Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042900698> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3042900698 abstract "Crack detection is of pivotal importance in civil engineering and other related applications. Traditional methods of human inspection are tedious and severely limited. Automated crack detection by conventional image processing techniques is challenging due to their inability to discriminate crack features from background noise. Inhomogeneous lighting, shadows, and surface finish hinder the performance of digital image processing methods. The use of convolutional neural networks has helped achieve remarkably better results in the field of computer vision. Ensemble learning is an approach to aggregate the results of a number of individual models for classification or regression. Ensemble learning for crack detection has been implemented using deep convolutional neural networks (DCNN) in this paper. The models are evaluated on a number of performance metrics, namely-(i) accuracy, (ii) precision, (iii) recall (iv) Matthews correlation coefficient (MCC), (v) AUROC, and (vi) F1 score. Experimental results show the robustness of the ensembling method and offer promising scope in crack detection. They outperform the current best performance on open source concrete crack dataset. The ensemble models achieved much better performance than their individual counterparts with the best ensemble achieving a validation accuracy of 99.67%." @default.
- W3042900698 created "2020-07-23" @default.
- W3042900698 creator A5039551729 @default.
- W3042900698 creator A5050394026 @default.
- W3042900698 creator A5080931121 @default.
- W3042900698 creator A5085814878 @default.
- W3042900698 date "2020-06-01" @default.
- W3042900698 modified "2023-09-27" @default.
- W3042900698 title "Ensemble learning-based approach for crack detection using CNN" @default.
- W3042900698 cites W2084524982 @default.
- W3042900698 cites W2091149439 @default.
- W3042900698 cites W2100805904 @default.
- W3042900698 cites W2108598243 @default.
- W3042900698 cites W2154805199 @default.
- W3042900698 cites W2289283324 @default.
- W3042900698 cites W2511065100 @default.
- W3042900698 cites W2598457882 @default.
- W3042900698 cites W2914870198 @default.
- W3042900698 cites W2942900320 @default.
- W3042900698 cites W3006436762 @default.
- W3042900698 cites W4239808474 @default.
- W3042900698 doi "https://doi.org/10.1109/icoei48184.2020.9143035" @default.
- W3042900698 hasPublicationYear "2020" @default.
- W3042900698 type Work @default.
- W3042900698 sameAs 3042900698 @default.
- W3042900698 citedByCount "2" @default.
- W3042900698 countsByYear W30429006982022 @default.
- W3042900698 countsByYear W30429006982023 @default.
- W3042900698 crossrefType "proceedings-article" @default.
- W3042900698 hasAuthorship W3042900698A5039551729 @default.
- W3042900698 hasAuthorship W3042900698A5050394026 @default.
- W3042900698 hasAuthorship W3042900698A5080931121 @default.
- W3042900698 hasAuthorship W3042900698A5085814878 @default.
- W3042900698 hasConcept C104317684 @default.
- W3042900698 hasConcept C108583219 @default.
- W3042900698 hasConcept C119857082 @default.
- W3042900698 hasConcept C119898033 @default.
- W3042900698 hasConcept C153180895 @default.
- W3042900698 hasConcept C154945302 @default.
- W3042900698 hasConcept C185592680 @default.
- W3042900698 hasConcept C41008148 @default.
- W3042900698 hasConcept C45942800 @default.
- W3042900698 hasConcept C50644808 @default.
- W3042900698 hasConcept C55493867 @default.
- W3042900698 hasConcept C63479239 @default.
- W3042900698 hasConcept C81363708 @default.
- W3042900698 hasConceptScore W3042900698C104317684 @default.
- W3042900698 hasConceptScore W3042900698C108583219 @default.
- W3042900698 hasConceptScore W3042900698C119857082 @default.
- W3042900698 hasConceptScore W3042900698C119898033 @default.
- W3042900698 hasConceptScore W3042900698C153180895 @default.
- W3042900698 hasConceptScore W3042900698C154945302 @default.
- W3042900698 hasConceptScore W3042900698C185592680 @default.
- W3042900698 hasConceptScore W3042900698C41008148 @default.
- W3042900698 hasConceptScore W3042900698C45942800 @default.
- W3042900698 hasConceptScore W3042900698C50644808 @default.
- W3042900698 hasConceptScore W3042900698C55493867 @default.
- W3042900698 hasConceptScore W3042900698C63479239 @default.
- W3042900698 hasConceptScore W3042900698C81363708 @default.
- W3042900698 hasLocation W30429006981 @default.
- W3042900698 hasOpenAccess W3042900698 @default.
- W3042900698 hasPrimaryLocation W30429006981 @default.
- W3042900698 hasRelatedWork W2810053714 @default.
- W3042900698 hasRelatedWork W3034006481 @default.
- W3042900698 hasRelatedWork W3124943098 @default.
- W3042900698 hasRelatedWork W3136979370 @default.
- W3042900698 hasRelatedWork W3162132941 @default.
- W3042900698 hasRelatedWork W4285741730 @default.
- W3042900698 hasRelatedWork W4308112567 @default.
- W3042900698 hasRelatedWork W4318677156 @default.
- W3042900698 hasRelatedWork W4321369474 @default.
- W3042900698 hasRelatedWork W4382345315 @default.
- W3042900698 isParatext "false" @default.
- W3042900698 isRetracted "false" @default.
- W3042900698 magId "3042900698" @default.
- W3042900698 workType "article" @default.