Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210366566> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4210366566 endingPage "333" @default.
- W4210366566 startingPage "333" @default.
- W4210366566 abstract "More frequent and thorough inspection of sewer pipes has the potential to save billions in utilities. However, the amount and quality of inspection are impeded by an imprecise and highly subjective manual process. It involves technicians judging stretches of sewer based on video from remote-controlled robots. Determining the state of sewer pipes based on these videos entails a great deal of ambiguity. Furthermore, the frequency with which the different defects occur differs a lot, leading to highly imbalanced datasets. Such datasets represent a poor basis for automating the labeling process using supervised learning. With this paper we explore the potential of self-supervision as a method for reducing the need for large numbers of well-balanced labels. First, our models learn to represent the data distribution using more than a million unlabeled images, then a small number of labeled examples are used to learn a mapping from the learned representations to a relevant target variable, in this case, water level. We choose a convolutional Autoencoder, a Variational Autoencoder and a Vector-Quantised Variational Autoencoder as the basis for our experiments. The best representations are shown to be learned by the classic Autoencoder with the Multi-Layer Perceptron achieving a Mean Absolute Error of 9.93. This is an improvement of 9.62 over the fully supervised baseline." @default.
- W4210366566 created "2022-02-08" @default.
- W4210366566 creator A5014741376 @default.
- W4210366566 creator A5022176859 @default.
- W4210366566 creator A5042215335 @default.
- W4210366566 creator A5042876566 @default.
- W4210366566 creator A5044183257 @default.
- W4210366566 creator A5090952399 @default.
- W4210366566 date "2022-01-24" @default.
- W4210366566 modified "2023-10-14" @default.
- W4210366566 title "Autoencoders for Semi-Supervised Water Level Modeling in Sewer Pipes with Sparse Labeled Data" @default.
- W4210366566 cites W1566135517 @default.
- W4210366566 cites W1925745898 @default.
- W4210366566 cites W2012444155 @default.
- W4210366566 cites W2039183981 @default.
- W4210366566 cites W2085477122 @default.
- W4210366566 cites W2124386111 @default.
- W4210366566 cites W2128880484 @default.
- W4210366566 cites W2509322645 @default.
- W4210366566 cites W2618530766 @default.
- W4210366566 cites W2792146897 @default.
- W4210366566 cites W2792741217 @default.
- W4210366566 cites W2922005503 @default.
- W4210366566 cites W2982284503 @default.
- W4210366566 cites W2995360785 @default.
- W4210366566 cites W3110305765 @default.
- W4210366566 cites W3111817041 @default.
- W4210366566 cites W3115724051 @default.
- W4210366566 doi "https://doi.org/10.3390/w14030333" @default.
- W4210366566 hasPublicationYear "2022" @default.
- W4210366566 type Work @default.
- W4210366566 citedByCount "1" @default.
- W4210366566 countsByYear W42103665662022 @default.
- W4210366566 crossrefType "journal-article" @default.
- W4210366566 hasAuthorship W4210366566A5014741376 @default.
- W4210366566 hasAuthorship W4210366566A5022176859 @default.
- W4210366566 hasAuthorship W4210366566A5042215335 @default.
- W4210366566 hasAuthorship W4210366566A5042876566 @default.
- W4210366566 hasAuthorship W4210366566A5044183257 @default.
- W4210366566 hasAuthorship W4210366566A5090952399 @default.
- W4210366566 hasBestOaLocation W42103665661 @default.
- W4210366566 hasConcept C101738243 @default.
- W4210366566 hasConcept C111368507 @default.
- W4210366566 hasConcept C111919701 @default.
- W4210366566 hasConcept C119857082 @default.
- W4210366566 hasConcept C124101348 @default.
- W4210366566 hasConcept C12426560 @default.
- W4210366566 hasConcept C12725497 @default.
- W4210366566 hasConcept C127313418 @default.
- W4210366566 hasConcept C153180895 @default.
- W4210366566 hasConcept C154945302 @default.
- W4210366566 hasConcept C199360897 @default.
- W4210366566 hasConcept C2524010 @default.
- W4210366566 hasConcept C2780522230 @default.
- W4210366566 hasConcept C33923547 @default.
- W4210366566 hasConcept C41008148 @default.
- W4210366566 hasConcept C50644808 @default.
- W4210366566 hasConcept C81363708 @default.
- W4210366566 hasConcept C98045186 @default.
- W4210366566 hasConceptScore W4210366566C101738243 @default.
- W4210366566 hasConceptScore W4210366566C111368507 @default.
- W4210366566 hasConceptScore W4210366566C111919701 @default.
- W4210366566 hasConceptScore W4210366566C119857082 @default.
- W4210366566 hasConceptScore W4210366566C124101348 @default.
- W4210366566 hasConceptScore W4210366566C12426560 @default.
- W4210366566 hasConceptScore W4210366566C12725497 @default.
- W4210366566 hasConceptScore W4210366566C127313418 @default.
- W4210366566 hasConceptScore W4210366566C153180895 @default.
- W4210366566 hasConceptScore W4210366566C154945302 @default.
- W4210366566 hasConceptScore W4210366566C199360897 @default.
- W4210366566 hasConceptScore W4210366566C2524010 @default.
- W4210366566 hasConceptScore W4210366566C2780522230 @default.
- W4210366566 hasConceptScore W4210366566C33923547 @default.
- W4210366566 hasConceptScore W4210366566C41008148 @default.
- W4210366566 hasConceptScore W4210366566C50644808 @default.
- W4210366566 hasConceptScore W4210366566C81363708 @default.
- W4210366566 hasConceptScore W4210366566C98045186 @default.
- W4210366566 hasIssue "3" @default.
- W4210366566 hasLocation W42103665661 @default.
- W4210366566 hasLocation W42103665662 @default.
- W4210366566 hasLocation W42103665663 @default.
- W4210366566 hasOpenAccess W4210366566 @default.
- W4210366566 hasPrimaryLocation W42103665661 @default.
- W4210366566 hasRelatedWork W2292254049 @default.
- W4210366566 hasRelatedWork W2592385986 @default.
- W4210366566 hasRelatedWork W2610906757 @default.
- W4210366566 hasRelatedWork W2897995864 @default.
- W4210366566 hasRelatedWork W2998168123 @default.
- W4210366566 hasRelatedWork W3027997911 @default.
- W4210366566 hasRelatedWork W4281924768 @default.
- W4210366566 hasRelatedWork W4287083450 @default.
- W4210366566 hasRelatedWork W4287776258 @default.
- W4210366566 hasRelatedWork W4287995534 @default.
- W4210366566 hasVolume "14" @default.
- W4210366566 isParatext "false" @default.
- W4210366566 isRetracted "false" @default.
- W4210366566 workType "article" @default.