Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122091261> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3122091261 endingPage "11111" @default.
- W3122091261 startingPage "11100" @default.
- W3122091261 abstract "The advancements of AI and the exponential growth of sensory data are unlocking a wave of intelligent sensing applications. To overcome the shortcoming of centralized learning and local training, Google proposes federated learning that allows users to collectively reap the benefits of shared models trained from decentralized data. However, directly applying federated learning to intelligent sensing applications faces two deficiencies: 1) omitting personalities of local models and 2) high latency. Aiming at these limitations, in this article, we propose a new framework, Federated Sensing, to enable edge-cloud elastic collaborative learning from decentralized sensory data. We design an elastic local update algorithm that can train the personalized models by setting specific updating weights for each node based on the difference between the global and local model. Our algorithm takes both the global consistency and the personalities of the local models. We further propose an n-softsync model aggregation method that significantly reduces training time by combining the synchronous and asynchronous aggregations. Extensive experiments are conducted on two real-world data sets of air quality from Beijing and Los Angeles. Compared with existing federated learning techniques, our framework improves the model performance at least by 2.61% and 18.8% in two data sets, respectively. Besides, it reduces the cloud idle time to 25.5% of the total time, which verifies the advantages of our method in terms of both model performance and training overhead." @default.
- W3122091261 created "2021-02-01" @default.
- W3122091261 creator A5003554962 @default.
- W3122091261 creator A5047612806 @default.
- W3122091261 creator A5054452935 @default.
- W3122091261 creator A5060249411 @default.
- W3122091261 creator A5089277973 @default.
- W3122091261 date "2021-07-15" @default.
- W3122091261 modified "2023-10-12" @default.
- W3122091261 title "<i>Federated Sensing</i>: Edge-Cloud Elastic Collaborative Learning for Intelligent Sensing" @default.
- W3122091261 cites W114517082 @default.
- W3122091261 cites W1973767013 @default.
- W3122091261 cites W2039240409 @default.
- W3122091261 cites W2058401212 @default.
- W3122091261 cites W2111619626 @default.
- W3122091261 cites W2153268908 @default.
- W3122091261 cites W2183341477 @default.
- W3122091261 cites W2398416149 @default.
- W3122091261 cites W2416799949 @default.
- W3122091261 cites W2460580556 @default.
- W3122091261 cites W2730523305 @default.
- W3122091261 cites W2738362612 @default.
- W3122091261 cites W2754062090 @default.
- W3122091261 cites W2768475350 @default.
- W3122091261 cites W2808064527 @default.
- W3122091261 cites W2810292802 @default.
- W3122091261 cites W2895964035 @default.
- W3122091261 cites W2912348842 @default.
- W3122091261 cites W2920270483 @default.
- W3122091261 cites W2962883027 @default.
- W3122091261 cites W2963470657 @default.
- W3122091261 cites W3018040655 @default.
- W3122091261 cites W3018464563 @default.
- W3122091261 cites W3021026170 @default.
- W3122091261 cites W3103802018 @default.
- W3122091261 cites W3105122387 @default.
- W3122091261 cites W3119906609 @default.
- W3122091261 cites W994102297 @default.
- W3122091261 doi "https://doi.org/10.1109/jiot.2021.3053055" @default.
- W3122091261 hasPublicationYear "2021" @default.
- W3122091261 type Work @default.
- W3122091261 sameAs 3122091261 @default.
- W3122091261 citedByCount "14" @default.
- W3122091261 countsByYear W31220912612022 @default.
- W3122091261 countsByYear W31220912612023 @default.
- W3122091261 crossrefType "journal-article" @default.
- W3122091261 hasAuthorship W3122091261A5003554962 @default.
- W3122091261 hasAuthorship W3122091261A5047612806 @default.
- W3122091261 hasAuthorship W3122091261A5054452935 @default.
- W3122091261 hasAuthorship W3122091261A5060249411 @default.
- W3122091261 hasAuthorship W3122091261A5089277973 @default.
- W3122091261 hasConcept C111919701 @default.
- W3122091261 hasConcept C119857082 @default.
- W3122091261 hasConcept C120314980 @default.
- W3122091261 hasConcept C138236772 @default.
- W3122091261 hasConcept C151319957 @default.
- W3122091261 hasConcept C154945302 @default.
- W3122091261 hasConcept C162307627 @default.
- W3122091261 hasConcept C2779960059 @default.
- W3122091261 hasConcept C31258907 @default.
- W3122091261 hasConcept C41008148 @default.
- W3122091261 hasConcept C67186912 @default.
- W3122091261 hasConcept C77088390 @default.
- W3122091261 hasConcept C79974875 @default.
- W3122091261 hasConceptScore W3122091261C111919701 @default.
- W3122091261 hasConceptScore W3122091261C119857082 @default.
- W3122091261 hasConceptScore W3122091261C120314980 @default.
- W3122091261 hasConceptScore W3122091261C138236772 @default.
- W3122091261 hasConceptScore W3122091261C151319957 @default.
- W3122091261 hasConceptScore W3122091261C154945302 @default.
- W3122091261 hasConceptScore W3122091261C162307627 @default.
- W3122091261 hasConceptScore W3122091261C2779960059 @default.
- W3122091261 hasConceptScore W3122091261C31258907 @default.
- W3122091261 hasConceptScore W3122091261C41008148 @default.
- W3122091261 hasConceptScore W3122091261C67186912 @default.
- W3122091261 hasConceptScore W3122091261C77088390 @default.
- W3122091261 hasConceptScore W3122091261C79974875 @default.
- W3122091261 hasFunder F4320321001 @default.
- W3122091261 hasFunder F4320327912 @default.
- W3122091261 hasIssue "14" @default.
- W3122091261 hasLocation W31220912611 @default.
- W3122091261 hasOpenAccess W3122091261 @default.
- W3122091261 hasPrimaryLocation W31220912611 @default.
- W3122091261 hasRelatedWork W2015855483 @default.
- W3122091261 hasRelatedWork W2092071486 @default.
- W3122091261 hasRelatedWork W2364921833 @default.
- W3122091261 hasRelatedWork W2391167130 @default.
- W3122091261 hasRelatedWork W2475198316 @default.
- W3122091261 hasRelatedWork W2765557566 @default.
- W3122091261 hasRelatedWork W2942586735 @default.
- W3122091261 hasRelatedWork W3211931762 @default.
- W3122091261 hasRelatedWork W4283067488 @default.
- W3122091261 hasRelatedWork W4307482744 @default.
- W3122091261 hasVolume "8" @default.
- W3122091261 isParatext "false" @default.
- W3122091261 isRetracted "false" @default.
- W3122091261 magId "3122091261" @default.
- W3122091261 workType "article" @default.