FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186281912> ?p ?o ?g. }

• W3186281912 endingPage "3274" @default.
• W3186281912 startingPage "3260" @default.
• W3186281912 abstract "Web-based Deep Neural Networks (DNNs) enhance the ability of object recognition and has attracted considerable attention in mobile Web AR and other services. However, neither performing the DNN inference on mobile Web browsers locally nor offloading computations to the cloud can strike a balance between accuracy and efficiency; generally, rude methods are often accompanied by unsatisfactory accuracy. Collaborative approaches seem to fill this gap by coordinating the distributed hierarchical computing resources, especially in the 5G era, but it still faces challenges in the current solutions, such as the lack of (1) full use of 5G resources for the one point DNN computation partitioning schemes; (2) fine-grained branching mechanism; (3) efficient partitioning method; and (4) multi-objective optimization. To this end, we present the fine-grained elastic computation partitioning mechanism for distributed DNN in 5G networks. First, we elaborate two collaborative scenarios. Second, we study the DNN branching mechanism at layer granularity. Next, we propose a DNN computation partitioning algorithm based on deep reinforcement learning. Finally, we develop a mobile Web AR application as a proof of concept. The experiments were conducted in an actually deployed 5G trial network, and the results show the superiority of this collaborative approach. The common theme is, under the premise that Quality of Service (QoS) is satisfied, to balance multiple interests by orchestrating computations across heterogeneous computing platforms." @default.
• W3186281912 created "2021-08-02" @default.
• W3186281912 creator A5004847496 @default.
• W3186281912 creator A5017360203 @default.
• W3186281912 creator A5075937691 @default.
• W3186281912 creator A5081442372 @default.
• W3186281912 creator A5084137249 @default.
• W3186281912 creator A5089217953 @default.
• W3186281912 date "2022-11-01" @default.
• W3186281912 modified "2023-10-18" @default.
• W3186281912 title "Fine-Grained Elastic Partitioning for Distributed DNN Towards Mobile Web AR Services in the 5G Era" @default.
• W3186281912 cites W1969281101 @default.
• W3186281912 cites W2023380813 @default.
• W3186281912 cites W2070294837 @default.
• W3186281912 cites W2097117768 @default.
• W3186281912 cites W2101788345 @default.
• W3186281912 cites W2117228865 @default.
• W3186281912 cites W2129861682 @default.
• W3186281912 cites W2141362318 @default.
• W3186281912 cites W2151103935 @default.
• W3186281912 cites W2233116163 @default.
• W3186281912 cites W2267244539 @default.
• W3186281912 cites W2416799949 @default.
• W3186281912 cites W2529556398 @default.
• W3186281912 cites W2558974524 @default.
• W3186281912 cites W2561715741 @default.
• W3186281912 cites W2625141509 @default.
• W3186281912 cites W2810477489 @default.
• W3186281912 cites W2886901290 @default.
• W3186281912 cites W2898408788 @default.
• W3186281912 cites W2903978855 @default.
• W3186281912 cites W2909267459 @default.
• W3186281912 cites W2913293643 @default.
• W3186281912 cites W2915609635 @default.
• W3186281912 cites W2962677625 @default.
• W3186281912 cites W2962861284 @default.
• W3186281912 cites W2962883027 @default.
• W3186281912 cites W2978563932 @default.
• W3186281912 cites W2980856918 @default.
• W3186281912 cites W2984381742 @default.
• W3186281912 cites W3010837127 @default.
• W3186281912 cites W4206434639 @default.
• W3186281912 cites W4236099117 @default.
• W3186281912 doi "https://doi.org/10.1109/tsc.2021.3098816" @default.
• W3186281912 hasPublicationYear "2022" @default.
• W3186281912 type Work @default.
• W3186281912 sameAs 3186281912 @default.
• W3186281912 citedByCount "9" @default.
• W3186281912 countsByYear W31862819122022 @default.
• W3186281912 countsByYear W31862819122023 @default.
• W3186281912 crossrefType "journal-article" @default.
• W3186281912 hasAuthorship W3186281912A5004847496 @default.
• W3186281912 hasAuthorship W3186281912A5017360203 @default.
• W3186281912 hasAuthorship W3186281912A5075937691 @default.
• W3186281912 hasAuthorship W3186281912A5081442372 @default.
• W3186281912 hasAuthorship W3186281912A5084137249 @default.
• W3186281912 hasAuthorship W3186281912A5089217953 @default.
• W3186281912 hasConcept C111919701 @default.
• W3186281912 hasConcept C11413529 @default.
• W3186281912 hasConcept C120314980 @default.
• W3186281912 hasConcept C136764020 @default.
• W3186281912 hasConcept C154945302 @default.
• W3186281912 hasConcept C177774035 @default.
• W3186281912 hasConcept C186967261 @default.
• W3186281912 hasConcept C2776214188 @default.
• W3186281912 hasConcept C31258907 @default.
• W3186281912 hasConcept C35578498 @default.
• W3186281912 hasConcept C41008148 @default.
• W3186281912 hasConcept C45374587 @default.
• W3186281912 hasConcept C50644808 @default.
• W3186281912 hasConcept C5119721 @default.
• W3186281912 hasConcept C79974875 @default.
• W3186281912 hasConceptScore W3186281912C111919701 @default.
• W3186281912 hasConceptScore W3186281912C11413529 @default.
• W3186281912 hasConceptScore W3186281912C120314980 @default.
• W3186281912 hasConceptScore W3186281912C136764020 @default.
• W3186281912 hasConceptScore W3186281912C154945302 @default.
• W3186281912 hasConceptScore W3186281912C177774035 @default.
• W3186281912 hasConceptScore W3186281912C186967261 @default.
• W3186281912 hasConceptScore W3186281912C2776214188 @default.
• W3186281912 hasConceptScore W3186281912C31258907 @default.
• W3186281912 hasConceptScore W3186281912C35578498 @default.
• W3186281912 hasConceptScore W3186281912C41008148 @default.
• W3186281912 hasConceptScore W3186281912C45374587 @default.
• W3186281912 hasConceptScore W3186281912C50644808 @default.
• W3186281912 hasConceptScore W3186281912C5119721 @default.
• W3186281912 hasConceptScore W3186281912C79974875 @default.
• W3186281912 hasFunder F4320321001 @default.
• W3186281912 hasFunder F4320327912 @default.
• W3186281912 hasIssue "6" @default.
• W3186281912 hasLocation W31862819121 @default.
• W3186281912 hasOpenAccess W3186281912 @default.
• W3186281912 hasPrimaryLocation W31862819121 @default.
• W3186281912 hasRelatedWork W1577931366 @default.
• W3186281912 hasRelatedWork W1911735095 @default.
• W3186281912 hasRelatedWork W1995399085 @default.
• W3186281912 hasRelatedWork W2046698369 @default.
• W3186281912 hasRelatedWork W2057320978 @default.

• next