FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220663406> ?p ?o ?g. }

• W4220663406 endingPage "102461" @default.
• W4220663406 startingPage "102461" @default.
• W4220663406 abstract "The artificial intelligence (AI) empowered advanced technologies have been widely applied to process in real-time the vast amount of data in the internet of things (IoT) for a fast response. However, traditional approaches to deploying AI models impose overwhelming computation and communication overheads. In this paper, we propose a novel edge-cloud collaborative intelligence scheme that jointly compresses and partitions Convolutional Neural Network (CNN) models for fast response in IoT applications. The proposed approach first accelerates a CNN by using an acceleration technique to generate new layers that can serve as candidate partitioning since their outputs are smaller than the unaccelerated layers. It then designs fine-grained prediction models to accurately estimate the execution latency for each layer in the CNN model, and finds an optimal partitioning. The proposed approach splits the compressed CNN model into two parts according to the optimal partitioning. The obtained two parts are deployed at the edge device and in the cloud, respectively, which collaboratively minimize the overall latency without compromising the accuracy of the deep CNN model. To the best of our knowledge, this is the first work that jointly compresses and partitions CNN models for fast edge-cloud collaborative intelligence considering both execution latency and communication latency. Experimental results show that the proposed technique can reduce the latency by up to 73.14% compared to five benchmarking methods." @default.
• W4220663406 created "2022-04-03" @default.
• W4220663406 creator A5040236478 @default.
• W4220663406 creator A5042163232 @default.
• W4220663406 creator A5072408261 @default.
• W4220663406 creator A5073229141 @default.
• W4220663406 date "2022-04-01" @default.
• W4220663406 modified "2023-10-17" @default.
• W4220663406 title "Joint compressing and partitioning of CNNs for fast edge-cloud collaborative intelligence for IoT" @default.
• W4220663406 cites W2061417357 @default.
• W4220663406 cites W2109351996 @default.
• W4220663406 cites W2155893237 @default.
• W4220663406 cites W2343779160 @default.
• W4220663406 cites W2612193523 @default.
• W4220663406 cites W2805153572 @default.
• W4220663406 cites W2807848753 @default.
• W4220663406 cites W2883070812 @default.
• W4220663406 cites W2894994475 @default.
• W4220663406 cites W2914434280 @default.
• W4220663406 cites W2920031528 @default.
• W4220663406 cites W2920270483 @default.
• W4220663406 cites W2924515500 @default.
• W4220663406 cites W2941227905 @default.
• W4220663406 cites W2944908033 @default.
• W4220663406 cites W2945038543 @default.
• W4220663406 cites W2945047231 @default.
• W4220663406 cites W2950865323 @default.
• W4220663406 cites W2964233199 @default.
• W4220663406 cites W2964262038 @default.
• W4220663406 cites W2990456352 @default.
• W4220663406 cites W3006631416 @default.
• W4220663406 cites W3022837298 @default.
• W4220663406 cites W3088199650 @default.
• W4220663406 cites W3160403640 @default.
• W4220663406 cites W4236099117 @default.
• W4220663406 cites W77200240 @default.
• W4220663406 doi "https://doi.org/10.1016/j.sysarc.2022.102461" @default.
• W4220663406 hasPublicationYear "2022" @default.
• W4220663406 type Work @default.
• W4220663406 citedByCount "3" @default.
• W4220663406 countsByYear W42206634062022 @default.
• W4220663406 countsByYear W42206634062023 @default.
• W4220663406 crossrefType "journal-article" @default.
• W4220663406 hasAuthorship W4220663406A5040236478 @default.
• W4220663406 hasAuthorship W4220663406A5042163232 @default.
• W4220663406 hasAuthorship W4220663406A5072408261 @default.
• W4220663406 hasAuthorship W4220663406A5073229141 @default.
• W4220663406 hasConcept C111919701 @default.
• W4220663406 hasConcept C11413529 @default.
• W4220663406 hasConcept C120314980 @default.
• W4220663406 hasConcept C138236772 @default.
• W4220663406 hasConcept C144133560 @default.
• W4220663406 hasConcept C149635348 @default.
• W4220663406 hasConcept C154945302 @default.
• W4220663406 hasConcept C162307627 @default.
• W4220663406 hasConcept C162853370 @default.
• W4220663406 hasConcept C173608175 @default.
• W4220663406 hasConcept C2778456923 @default.
• W4220663406 hasConcept C41008148 @default.
• W4220663406 hasConcept C45374587 @default.
• W4220663406 hasConcept C76155785 @default.
• W4220663406 hasConcept C79974875 @default.
• W4220663406 hasConcept C81363708 @default.
• W4220663406 hasConcept C81860439 @default.
• W4220663406 hasConcept C82876162 @default.
• W4220663406 hasConcept C86251818 @default.
• W4220663406 hasConceptScore W4220663406C111919701 @default.
• W4220663406 hasConceptScore W4220663406C11413529 @default.
• W4220663406 hasConceptScore W4220663406C120314980 @default.
• W4220663406 hasConceptScore W4220663406C138236772 @default.
• W4220663406 hasConceptScore W4220663406C144133560 @default.
• W4220663406 hasConceptScore W4220663406C149635348 @default.
• W4220663406 hasConceptScore W4220663406C154945302 @default.
• W4220663406 hasConceptScore W4220663406C162307627 @default.
• W4220663406 hasConceptScore W4220663406C162853370 @default.
• W4220663406 hasConceptScore W4220663406C173608175 @default.
• W4220663406 hasConceptScore W4220663406C2778456923 @default.
• W4220663406 hasConceptScore W4220663406C41008148 @default.
• W4220663406 hasConceptScore W4220663406C45374587 @default.
• W4220663406 hasConceptScore W4220663406C76155785 @default.
• W4220663406 hasConceptScore W4220663406C79974875 @default.
• W4220663406 hasConceptScore W4220663406C81363708 @default.
• W4220663406 hasConceptScore W4220663406C81860439 @default.
• W4220663406 hasConceptScore W4220663406C82876162 @default.
• W4220663406 hasConceptScore W4220663406C86251818 @default.
• W4220663406 hasLocation W42206634061 @default.
• W4220663406 hasOpenAccess W4220663406 @default.
• W4220663406 hasPrimaryLocation W42206634061 @default.
• W4220663406 hasRelatedWork W2534668683 @default.
• W4220663406 hasRelatedWork W2942586735 @default.
• W4220663406 hasRelatedWork W3184768109 @default.
• W4220663406 hasRelatedWork W3211931762 @default.
• W4220663406 hasRelatedWork W4225757241 @default.
• W4220663406 hasRelatedWork W4287076991 @default.
• W4220663406 hasRelatedWork W4307482744 @default.
• W4220663406 hasRelatedWork W4375928818 @default.
• W4220663406 hasRelatedWork W4385414328 @default.
• W4220663406 hasRelatedWork W3106131444 @default.

• next