150709 cites W3025475838 @default.
• W4387150709 cites W3033043953 @default.
• W4387150709 cites W3035524453 @default.
• W4387150709 cites W3041133507 @default.
• W4387150709 cites W3089183752 @default.
• W4387150709 cites W3115710758 @default.
• W4387150709 cites W3118534614 @default.
• W4387150709 cites W3129318029 @default.
• W4387150709 cites W3142041738 @default.
• W4387150709 cites W3169736721 @default.
• W4387150709 cites W3171007011 @default.
• W4387150709 cites W3179317353 @default.
• W4387150709 cites W3200230256 @default.
• W4387150709 cites W3217212503 @default.
• W4387150709 cites W343636949 @default.
• W4387150709 cites W4200072094 @default.
• W4387150709 cites W4200348518 @default.
• W4387150709 cites W4206553297 @default.
• W4387150709 cites W4281554598 @default.
• W4387150709 cites W4283756813 @default.
• W4387150709 cites W4284887971 @default.
• W4387150709 cites W4285169412 @default.
• W4387150709 cites W4285277680 @default.
• W4387150709 cites W4295872969 @default.
• W4387150709 cites W4311316079 @default.
• W4387150709 cites W4313854925 @default.
• W4387150709 cites W4319602012 @default.
• W4387150709 cites W4323338449 @default.
• W4387150709 cites W4324258826 @default.
• W4387150709 cites W4324354026 @default.
• W4387150709 cites W4378635572 @default.
• W4387150709 cites W4379142516 @default.
• W4387150709 doi "https://doi.org/10.1016/j.jmsy.2023.09.008" @default.
• W4387150709 hasPublicationYear "2023" @default.
• W4387150709 type Work @default.
• W4387150709 citedByCount "0" @default.
• W4387150709 crossrefType "journal-article" @default.
• W4387150709 hasAuthorship W4387150709A5022731352 @default.
• W4387150709 hasAuthorship W4387150709A5053225265 @default.
• W4387150709 hasConcept C119857082 @default.
• W4387150709 hasConcept C132964779 @default.
• W4387150709 hasConcept C134306372 @default.
• W4387150709 hasConcept C138885662 @default.
• W4387150709 hasConcept C150899416 @default.
• W4387150709 hasConcept C154945302 @default.
• W4387150709 hasConcept C15744967 @default.
• W4387150709 hasConcept C177148314 @default.
• W4387150709 hasConcept C199360897 @default.
• W4387150709 hasConcept C2776401178 @default.
• W4387150709 hasConcept C2780767217 @default.
• W4387150709 hasConcept C33923547 @default.
• W4387150709 hasConcept C36503486 @default.
• W4387150709 hasConcept C41008148 @default.
• W4387150709 hasConcept C41895202 @default.
• W4387150709 hasConcept C542102704 @default.
• W4387150709 hasConcept C58973888 @default.
• W4387150709 hasConcept C97931131 @default.
• W4387150709 hasConceptScore W4387150709C119857082 @default.
• W4387150709 hasConceptScore W4387150709C132964779 @default.
• W4387150709 hasConceptScore W4387150709C134306372 @default.
• W4387150709 hasConceptScore W4387150709C138885662 @default.
• W4387150709 hasConceptScore W4387150709C150899416 @default.
• W4387150709 hasConceptScore W4387150709C154945302 @default.
• W4387150709 hasConceptScore W4387150709C15744967 @default.
• W4387150709 hasConceptScore W4387150709C177148314 @default.
• W4387150709 hasConceptScore W4387150709C199360897 @default.
• W4387150709 hasConceptScore W4387150709C2776401178 @default.
• W4387150709 hasConceptScore W4387150709C2780767217 @default.
• W4387150709 hasConceptScore W4387150709C33923547 @default.
• W4387150709 hasConceptScore W4387150709C36503486 @default.
• W4387150709 hasConceptScore W4387150709C41008148 @default.
• W4387150709 hasConceptScore W4387150709C41895202 @default.
• W4387150709 hasConceptScore W4387150709C542102704 @default.
• W4387150709 hasConceptScore W4387150709C58973888 @default.
• W4387150709 hasConceptScore W4387150709C97931131 @default.
• W4387150709 hasLocation W43871507091 @default.
• W4387150709 hasOpenAccess W4387150709 @default.
• W4387150709 hasPrimaryLocation W43871507091 @default.
• W4387150709 hasRelatedWork W1522139108 @default.
• W4387150709 hasRelatedWork W1977906818 @default.
• W4387150709 hasRelatedWork W2032776242 @default.

• next