Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211937969> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3211937969 abstract "Implementation of Deep Neural Networks (DNNs) in 6G era is expected to get widespread attention in the applications of Internet of Things (IoT). Unfortunately, it is a challenging task to run DNN models in IoT devices due to their limited computation capability. Further, remotely deployed cloud is incompatible to support DNN inferences in IoT platform due to its latency constraints and unreliable connectivity during poor network conditions. To address the problems, we deploy edge devices to the close proximity of IoT devices and introduce the concept of “Split Computing” to execute the DNN inference task among IoT-edge devices. In the context of split computing, we propose two mechanisms that can reduce both computational and communicational overhead by finding a trade-off between them given as follows: (1) Dynamic Split Computation (DSC) mechanism: selects an optimal partition of DNN inference between IoT device and edge to reduce computation latency and computational resources. (2) Reliable Communication Network Switching (RCNS) mechanism: During poor network conditions, this mechanism provides suitable network selection to decide whether to choose Cellular (i.e., 4G/SG/6G), Wi-Fi or Bluetooth network, respectively based on the available bandwidth. To illustrate RCNS mechanism, we propose learning based reliable communication network switching (L-RCNS) and rule based reliable communication network switching (R-RCNS) models, respectively to provide reliable connectivity compared to Cellular/Wi-Fi/Bluetooth in poor network conditions. Based on the real data-set for Cellular, Wi-Fi and Bluetooth collected by Samsung Galaxy S20 device and Raspberry Pi, we conduct extensive experiments to compare performance of the mechanisms with respect to the state of art." @default.
- W3211937969 created "2021-11-22" @default.
- W3211937969 creator A5027092774 @default.
- W3211937969 creator A5034876765 @default.
- W3211937969 creator A5036995406 @default.
- W3211937969 creator A5037808336 @default.
- W3211937969 creator A5071069201 @default.
- W3211937969 creator A5072925080 @default.
- W3211937969 date "2021-08-01" @default.
- W3211937969 modified "2023-10-17" @default.
- W3211937969 title "Split Computing: Dynamic Partitioning and Reliable Communications in IoT-Edge for 6G Vision" @default.
- W3211937969 cites W2549993562 @default.
- W3211937969 cites W2749086189 @default.
- W3211937969 cites W2786070938 @default.
- W3211937969 cites W2786839822 @default.
- W3211937969 cites W2901502597 @default.
- W3211937969 cites W2912654452 @default.
- W3211937969 cites W2955798129 @default.
- W3211937969 cites W2964223234 @default.
- W3211937969 cites W2976146566 @default.
- W3211937969 cites W2980856918 @default.
- W3211937969 cites W2981114133 @default.
- W3211937969 cites W3013668032 @default.
- W3211937969 cites W3036390306 @default.
- W3211937969 doi "https://doi.org/10.1109/ficloud49777.2021.00041" @default.
- W3211937969 hasPublicationYear "2021" @default.
- W3211937969 type Work @default.
- W3211937969 sameAs 3211937969 @default.
- W3211937969 citedByCount "5" @default.
- W3211937969 countsByYear W32119379692021 @default.
- W3211937969 countsByYear W32119379692022 @default.
- W3211937969 countsByYear W32119379692023 @default.
- W3211937969 crossrefType "proceedings-article" @default.
- W3211937969 hasAuthorship W3211937969A5027092774 @default.
- W3211937969 hasAuthorship W3211937969A5034876765 @default.
- W3211937969 hasAuthorship W3211937969A5036995406 @default.
- W3211937969 hasAuthorship W3211937969A5037808336 @default.
- W3211937969 hasAuthorship W3211937969A5071069201 @default.
- W3211937969 hasAuthorship W3211937969A5072925080 @default.
- W3211937969 hasConcept C111919701 @default.
- W3211937969 hasConcept C120314980 @default.
- W3211937969 hasConcept C138236772 @default.
- W3211937969 hasConcept C154945302 @default.
- W3211937969 hasConcept C162307627 @default.
- W3211937969 hasConcept C2776214188 @default.
- W3211937969 hasConcept C2778456923 @default.
- W3211937969 hasConcept C2781041963 @default.
- W3211937969 hasConcept C31258907 @default.
- W3211937969 hasConcept C41008148 @default.
- W3211937969 hasConcept C546215728 @default.
- W3211937969 hasConcept C555944384 @default.
- W3211937969 hasConcept C76155785 @default.
- W3211937969 hasConcept C79974875 @default.
- W3211937969 hasConceptScore W3211937969C111919701 @default.
- W3211937969 hasConceptScore W3211937969C120314980 @default.
- W3211937969 hasConceptScore W3211937969C138236772 @default.
- W3211937969 hasConceptScore W3211937969C154945302 @default.
- W3211937969 hasConceptScore W3211937969C162307627 @default.
- W3211937969 hasConceptScore W3211937969C2776214188 @default.
- W3211937969 hasConceptScore W3211937969C2778456923 @default.
- W3211937969 hasConceptScore W3211937969C2781041963 @default.
- W3211937969 hasConceptScore W3211937969C31258907 @default.
- W3211937969 hasConceptScore W3211937969C41008148 @default.
- W3211937969 hasConceptScore W3211937969C546215728 @default.
- W3211937969 hasConceptScore W3211937969C555944384 @default.
- W3211937969 hasConceptScore W3211937969C76155785 @default.
- W3211937969 hasConceptScore W3211937969C79974875 @default.
- W3211937969 hasLocation W32119379691 @default.
- W3211937969 hasOpenAccess W3211937969 @default.
- W3211937969 hasPrimaryLocation W32119379691 @default.
- W3211937969 hasRelatedWork W2534668683 @default.
- W3211937969 hasRelatedWork W2942586735 @default.
- W3211937969 hasRelatedWork W3009018976 @default.
- W3211937969 hasRelatedWork W3013760193 @default.
- W3211937969 hasRelatedWork W3211931762 @default.
- W3211937969 hasRelatedWork W4225757241 @default.
- W3211937969 hasRelatedWork W4293812074 @default.
- W3211937969 hasRelatedWork W4313145167 @default.
- W3211937969 hasRelatedWork W4375928818 @default.
- W3211937969 hasRelatedWork W4385414328 @default.
- W3211937969 isParatext "false" @default.
- W3211937969 isRetracted "false" @default.
- W3211937969 magId "3211937969" @default.
- W3211937969 workType "article" @default.