Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212241818> ?p ?o ?g. }
- W3212241818 endingPage "7506" @default.
- W3212241818 startingPage "7506" @default.
- W3212241818 abstract "Automatic flood detection may be an important component for triggering damage control systems and minimizing the risk of social or economic impacts caused by flooding. Riverside images from regular cameras are a widely available resource that can be used for tackling this problem. Nevertheless, state-of-the-art neural networks, the most suitable approach for this type of computer vision task, are usually resource-consuming, which poses a challenge for deploying these models within low-capability Internet of Things (IoT) devices with unstable internet connections. In this work, we propose a deep neural network (DNN) architecture pruning algorithm capable of finding a pruned version of a given DNN within a user-specified memory footprint. Our results demonstrate that our proposed algorithm can find a pruned DNN model with the specified memory footprint with little to no degradation of its segmentation performance. Finally, we show that our algorithm can be used in a memory-constraint wireless sensor network (WSN) employed to detect flooding events of urban rivers, and the resulting pruned models have competitive results compared with the original models." @default.
- W3212241818 created "2021-11-22" @default.
- W3212241818 creator A5011424640 @default.
- W3212241818 creator A5023928945 @default.
- W3212241818 creator A5068357965 @default.
- W3212241818 creator A5090999980 @default.
- W3212241818 date "2021-11-12" @default.
- W3212241818 modified "2023-10-17" @default.
- W3212241818 title "Memory-Based Pruning of Deep Neural Networks for IoT Devices Applied to Flood Detection" @default.
- W3212241818 cites W1745334888 @default.
- W3212241818 cites W1861492603 @default.
- W3212241818 cites W1901129140 @default.
- W3212241818 cites W1998198053 @default.
- W3212241818 cites W2110379134 @default.
- W3212241818 cites W2397508230 @default.
- W3212241818 cites W2605903226 @default.
- W3212241818 cites W2619420887 @default.
- W3212241818 cites W2772049907 @default.
- W3212241818 cites W2791088620 @default.
- W3212241818 cites W2905975100 @default.
- W3212241818 cites W2953951737 @default.
- W3212241818 cites W2964233199 @default.
- W3212241818 cites W2994582029 @default.
- W3212241818 cites W3010829258 @default.
- W3212241818 cites W3016889634 @default.
- W3212241818 cites W3092580847 @default.
- W3212241818 cites W3106913724 @default.
- W3212241818 cites W3171186717 @default.
- W3212241818 cites W3195589214 @default.
- W3212241818 doi "https://doi.org/10.3390/s21227506" @default.
- W3212241818 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8622476" @default.
- W3212241818 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34833583" @default.
- W3212241818 hasPublicationYear "2021" @default.
- W3212241818 type Work @default.
- W3212241818 sameAs 3212241818 @default.
- W3212241818 citedByCount "6" @default.
- W3212241818 countsByYear W32122418182022 @default.
- W3212241818 countsByYear W32122418182023 @default.
- W3212241818 crossrefType "journal-article" @default.
- W3212241818 hasAuthorship W3212241818A5011424640 @default.
- W3212241818 hasAuthorship W3212241818A5023928945 @default.
- W3212241818 hasAuthorship W3212241818A5068357965 @default.
- W3212241818 hasAuthorship W3212241818A5090999980 @default.
- W3212241818 hasBestOaLocation W32122418181 @default.
- W3212241818 hasConcept C108010975 @default.
- W3212241818 hasConcept C108583219 @default.
- W3212241818 hasConcept C111919701 @default.
- W3212241818 hasConcept C119857082 @default.
- W3212241818 hasConcept C132943942 @default.
- W3212241818 hasConcept C147168706 @default.
- W3212241818 hasConcept C151730666 @default.
- W3212241818 hasConcept C154945302 @default.
- W3212241818 hasConcept C15744967 @default.
- W3212241818 hasConcept C186594467 @default.
- W3212241818 hasConcept C24590314 @default.
- W3212241818 hasConcept C31258907 @default.
- W3212241818 hasConcept C41008148 @default.
- W3212241818 hasConcept C50644808 @default.
- W3212241818 hasConcept C542102704 @default.
- W3212241818 hasConcept C6557445 @default.
- W3212241818 hasConcept C74912251 @default.
- W3212241818 hasConcept C79403827 @default.
- W3212241818 hasConcept C86803240 @default.
- W3212241818 hasConcept C89600930 @default.
- W3212241818 hasConceptScore W3212241818C108010975 @default.
- W3212241818 hasConceptScore W3212241818C108583219 @default.
- W3212241818 hasConceptScore W3212241818C111919701 @default.
- W3212241818 hasConceptScore W3212241818C119857082 @default.
- W3212241818 hasConceptScore W3212241818C132943942 @default.
- W3212241818 hasConceptScore W3212241818C147168706 @default.
- W3212241818 hasConceptScore W3212241818C151730666 @default.
- W3212241818 hasConceptScore W3212241818C154945302 @default.
- W3212241818 hasConceptScore W3212241818C15744967 @default.
- W3212241818 hasConceptScore W3212241818C186594467 @default.
- W3212241818 hasConceptScore W3212241818C24590314 @default.
- W3212241818 hasConceptScore W3212241818C31258907 @default.
- W3212241818 hasConceptScore W3212241818C41008148 @default.
- W3212241818 hasConceptScore W3212241818C50644808 @default.
- W3212241818 hasConceptScore W3212241818C542102704 @default.
- W3212241818 hasConceptScore W3212241818C6557445 @default.
- W3212241818 hasConceptScore W3212241818C74912251 @default.
- W3212241818 hasConceptScore W3212241818C79403827 @default.
- W3212241818 hasConceptScore W3212241818C86803240 @default.
- W3212241818 hasConceptScore W3212241818C89600930 @default.
- W3212241818 hasFunder F4320320997 @default.
- W3212241818 hasIssue "22" @default.
- W3212241818 hasLocation W32122418181 @default.
- W3212241818 hasLocation W32122418182 @default.
- W3212241818 hasLocation W32122418183 @default.
- W3212241818 hasLocation W32122418184 @default.
- W3212241818 hasOpenAccess W3212241818 @default.
- W3212241818 hasPrimaryLocation W32122418181 @default.
- W3212241818 hasRelatedWork W2790662084 @default.
- W3212241818 hasRelatedWork W2972287445 @default.
- W3212241818 hasRelatedWork W3014300295 @default.
- W3212241818 hasRelatedWork W4223943233 @default.
- W3212241818 hasRelatedWork W4225161397 @default.
- W3212241818 hasRelatedWork W4312200629 @default.