FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200379833> ?p ?o ?g. }

• W3200379833 endingPage "15065" @default.
• W3200379833 startingPage "15053" @default.
• W3200379833 abstract "Deep neural network (DNN) shows great promise in providing more intelligence to ubiquitous end devices. However, the existing partition-offloading schemes adopt data-parallel or model-parallel collaboration between devices and the cloud, which does not make full use of the resources of end devices for deep-level parallel execution. This article proposes eDDNN (i.e., enabling Distributed DNN), a collaborative inference scheme over heterogeneous end devices using cross-platform Web technology, moving the computation close to ubiquitous end devices, improving resource utilization, and reducing the computing pressure of data centers. eDDNN implements D2D communication and collaborative inference among heterogeneous end devices with WebRTC protocol, divides the data and corresponding DNN model into pieces simultaneously, and then executes inference almost independently by establishing a layer dependency table. Besides, eDDNN provides a dynamic allocation algorithm based on deep reinforcement learning to minimize latency. We conduct experiments on various data sets and DNNs and further employ eDDNN into a mobile Web AR application to illustrate the effectiveness. The results show that eDDNN can achieve the latency decrease by <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$2.98times $ </tex-math></inline-formula> , reduce mobile energy by <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$1.8times $ </tex-math></inline-formula> , and relieve the computing pressure of the edge server by <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$2.57times $ </tex-math></inline-formula> , against a typical partition-offloading approach." @default.
• W3200379833 created "2021-09-27" @default.
• W3200379833 creator A5004847496 @default.
• W3200379833 creator A5006247366 @default.
• W3200379833 creator A5042834573 @default.
• W3200379833 creator A5075937691 @default.
• W3200379833 creator A5079445870 @default.
• W3200379833 creator A5084137249 @default.
• W3200379833 date "2022-08-15" @default.
• W3200379833 modified "2023-10-03" @default.
• W3200379833 title "Enabling DNN Acceleration With Data and Model Parallelization Over Ubiquitous End Devices" @default.
• W3200379833 cites W1545214685 @default.
• W3200379833 cites W2062978452 @default.
• W3200379833 cites W2194775991 @default.
• W3200379833 cites W2546571074 @default.
• W3200379833 cites W2736180647 @default.
• W3200379833 cites W2755005384 @default.
• W3200379833 cites W2766260608 @default.
• W3200379833 cites W2786070938 @default.
• W3200379833 cites W2808079695 @default.
• W3200379833 cites W2809251854 @default.
• W3200379833 cites W2809373459 @default.
• W3200379833 cites W2895891814 @default.
• W3200379833 cites W2915609635 @default.
• W3200379833 cites W2919897868 @default.
• W3200379833 cites W2949611323 @default.
• W3200379833 cites W2960833983 @default.
• W3200379833 cites W2962677625 @default.
• W3200379833 cites W2962814013 @default.
• W3200379833 cites W2962883027 @default.
• W3200379833 cites W2963125010 @default.
• W3200379833 cites W2981114133 @default.
• W3200379833 cites W2982334556 @default.
• W3200379833 cites W3005276590 @default.
• W3200379833 cites W3047554830 @default.
• W3200379833 cites W3101077457 @default.
• W3200379833 cites W3154231689 @default.
• W3200379833 cites W3217228444 @default.
• W3200379833 cites W4236099117 @default.
• W3200379833 doi "https://doi.org/10.1109/jiot.2021.3112715" @default.
• W3200379833 hasPublicationYear "2022" @default.
• W3200379833 type Work @default.
• W3200379833 sameAs 3200379833 @default.
• W3200379833 citedByCount "5" @default.
• W3200379833 countsByYear W32003798332021 @default.
• W3200379833 countsByYear W32003798332023 @default.
• W3200379833 crossrefType "journal-article" @default.
• W3200379833 hasAuthorship W3200379833A5004847496 @default.
• W3200379833 hasAuthorship W3200379833A5006247366 @default.
• W3200379833 hasAuthorship W3200379833A5042834573 @default.
• W3200379833 hasAuthorship W3200379833A5075937691 @default.
• W3200379833 hasAuthorship W3200379833A5079445870 @default.
• W3200379833 hasAuthorship W3200379833A5084137249 @default.
• W3200379833 hasConcept C111919701 @default.
• W3200379833 hasConcept C154945302 @default.
• W3200379833 hasConcept C186967261 @default.
• W3200379833 hasConcept C2776214188 @default.
• W3200379833 hasConcept C41008148 @default.
• W3200379833 hasConcept C76155785 @default.
• W3200379833 hasConcept C80444323 @default.
• W3200379833 hasConcept C82876162 @default.
• W3200379833 hasConceptScore W3200379833C111919701 @default.
• W3200379833 hasConceptScore W3200379833C154945302 @default.
• W3200379833 hasConceptScore W3200379833C186967261 @default.
• W3200379833 hasConceptScore W3200379833C2776214188 @default.
• W3200379833 hasConceptScore W3200379833C41008148 @default.
• W3200379833 hasConceptScore W3200379833C76155785 @default.
• W3200379833 hasConceptScore W3200379833C80444323 @default.
• W3200379833 hasConceptScore W3200379833C82876162 @default.
• W3200379833 hasFunder F4320321001 @default.
• W3200379833 hasFunder F4320327912 @default.
• W3200379833 hasFunder F4320335777 @default.
• W3200379833 hasIssue "16" @default.
• W3200379833 hasLocation W32003798331 @default.
• W3200379833 hasOpenAccess W3200379833 @default.
• W3200379833 hasPrimaryLocation W32003798331 @default.
• W3200379833 hasRelatedWork W1987753576 @default.
• W3200379833 hasRelatedWork W2380362089 @default.
• W3200379833 hasRelatedWork W3006515133 @default.
• W3200379833 hasRelatedWork W3008625068 @default.
• W3200379833 hasRelatedWork W3026174634 @default.
• W3200379833 hasRelatedWork W3033499831 @default.
• W3200379833 hasRelatedWork W3128807919 @default.
• W3200379833 hasRelatedWork W3176411177 @default.
• W3200379833 hasRelatedWork W4361198556 @default.
• W3200379833 hasRelatedWork W2779562428 @default.
• W3200379833 hasVolume "9" @default.
• W3200379833 isParatext "false" @default.
• W3200379833 isRetracted "false" @default.
• W3200379833 magId "3200379833" @default.
• W3200379833 workType "article" @default.