Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384207605> ?p ?o ?g. }
- W4384207605 endingPage "128406" @default.
- W4384207605 startingPage "128406" @default.
- W4384207605 abstract "Oil Layer Identification (OLI) plays a significant role in petroleum development, but is unavoidably negatively affected by small samples, non-reservoirs interference, and layer classes imbalance. Existing transfer learning methods partially address the problem of insufficient samples in OLI. Nevertheless, they ignore the geological differences between blocks. This paper introduces Multi-Block Federated Learning (MBFL) to train a generalized pre-trained model, which consists of a Mask Attention Network (MAN), Class Balance Module (CBM), and Dynamic Weighted Fusion (DWF). MBFL uses MAN to dynamically avoid non-reservoir interference while learning the relationship between reservoirs and non-reservoirs; MBFL uses CBM to overcome layer classes imbalance and uses DWF to optimize traditional federated learning for addressing geological differences among blocks. Experimental results demonstrate that MBFL achieves an average accuracy of 89.32%, and an average F1 score of 81.74% with a real-world dataset. The results of two public datasets demonstrate the generalization of MBFL." @default.
- W4384207605 created "2023-07-14" @default.
- W4384207605 creator A5003976784 @default.
- W4384207605 creator A5022385009 @default.
- W4384207605 creator A5043877842 @default.
- W4384207605 creator A5052198700 @default.
- W4384207605 creator A5054480584 @default.
- W4384207605 creator A5070807733 @default.
- W4384207605 date "2023-11-01" @default.
- W4384207605 modified "2023-10-18" @default.
- W4384207605 title "Knowledge sharing-based multi-block federated learning for few-shot oil layer identification" @default.
- W4384207605 cites W2904021815 @default.
- W4384207605 cites W2910671769 @default.
- W4384207605 cites W2923222994 @default.
- W4384207605 cites W2954452271 @default.
- W4384207605 cites W2963691377 @default.
- W4384207605 cites W2965767414 @default.
- W4384207605 cites W3034745450 @default.
- W4384207605 cites W3044088702 @default.
- W4384207605 cites W3092288641 @default.
- W4384207605 cites W3106860847 @default.
- W4384207605 cites W3123932902 @default.
- W4384207605 cites W3124301840 @default.
- W4384207605 cites W3125815192 @default.
- W4384207605 cites W3127299377 @default.
- W4384207605 cites W3159353186 @default.
- W4384207605 cites W3159777636 @default.
- W4384207605 cites W3201032882 @default.
- W4384207605 cites W3201872403 @default.
- W4384207605 cites W3209796129 @default.
- W4384207605 cites W4205629695 @default.
- W4384207605 cites W4210760129 @default.
- W4384207605 cites W4220682747 @default.
- W4384207605 cites W4223935973 @default.
- W4384207605 cites W4224248509 @default.
- W4384207605 cites W4224912639 @default.
- W4384207605 cites W4226322519 @default.
- W4384207605 cites W4282928985 @default.
- W4384207605 cites W4288045786 @default.
- W4384207605 cites W4294969968 @default.
- W4384207605 cites W4296198142 @default.
- W4384207605 cites W4296903331 @default.
- W4384207605 cites W4308887525 @default.
- W4384207605 cites W4309022363 @default.
- W4384207605 cites W4309049997 @default.
- W4384207605 cites W4310440681 @default.
- W4384207605 cites W4311360194 @default.
- W4384207605 cites W4311758695 @default.
- W4384207605 cites W4312815172 @default.
- W4384207605 cites W4313443452 @default.
- W4384207605 cites W4318141649 @default.
- W4384207605 cites W4318293222 @default.
- W4384207605 cites W4319767771 @default.
- W4384207605 cites W4321763935 @default.
- W4384207605 cites W4322753713 @default.
- W4384207605 cites W4327920700 @default.
- W4384207605 doi "https://doi.org/10.1016/j.energy.2023.128406" @default.
- W4384207605 hasPublicationYear "2023" @default.
- W4384207605 type Work @default.
- W4384207605 citedByCount "0" @default.
- W4384207605 crossrefType "journal-article" @default.
- W4384207605 hasAuthorship W4384207605A5003976784 @default.
- W4384207605 hasAuthorship W4384207605A5022385009 @default.
- W4384207605 hasAuthorship W4384207605A5043877842 @default.
- W4384207605 hasAuthorship W4384207605A5052198700 @default.
- W4384207605 hasAuthorship W4384207605A5054480584 @default.
- W4384207605 hasAuthorship W4384207605A5070807733 @default.
- W4384207605 hasConcept C116834253 @default.
- W4384207605 hasConcept C119857082 @default.
- W4384207605 hasConcept C124101348 @default.
- W4384207605 hasConcept C127162648 @default.
- W4384207605 hasConcept C127313418 @default.
- W4384207605 hasConcept C134306372 @default.
- W4384207605 hasConcept C151730666 @default.
- W4384207605 hasConcept C154945302 @default.
- W4384207605 hasConcept C177148314 @default.
- W4384207605 hasConcept C178790620 @default.
- W4384207605 hasConcept C185592680 @default.
- W4384207605 hasConcept C2524010 @default.
- W4384207605 hasConcept C2777210771 @default.
- W4384207605 hasConcept C2777212361 @default.
- W4384207605 hasConcept C2779227376 @default.
- W4384207605 hasConcept C32022120 @default.
- W4384207605 hasConcept C33923547 @default.
- W4384207605 hasConcept C41008148 @default.
- W4384207605 hasConcept C548895740 @default.
- W4384207605 hasConcept C59822182 @default.
- W4384207605 hasConcept C76155785 @default.
- W4384207605 hasConcept C86803240 @default.
- W4384207605 hasConceptScore W4384207605C116834253 @default.
- W4384207605 hasConceptScore W4384207605C119857082 @default.
- W4384207605 hasConceptScore W4384207605C124101348 @default.
- W4384207605 hasConceptScore W4384207605C127162648 @default.
- W4384207605 hasConceptScore W4384207605C127313418 @default.
- W4384207605 hasConceptScore W4384207605C134306372 @default.
- W4384207605 hasConceptScore W4384207605C151730666 @default.
- W4384207605 hasConceptScore W4384207605C154945302 @default.
- W4384207605 hasConceptScore W4384207605C177148314 @default.