Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387455320> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4387455320 endingPage "972" @default.
- W4387455320 startingPage "965" @default.
- W4387455320 abstract "Remaining useful life (RUL) prediction has achieved considerable success through centralized learning methods. However, traditional data aggregation may cause privacy disclosure, and existing prediction models are often too large to be trained efficiently. This paper proposes a RUL prediction method in the federated learning (FL) framework, which aims to develop a lightweight model using network pruning and rebirth strategies. First, a deep convolutional neural network (DCNN) is designed as the prediction model. Next, the Taylor expansion and the l2 norm pruning criteria are executed on the convolutional and fully-connected layers of DCNN to prune some unimportant feature maps and neurons, respectively. After each pruning operation, the network rebirth strategies, including model relocation, federated averaging (FedAvg), and selective retraining, are used to fine-tune the pruned model in the FL. Finally, the network pruning and rebirth occur alternately to produce a compact RUL prediction model with fewer parameters, which can achieve the same good performance as the original one. Experiments study on the C-MAPSS dataset demonstrates the effectiveness of the proposed method." @default.
- W4387455320 created "2023-10-10" @default.
- W4387455320 creator A5011148961 @default.
- W4387455320 creator A5019691318 @default.
- W4387455320 creator A5032472408 @default.
- W4387455320 creator A5042204348 @default.
- W4387455320 creator A5057517079 @default.
- W4387455320 date "2023-08-01" @default.
- W4387455320 modified "2023-10-11" @default.
- W4387455320 title "Federated learning with network pruning and rebirth for remaining useful life prediction of engineering systems" @default.
- W4387455320 cites W2471161958 @default.
- W4387455320 cites W2516153342 @default.
- W4387455320 cites W2544905596 @default.
- W4387455320 cites W2591055632 @default.
- W4387455320 cites W2601486059 @default.
- W4387455320 cites W2617137613 @default.
- W4387455320 cites W2756887047 @default.
- W4387455320 cites W2772084711 @default.
- W4387455320 cites W2808622270 @default.
- W4387455320 cites W2889347686 @default.
- W4387455320 cites W2943154646 @default.
- W4387455320 cites W2948412158 @default.
- W4387455320 cites W2976132861 @default.
- W4387455320 cites W3001566134 @default.
- W4387455320 cites W3006585575 @default.
- W4387455320 cites W3010852232 @default.
- W4387455320 cites W3014570380 @default.
- W4387455320 cites W3115710758 @default.
- W4387455320 cites W3123983671 @default.
- W4387455320 cites W3135855722 @default.
- W4387455320 cites W3177862163 @default.
- W4387455320 cites W3207642814 @default.
- W4387455320 cites W4211051107 @default.
- W4387455320 doi "https://doi.org/10.1016/j.mfglet.2023.08.037" @default.
- W4387455320 hasPublicationYear "2023" @default.
- W4387455320 type Work @default.
- W4387455320 citedByCount "0" @default.
- W4387455320 crossrefType "journal-article" @default.
- W4387455320 hasAuthorship W4387455320A5011148961 @default.
- W4387455320 hasAuthorship W4387455320A5019691318 @default.
- W4387455320 hasAuthorship W4387455320A5032472408 @default.
- W4387455320 hasAuthorship W4387455320A5042204348 @default.
- W4387455320 hasAuthorship W4387455320A5057517079 @default.
- W4387455320 hasConcept C108010975 @default.
- W4387455320 hasConcept C108583219 @default.
- W4387455320 hasConcept C119857082 @default.
- W4387455320 hasConcept C124101348 @default.
- W4387455320 hasConcept C138885662 @default.
- W4387455320 hasConcept C144133560 @default.
- W4387455320 hasConcept C154945302 @default.
- W4387455320 hasConcept C155202549 @default.
- W4387455320 hasConcept C2776401178 @default.
- W4387455320 hasConcept C2778712577 @default.
- W4387455320 hasConcept C2778827112 @default.
- W4387455320 hasConcept C41008148 @default.
- W4387455320 hasConcept C41895202 @default.
- W4387455320 hasConcept C50644808 @default.
- W4387455320 hasConcept C6557445 @default.
- W4387455320 hasConcept C81363708 @default.
- W4387455320 hasConcept C86803240 @default.
- W4387455320 hasConceptScore W4387455320C108010975 @default.
- W4387455320 hasConceptScore W4387455320C108583219 @default.
- W4387455320 hasConceptScore W4387455320C119857082 @default.
- W4387455320 hasConceptScore W4387455320C124101348 @default.
- W4387455320 hasConceptScore W4387455320C138885662 @default.
- W4387455320 hasConceptScore W4387455320C144133560 @default.
- W4387455320 hasConceptScore W4387455320C154945302 @default.
- W4387455320 hasConceptScore W4387455320C155202549 @default.
- W4387455320 hasConceptScore W4387455320C2776401178 @default.
- W4387455320 hasConceptScore W4387455320C2778712577 @default.
- W4387455320 hasConceptScore W4387455320C2778827112 @default.
- W4387455320 hasConceptScore W4387455320C41008148 @default.
- W4387455320 hasConceptScore W4387455320C41895202 @default.
- W4387455320 hasConceptScore W4387455320C50644808 @default.
- W4387455320 hasConceptScore W4387455320C6557445 @default.
- W4387455320 hasConceptScore W4387455320C81363708 @default.
- W4387455320 hasConceptScore W4387455320C86803240 @default.
- W4387455320 hasLocation W43874553201 @default.
- W4387455320 hasOpenAccess W4387455320 @default.
- W4387455320 hasPrimaryLocation W43874553201 @default.
- W4387455320 hasRelatedWork W2050078012 @default.
- W4387455320 hasRelatedWork W2886383271 @default.
- W4387455320 hasRelatedWork W2965782936 @default.
- W4387455320 hasRelatedWork W3029198973 @default.
- W4387455320 hasRelatedWork W3034267371 @default.
- W4387455320 hasRelatedWork W3133861977 @default.
- W4387455320 hasRelatedWork W3167935049 @default.
- W4387455320 hasRelatedWork W3193565141 @default.
- W4387455320 hasRelatedWork W4226493464 @default.
- W4387455320 hasRelatedWork W4312417841 @default.
- W4387455320 hasVolume "35" @default.
- W4387455320 isParatext "false" @default.
- W4387455320 isRetracted "false" @default.
- W4387455320 workType "article" @default.