FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313071569> ?p ?o ?g. }

• W4313071569 endingPage "5023" @default.
• W4313071569 startingPage "5013" @default.
• W4313071569 abstract "The significant growth in the number of Internet of Things (IoT) devices has given impetus to the idea of edge computing for several applications. In addition, energy harvestable or wireless-powered wearable devices are envisioned to empower the edge intelligence in IoT applications. However, the intermittent energy supply and network connectivity of such devices in scenarios including remote areas and hard-to-reach regions such as in-body applications can limit the performance of edge computing-based IoT applications. Hence, deploying state-of-the-art convolutional neural networks (CNNs) on such energy-constrained devices is not feasible due to their computational cost. Existing model compression methods, such as network pruning and quantization can reduce complexity, but these methods only work for fixed computational or energy requirements, which is not the case for edge devices with an intermittent energy source. In this work, we propose a pruning scheme based on deep reinforcement learning (DRL), which can compress the CNN model adaptively according to the energy dictated by the energy management policy and accuracy requirements for IoT applications. The proposed energy policy uses predictions of energy to be harvested and dictates the amount of energy that can be used by the edge device for deep learning inference. We compare the performance of our proposed approach with existing state-of-the-art CNNs and data sets using different filter-ranking criteria and pruning ratios. We observe that by using DRL-driven pruning, the convolutional layers that consume relatively higher energy are pruned more as compared to their counterparts. Thereby, our approach outperforms existing approaches by reducing energy consumption and maintaining accuracy." @default.
• W4313071569 created "2023-01-06" @default.
• W4313071569 creator A5033415173 @default.
• W4313071569 creator A5034302661 @default.
• W4313071569 creator A5047327377 @default.
• W4313071569 creator A5080695525 @default.
• W4313071569 date "2023-03-15" @default.
• W4313071569 modified "2023-09-24" @default.
• W4313071569 title "Energy-Aware AI-Driven Framework for Edge-Computing-Based IoT Applications" @default.
• W4313071569 cites W2046376809 @default.
• W4313071569 cites W2123469553 @default.
• W4313071569 cites W2139418546 @default.
• W4313071569 cites W2194775991 @default.
• W4313071569 cites W2285660444 @default.
• W4313071569 cites W2886851211 @default.
• W4313071569 cites W2897303255 @default.
• W4313071569 cites W2897355299 @default.
• W4313071569 cites W2905975100 @default.
• W4313071569 cites W2914075294 @default.
• W4313071569 cites W2914440135 @default.
• W4313071569 cites W2916171158 @default.
• W4313071569 cites W2962851801 @default.
• W4313071569 cites W2964081807 @default.
• W4313071569 cites W2994881943 @default.
• W4313071569 cites W3001340915 @default.
• W4313071569 cites W3017790932 @default.
• W4313071569 cites W3144145005 @default.
• W4313071569 cites W3146736019 @default.
• W4313071569 cites W3168682364 @default.
• W4313071569 cites W3171733056 @default.
• W4313071569 cites W3195070922 @default.
• W4313071569 cites W3201902125 @default.
• W4313071569 cites W4213165097 @default.
• W4313071569 cites W4295832136 @default.
• W4313071569 doi "https://doi.org/10.1109/jiot.2022.3219202" @default.
• W4313071569 hasPublicationYear "2023" @default.
• W4313071569 type Work @default.
• W4313071569 citedByCount "1" @default.
• W4313071569 countsByYear W43130715692022 @default.
• W4313071569 crossrefType "journal-article" @default.
• W4313071569 hasAuthorship W4313071569A5033415173 @default.
• W4313071569 hasAuthorship W4313071569A5034302661 @default.
• W4313071569 hasAuthorship W4313071569A5047327377 @default.
• W4313071569 hasAuthorship W4313071569A5080695525 @default.
• W4313071569 hasBestOaLocation W43130715692 @default.
• W4313071569 hasConcept C108010975 @default.
• W4313071569 hasConcept C108583219 @default.
• W4313071569 hasConcept C111919701 @default.
• W4313071569 hasConcept C113775141 @default.
• W4313071569 hasConcept C119599485 @default.
• W4313071569 hasConcept C119857082 @default.
• W4313071569 hasConcept C120314980 @default.
• W4313071569 hasConcept C127413603 @default.
• W4313071569 hasConcept C138236772 @default.
• W4313071569 hasConcept C154945302 @default.
• W4313071569 hasConcept C162307627 @default.
• W4313071569 hasConcept C18903297 @default.
• W4313071569 hasConcept C2742236 @default.
• W4313071569 hasConcept C2778456923 @default.
• W4313071569 hasConcept C2780165032 @default.
• W4313071569 hasConcept C41008148 @default.
• W4313071569 hasConcept C6557445 @default.
• W4313071569 hasConcept C79974875 @default.
• W4313071569 hasConcept C81363708 @default.
• W4313071569 hasConcept C86803240 @default.
• W4313071569 hasConcept C97541855 @default.
• W4313071569 hasConceptScore W4313071569C108010975 @default.
• W4313071569 hasConceptScore W4313071569C108583219 @default.
• W4313071569 hasConceptScore W4313071569C111919701 @default.
• W4313071569 hasConceptScore W4313071569C113775141 @default.
• W4313071569 hasConceptScore W4313071569C119599485 @default.
• W4313071569 hasConceptScore W4313071569C119857082 @default.
• W4313071569 hasConceptScore W4313071569C120314980 @default.
• W4313071569 hasConceptScore W4313071569C127413603 @default.
• W4313071569 hasConceptScore W4313071569C138236772 @default.
• W4313071569 hasConceptScore W4313071569C154945302 @default.
• W4313071569 hasConceptScore W4313071569C162307627 @default.
• W4313071569 hasConceptScore W4313071569C18903297 @default.
• W4313071569 hasConceptScore W4313071569C2742236 @default.
• W4313071569 hasConceptScore W4313071569C2778456923 @default.
• W4313071569 hasConceptScore W4313071569C2780165032 @default.
• W4313071569 hasConceptScore W4313071569C41008148 @default.
• W4313071569 hasConceptScore W4313071569C6557445 @default.
• W4313071569 hasConceptScore W4313071569C79974875 @default.
• W4313071569 hasConceptScore W4313071569C81363708 @default.
• W4313071569 hasConceptScore W4313071569C86803240 @default.
• W4313071569 hasConceptScore W4313071569C97541855 @default.
• W4313071569 hasFunder F4320320847 @default.
• W4313071569 hasIssue "6" @default.
• W4313071569 hasLocation W43130715691 @default.
• W4313071569 hasLocation W43130715692 @default.
• W4313071569 hasOpenAccess W4313071569 @default.
• W4313071569 hasPrimaryLocation W43130715691 @default.
• W4313071569 hasRelatedWork W2337926734 @default.
• W4313071569 hasRelatedWork W2966011162 @default.
• W4313071569 hasRelatedWork W2988454569 @default.
• W4313071569 hasRelatedWork W3015440700 @default.
• W4313071569 hasRelatedWork W3094360146 @default.

• next