Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284958772> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4284958772 endingPage "105130" @default.
- W4284958772 startingPage "105130" @default.
- W4284958772 abstract "One of the emerging and powerful tools of Artificial Intelligence (AI) in computer vision is Convolutional Neural Network (CNN) which can outperform traditional algorithms for crack detection by extracting unique image features. The segmentation of crack images is intensively affected by the imbalanced presence of crack and non-crack elements. Tackling the influence of class imbalanced datasets on the training network, we proposed an additive attention gate-based network architecture called Crack Segmentation Network-II (CSN-II). CSN-II has fewer encoder–decoder blocks with improved accuracy and reduced computational cost as compared to other crack segmentation network architectures. An additive attention gate is used as a connecting block between the encoder–decoder section of CSN-II that focuses on significant crack regions in the image. The network performance is evaluated on two different crack image datasets i.e., MSCI (500 images) and CFD (118 images). The experimental results showed that the CSN-II architecture using a local balanced cross-entropy (LBCE) loss function has achieved 98.48 % and 94.39 % mean accuracy for MSCI and CFD dataset, respectively. Furthermore, extensive research experiments are performed on MSCI and CFD datasets to delineate the best combination of five network architectures (U-Net, SegNet, DeepLabv3＋, CSN, and CSN-II) and twelve loss functions for crack segmentation to observe the efficiency for tackling imbalanced dataset." @default.
- W4284958772 created "2022-07-10" @default.
- W4284958772 creator A5018208521 @default.
- W4284958772 creator A5030196845 @default.
- W4284958772 creator A5050429559 @default.
- W4284958772 creator A5065195068 @default.
- W4284958772 creator A5075948725 @default.
- W4284958772 date "2022-09-01" @default.
- W4284958772 modified "2023-10-03" @default.
- W4284958772 title "Crack Segmentation Network using Additive Attention Gate—CSN-II" @default.
- W4284958772 cites W1498436455 @default.
- W4284958772 cites W2023639956 @default.
- W4284958772 cites W2104167780 @default.
- W4284958772 cites W2114268578 @default.
- W4284958772 cites W2148143831 @default.
- W4284958772 cites W2407692387 @default.
- W4284958772 cites W2734349601 @default.
- W4284958772 cites W2884561390 @default.
- W4284958772 cites W2899242765 @default.
- W4284958772 cites W2900519066 @default.
- W4284958772 cites W2903617078 @default.
- W4284958772 cites W2956776634 @default.
- W4284958772 cites W2963043051 @default.
- W4284958772 cites W2963881378 @default.
- W4284958772 cites W2979396152 @default.
- W4284958772 cites W2981850489 @default.
- W4284958772 cites W2998291112 @default.
- W4284958772 cites W3016245448 @default.
- W4284958772 cites W3036991312 @default.
- W4284958772 cites W3044468720 @default.
- W4284958772 cites W3049688872 @default.
- W4284958772 cites W3082043672 @default.
- W4284958772 cites W3096030187 @default.
- W4284958772 cites W3099564553 @default.
- W4284958772 cites W3104725225 @default.
- W4284958772 cites W3124451475 @default.
- W4284958772 cites W3152753009 @default.
- W4284958772 cites W3162760148 @default.
- W4284958772 doi "https://doi.org/10.1016/j.engappai.2022.105130" @default.
- W4284958772 hasPublicationYear "2022" @default.
- W4284958772 type Work @default.
- W4284958772 citedByCount "5" @default.
- W4284958772 countsByYear W42849587722023 @default.
- W4284958772 crossrefType "journal-article" @default.
- W4284958772 hasAuthorship W4284958772A5018208521 @default.
- W4284958772 hasAuthorship W4284958772A5030196845 @default.
- W4284958772 hasAuthorship W4284958772A5050429559 @default.
- W4284958772 hasAuthorship W4284958772A5065195068 @default.
- W4284958772 hasAuthorship W4284958772A5075948725 @default.
- W4284958772 hasConcept C108583219 @default.
- W4284958772 hasConcept C111919701 @default.
- W4284958772 hasConcept C118505674 @default.
- W4284958772 hasConcept C119857082 @default.
- W4284958772 hasConcept C153180895 @default.
- W4284958772 hasConcept C154945302 @default.
- W4284958772 hasConcept C167981619 @default.
- W4284958772 hasConcept C193415008 @default.
- W4284958772 hasConcept C38652104 @default.
- W4284958772 hasConcept C41008148 @default.
- W4284958772 hasConcept C50644808 @default.
- W4284958772 hasConcept C81363708 @default.
- W4284958772 hasConcept C89600930 @default.
- W4284958772 hasConceptScore W4284958772C108583219 @default.
- W4284958772 hasConceptScore W4284958772C111919701 @default.
- W4284958772 hasConceptScore W4284958772C118505674 @default.
- W4284958772 hasConceptScore W4284958772C119857082 @default.
- W4284958772 hasConceptScore W4284958772C153180895 @default.
- W4284958772 hasConceptScore W4284958772C154945302 @default.
- W4284958772 hasConceptScore W4284958772C167981619 @default.
- W4284958772 hasConceptScore W4284958772C193415008 @default.
- W4284958772 hasConceptScore W4284958772C38652104 @default.
- W4284958772 hasConceptScore W4284958772C41008148 @default.
- W4284958772 hasConceptScore W4284958772C50644808 @default.
- W4284958772 hasConceptScore W4284958772C81363708 @default.
- W4284958772 hasConceptScore W4284958772C89600930 @default.
- W4284958772 hasLocation W42849587721 @default.
- W4284958772 hasOpenAccess W4284958772 @default.
- W4284958772 hasPrimaryLocation W42849587721 @default.
- W4284958772 hasRelatedWork W2517027266 @default.
- W4284958772 hasRelatedWork W2731899572 @default.
- W4284958772 hasRelatedWork W2999805992 @default.
- W4284958772 hasRelatedWork W3091976719 @default.
- W4284958772 hasRelatedWork W3116150086 @default.
- W4284958772 hasRelatedWork W3133861977 @default.
- W4284958772 hasRelatedWork W4200173597 @default.
- W4284958772 hasRelatedWork W4312417841 @default.
- W4284958772 hasRelatedWork W4321369474 @default.
- W4284958772 hasRelatedWork W4380075502 @default.
- W4284958772 hasVolume "114" @default.
- W4284958772 isParatext "false" @default.
- W4284958772 isRetracted "false" @default.
- W4284958772 workType "article" @default.