FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980856918> ?p ?o ?g. }

• W2980856918 endingPage "457" @default.
• W2980856918 startingPage "447" @default.
• W2980856918 abstract "As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run computation-intensive DNN-based tasks on mobile devices due to the limited computation resources. What’s worse, traditional cloud-assisted DNN inference is heavily hindered by the significant wide-area network latency, leading to poor real-time performance as well as low quality of user experience. To address these challenges, in this paper, we propose <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> , a framework that leverages edge computing for DNN collaborative inference through device-edge synergy. <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> exploits two design knobs: (1) DNN partitioning that adaptively partitions computation between device and edge for purpose of coordinating the powerful cloud resource and the proximal edge resource for real-time DNN inference; (2) DNN right-sizing that further reduces computing latency via early exiting inference at an appropriate intermediate DNN layer. In addition, considering the potential network fluctuation in real-world deployment, <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> is properly design to specialize for both static and dynamic network environment. Specifically, in a static environment where the bandwidth changes slowly, <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> derives the best configurations with the assist of regression-based prediction models, while in a dynamic environment where the bandwidth varies dramatically, <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> generates the best execution plan through the online change point detection algorithm that maps the current bandwidth state to the optimal configuration. We implement <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> prototype based on the Raspberry Pi and the desktop PC and the extensive experimental evaluations demonstrate <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Edgent</i> ’s effectiveness in enabling on-demand low-latency edge intelligence." @default.
• W2980856918 created "2019-10-25" @default.
• W2980856918 creator A5042785211 @default.
• W2980856918 creator A5055161955 @default.
• W2980856918 creator A5068248239 @default.
• W2980856918 creator A5078909773 @default.
• W2980856918 date "2020-01-01" @default.
• W2980856918 modified "2023-10-14" @default.
• W2980856918 title "Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing" @default.
• W2980856918 cites W1997430507 @default.
• W2980856918 cites W2097117768 @default.
• W2980856918 cites W2233116163 @default.
• W2980856918 cites W2251202616 @default.
• W2980856918 cites W2416799949 @default.
• W2980856918 cites W2507174453 @default.
• W2980856918 cites W2513554817 @default.
• W2980856918 cites W2530887700 @default.
• W2980856918 cites W2558974524 @default.
• W2980856918 cites W2589148360 @default.
• W2980856918 cites W2623333128 @default.
• W2980856918 cites W2624989916 @default.
• W2980856918 cites W2786070938 @default.
• W2980856918 cites W2786652201 @default.
• W2980856918 cites W2789900165 @default.
• W2980856918 cites W2807754472 @default.
• W2980856918 cites W2809251854 @default.
• W2980856918 cites W2849781392 @default.
• W2980856918 cites W2887892418 @default.
• W2980856918 cites W2890928364 @default.
• W2980856918 cites W2909146762 @default.
• W2980856918 cites W2912654452 @default.
• W2980856918 cites W2950865323 @default.
• W2980856918 cites W2962677625 @default.
• W2980856918 cites W2964050982 @default.
• W2980856918 cites W3102169921 @default.
• W2980856918 cites W3106445841 @default.
• W2980856918 cites W4236099117 @default.
• W2980856918 doi "https://doi.org/10.1109/twc.2019.2946140" @default.
• W2980856918 hasPublicationYear "2020" @default.
• W2980856918 type Work @default.
• W2980856918 sameAs 2980856918 @default.
• W2980856918 citedByCount "360" @default.
• W2980856918 countsByYear W29808569182019 @default.
• W2980856918 countsByYear W29808569182020 @default.
• W2980856918 countsByYear W29808569182021 @default.
• W2980856918 countsByYear W29808569182022 @default.
• W2980856918 countsByYear W29808569182023 @default.
• W2980856918 crossrefType "journal-article" @default.
• W2980856918 hasAuthorship W2980856918A5042785211 @default.
• W2980856918 hasAuthorship W2980856918A5055161955 @default.
• W2980856918 hasAuthorship W2980856918A5068248239 @default.
• W2980856918 hasAuthorship W2980856918A5078909773 @default.
• W2980856918 hasBestOaLocation W29808569182 @default.
• W2980856918 hasConcept C111919701 @default.
• W2980856918 hasConcept C11413529 @default.
• W2980856918 hasConcept C119857082 @default.
• W2980856918 hasConcept C154945302 @default.
• W2980856918 hasConcept C162307627 @default.
• W2980856918 hasConcept C2776214188 @default.
• W2980856918 hasConcept C2778456923 @default.
• W2980856918 hasConcept C41008148 @default.
• W2980856918 hasConcept C45374587 @default.
• W2980856918 hasConcept C50644808 @default.
• W2980856918 hasConcept C76155785 @default.
• W2980856918 hasConcept C79974875 @default.
• W2980856918 hasConcept C82876162 @default.
• W2980856918 hasConceptScore W2980856918C111919701 @default.
• W2980856918 hasConceptScore W2980856918C11413529 @default.
• W2980856918 hasConceptScore W2980856918C119857082 @default.
• W2980856918 hasConceptScore W2980856918C154945302 @default.
• W2980856918 hasConceptScore W2980856918C162307627 @default.
• W2980856918 hasConceptScore W2980856918C2776214188 @default.
• W2980856918 hasConceptScore W2980856918C2778456923 @default.
• W2980856918 hasConceptScore W2980856918C41008148 @default.
• W2980856918 hasConceptScore W2980856918C45374587 @default.
• W2980856918 hasConceptScore W2980856918C50644808 @default.
• W2980856918 hasConceptScore W2980856918C76155785 @default.
• W2980856918 hasConceptScore W2980856918C79974875 @default.
• W2980856918 hasConceptScore W2980856918C82876162 @default.
• W2980856918 hasFunder F4320321001 @default.
• W2980856918 hasFunder F4320335787 @default.
• W2980856918 hasIssue "1" @default.
• W2980856918 hasLocation W29808569181 @default.
• W2980856918 hasLocation W29808569182 @default.
• W2980856918 hasOpenAccess W2980856918 @default.
• W2980856918 hasPrimaryLocation W29808569181 @default.
• W2980856918 hasRelatedWork W2534668683 @default.
• W2980856918 hasRelatedWork W2942586735 @default.
• W2980856918 hasRelatedWork W3009018976 @default.
• W2980856918 hasRelatedWork W3126507566 @default.
• W2980856918 hasRelatedWork W3184768109 @default.
• W2980856918 hasRelatedWork W3211931762 @default.
• W2980856918 hasRelatedWork W4225757241 @default.
• W2980856918 hasRelatedWork W4281678247 @default.
• W2980856918 hasRelatedWork W4287076991 @default.
• W2980856918 hasRelatedWork W4385414328 @default.
• W2980856918 hasVolume "19" @default.
• W2980856918 isParatext "false" @default.

• next