Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285203498> ?p ?o ?g. }
- W4285203498 endingPage "13" @default.
- W4285203498 startingPage "1" @default.
- W4285203498 abstract "Edge intelligence is an emerging technology that integrates edge computing and deep learning to bring AI to the network’s edge. It has gained wide attention for its lower network latency and better privacy preservation abilities. However, the inference of deep neural networks is computationally demanding and results in poor real-time performance, making it challenging for resource-constrained edge devices. In this paper, we propose a hierarchical deep learning model based on TreeNet to reduce the computational cost for edge devices. Based on the similarity of the classification categories, we decompose a given task into disjoint sub-tasks to reduce the complexity of the required model. Then a lightweight binary classifier is proposed for evaluating the sub-task inference result. If the inference result of a sub-task is unreliable, our system will forward the input samples to the cloud server for further processing. We also proposed a new strategy for finding and sharing common features across sub-tasks to improve training speed and accuracy. The experimental results on several popular datasets demonstrate the effectiveness of our approach in speeding up inferences while processing most of the input data with a low error rate." @default.
- W4285203498 created "2022-07-14" @default.
- W4285203498 creator A5011730425 @default.
- W4285203498 creator A5031318875 @default.
- W4285203498 creator A5033309972 @default.
- W4285203498 creator A5056792933 @default.
- W4285203498 creator A5057968753 @default.
- W4285203498 creator A5074115619 @default.
- W4285203498 date "2022-01-01" @default.
- W4285203498 modified "2023-09-27" @default.
- W4285203498 title "TreeNet Based Fast Task Decomposition for Resource-Constrained Edge Intelligence" @default.
- W4285203498 cites W2066334462 @default.
- W4285203498 cites W2108598243 @default.
- W4285203498 cites W2131681506 @default.
- W4285203498 cites W2194775991 @default.
- W4285203498 cites W2416799949 @default.
- W4285203498 cites W2533598788 @default.
- W4285203498 cites W2593768305 @default.
- W4285203498 cites W2605258629 @default.
- W4285203498 cites W2618530766 @default.
- W4285203498 cites W2742055352 @default.
- W4285203498 cites W2808168148 @default.
- W4285203498 cites W2883780447 @default.
- W4285203498 cites W2884561390 @default.
- W4285203498 cites W2946933691 @default.
- W4285203498 cites W2950865323 @default.
- W4285203498 cites W2962677625 @default.
- W4285203498 cites W2962814013 @default.
- W4285203498 cites W2962935523 @default.
- W4285203498 cites W2963122961 @default.
- W4285203498 cites W2963163009 @default.
- W4285203498 cites W2980856918 @default.
- W4285203498 cites W2981587265 @default.
- W4285203498 cites W2982083293 @default.
- W4285203498 cites W2997006708 @default.
- W4285203498 cites W3006781240 @default.
- W4285203498 cites W3011091971 @default.
- W4285203498 cites W3049663264 @default.
- W4285203498 cites W3107241502 @default.
- W4285203498 cites W3113797829 @default.
- W4285203498 cites W3192637288 @default.
- W4285203498 cites W3204647170 @default.
- W4285203498 cites W3210635777 @default.
- W4285203498 cites W4240212793 @default.
- W4285203498 cites W4243928383 @default.
- W4285203498 doi "https://doi.org/10.1109/tsc.2022.3187118" @default.
- W4285203498 hasPublicationYear "2022" @default.
- W4285203498 type Work @default.
- W4285203498 citedByCount "1" @default.
- W4285203498 countsByYear W42852034982022 @default.
- W4285203498 crossrefType "journal-article" @default.
- W4285203498 hasAuthorship W4285203498A5011730425 @default.
- W4285203498 hasAuthorship W4285203498A5031318875 @default.
- W4285203498 hasAuthorship W4285203498A5033309972 @default.
- W4285203498 hasAuthorship W4285203498A5056792933 @default.
- W4285203498 hasAuthorship W4285203498A5057968753 @default.
- W4285203498 hasAuthorship W4285203498A5074115619 @default.
- W4285203498 hasConcept C108583219 @default.
- W4285203498 hasConcept C111919701 @default.
- W4285203498 hasConcept C119857082 @default.
- W4285203498 hasConcept C124101348 @default.
- W4285203498 hasConcept C138236772 @default.
- W4285203498 hasConcept C154945302 @default.
- W4285203498 hasConcept C162307627 @default.
- W4285203498 hasConcept C162324750 @default.
- W4285203498 hasConcept C187736073 @default.
- W4285203498 hasConcept C2776214188 @default.
- W4285203498 hasConcept C2778456923 @default.
- W4285203498 hasConcept C2780451532 @default.
- W4285203498 hasConcept C41008148 @default.
- W4285203498 hasConcept C50644808 @default.
- W4285203498 hasConcept C79974875 @default.
- W4285203498 hasConceptScore W4285203498C108583219 @default.
- W4285203498 hasConceptScore W4285203498C111919701 @default.
- W4285203498 hasConceptScore W4285203498C119857082 @default.
- W4285203498 hasConceptScore W4285203498C124101348 @default.
- W4285203498 hasConceptScore W4285203498C138236772 @default.
- W4285203498 hasConceptScore W4285203498C154945302 @default.
- W4285203498 hasConceptScore W4285203498C162307627 @default.
- W4285203498 hasConceptScore W4285203498C162324750 @default.
- W4285203498 hasConceptScore W4285203498C187736073 @default.
- W4285203498 hasConceptScore W4285203498C2776214188 @default.
- W4285203498 hasConceptScore W4285203498C2778456923 @default.
- W4285203498 hasConceptScore W4285203498C2780451532 @default.
- W4285203498 hasConceptScore W4285203498C41008148 @default.
- W4285203498 hasConceptScore W4285203498C50644808 @default.
- W4285203498 hasConceptScore W4285203498C79974875 @default.
- W4285203498 hasLocation W42852034981 @default.
- W4285203498 hasOpenAccess W4285203498 @default.
- W4285203498 hasPrimaryLocation W42852034981 @default.
- W4285203498 hasRelatedWork W2534668683 @default.
- W4285203498 hasRelatedWork W2942586735 @default.
- W4285203498 hasRelatedWork W2966001425 @default.
- W4285203498 hasRelatedWork W3009018976 @default.
- W4285203498 hasRelatedWork W3106789060 @default.
- W4285203498 hasRelatedWork W3211931762 @default.
- W4285203498 hasRelatedWork W4223535265 @default.
- W4285203498 hasRelatedWork W4225757241 @default.