Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285201265> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4285201265 endingPage "2095" @default.
- W4285201265 startingPage "2084" @default.
- W4285201265 abstract "Distributed cloud/edge resources are needed to execute pervasive artificial intelligence tasks, collectively. The AI workload and data sets have variable multitasking granularity, privacy constraints, and communication latency concerns. This article presents a novel <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>federated cloud/edge</i> (FCE <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>)</i> framework, illustrated by distributed medical image processing across multiple hospital sites. This federated cloud system appeals to train many machine learning models efficiently with workload balancing and reduced communication overheads. We tested the FCE model on a multi-cloud platform recently built at the Chinese University of Hong Kong in Shenzhen. We claim three distinct advantages in using the FCE system. First, our federated cloud system results in 41.3% reduction in total AI processing time in large-scale ML/DL experiments. Second, high machine model accuracy was achieved at 87% level in telemedicine experiments. The virtual graph helps reduce internode traffic latencies to avoid ML inference slowdowns. Third, the system can tolerate multiple cloud failures to enter a graceful degradation mode in case of node failures. The scalable performance gains in AI processing speed, model accuracy, and fault tolerance make our federated clouds a truly viable approach to solving massive AI multitasking problems in pervasive AI applications." @default.
- W4285201265 created "2022-07-14" @default.
- W4285201265 creator A5015993565 @default.
- W4285201265 creator A5034767301 @default.
- W4285201265 creator A5040908982 @default.
- W4285201265 creator A5046994015 @default.
- W4285201265 creator A5058174027 @default.
- W4285201265 date "2023-04-01" @default.
- W4285201265 modified "2023-09-29" @default.
- W4285201265 title "Federated Clouds for Efficient Multitasking in Distributed Artificial Intelligence Applications" @default.
- W4285201265 cites W1511254540 @default.
- W4285201265 cites W2023888116 @default.
- W4285201265 cites W2116873850 @default.
- W4285201265 cites W2132172731 @default.
- W4285201265 cites W2150093579 @default.
- W4285201265 cites W2169528473 @default.
- W4285201265 cites W2170757999 @default.
- W4285201265 cites W2194775991 @default.
- W4285201265 cites W2327372134 @default.
- W4285201265 cites W2504150216 @default.
- W4285201265 cites W2937128637 @default.
- W4285201265 cites W2942039764 @default.
- W4285201265 cites W2946640457 @default.
- W4285201265 cites W2970825779 @default.
- W4285201265 cites W3020279595 @default.
- W4285201265 cites W3045638580 @default.
- W4285201265 cites W3105122387 @default.
- W4285201265 cites W3131796779 @default.
- W4285201265 cites W3175777295 @default.
- W4285201265 cites W3191052041 @default.
- W4285201265 cites W3205994751 @default.
- W4285201265 cites W4205500752 @default.
- W4285201265 cites W4285256074 @default.
- W4285201265 cites W4285722492 @default.
- W4285201265 cites W4286365441 @default.
- W4285201265 doi "https://doi.org/10.1109/tcc.2022.3184157" @default.
- W4285201265 hasPublicationYear "2023" @default.
- W4285201265 type Work @default.
- W4285201265 citedByCount "1" @default.
- W4285201265 countsByYear W42852012652023 @default.
- W4285201265 crossrefType "journal-article" @default.
- W4285201265 hasAuthorship W4285201265A5015993565 @default.
- W4285201265 hasAuthorship W4285201265A5034767301 @default.
- W4285201265 hasAuthorship W4285201265A5040908982 @default.
- W4285201265 hasAuthorship W4285201265A5046994015 @default.
- W4285201265 hasAuthorship W4285201265A5058174027 @default.
- W4285201265 hasConcept C107418235 @default.
- W4285201265 hasConcept C111919701 @default.
- W4285201265 hasConcept C119857082 @default.
- W4285201265 hasConcept C120314980 @default.
- W4285201265 hasConcept C154945302 @default.
- W4285201265 hasConcept C15744967 @default.
- W4285201265 hasConcept C180747234 @default.
- W4285201265 hasConcept C2778476105 @default.
- W4285201265 hasConcept C41008148 @default.
- W4285201265 hasConcept C48044578 @default.
- W4285201265 hasConcept C63540848 @default.
- W4285201265 hasConcept C79974875 @default.
- W4285201265 hasConceptScore W4285201265C107418235 @default.
- W4285201265 hasConceptScore W4285201265C111919701 @default.
- W4285201265 hasConceptScore W4285201265C119857082 @default.
- W4285201265 hasConceptScore W4285201265C120314980 @default.
- W4285201265 hasConceptScore W4285201265C154945302 @default.
- W4285201265 hasConceptScore W4285201265C15744967 @default.
- W4285201265 hasConceptScore W4285201265C180747234 @default.
- W4285201265 hasConceptScore W4285201265C2778476105 @default.
- W4285201265 hasConceptScore W4285201265C41008148 @default.
- W4285201265 hasConceptScore W4285201265C48044578 @default.
- W4285201265 hasConceptScore W4285201265C63540848 @default.
- W4285201265 hasConceptScore W4285201265C79974875 @default.
- W4285201265 hasIssue "2" @default.
- W4285201265 hasLocation W42852012651 @default.
- W4285201265 hasOpenAccess W4285201265 @default.
- W4285201265 hasPrimaryLocation W42852012651 @default.
- W4285201265 hasRelatedWork W1494029964 @default.
- W4285201265 hasRelatedWork W1980717413 @default.
- W4285201265 hasRelatedWork W1992741870 @default.
- W4285201265 hasRelatedWork W2027487876 @default.
- W4285201265 hasRelatedWork W2240063513 @default.
- W4285201265 hasRelatedWork W2267601986 @default.
- W4285201265 hasRelatedWork W2293991785 @default.
- W4285201265 hasRelatedWork W3210966092 @default.
- W4285201265 hasRelatedWork W4300361016 @default.
- W4285201265 hasRelatedWork W2336571897 @default.
- W4285201265 hasVolume "11" @default.
- W4285201265 isParatext "false" @default.
- W4285201265 isRetracted "false" @default.
- W4285201265 workType "article" @default.