FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280498637> ?p ?o ?g. }

• W4280498637 endingPage "095404" @default.
• W4280498637 startingPage "095404" @default.
• W4280498637 abstract "Abstract With the development of industrialization, steel has been widely used in various fields. Current artificial intelligence (AI) methods based on steel surface images can automatically classify defect types on steel surfaces, but they still face challenges when embedded in actual industrial production. For example, the performance of convolutional networks is limited, and some categories of industrial fault data are scarce. In order to alleviate the above problems, this paper proposes a novel network structure, DRCDCT-Net. It is designed as a dual-route structure: a feature attention defect diagnosis module (FAD) and a cross-domain joint learning defect diagnosis module (CJLD). With the Feature Transformer designed as the core, the FAD is mainly responsible for handling defect classification tasks with sufficient samples. It can alleviate the problem of interdependence between features that are difficult for convolutional networks to learn. With the cross-domain joint learning network designed as the core, the CJLD is used to deal with the task of defect classification with extremely scarce samples. It can decouple the domain features of the image, so that the model can use data from different domains to learn the target data. When using the full data of both datasets, the model achieved 99.7 ± 0.2% and 90.0 ± 0.6% precision in Northeastern University (NEU)-CLS and SEVERSTAL, respectively. When using 20 images per class, it achieved 99.5 ± 0.2% and 71.3 ± 0.9% precision in NEU-CLS and SEVERSTAL, respectively. This paper proposes a novel deep learning structure. When faced with sufficient data, the model can take into account both performance and computing resource requirements. When faced with a small amount of sample data, the model can decouple data domain features and use unrelated features to learn the target data. The model proposed is more implementable and builds a bridge for the integration of AI technology and industrial defect real-time monitoring technology." @default.
• W4280498637 created "2022-05-22" @default.
• W4280498637 creator A5027669223 @default.
• W4280498637 creator A5038766727 @default.
• W4280498637 creator A5055720455 @default.
• W4280498637 date "2022-06-22" @default.
• W4280498637 modified "2023-09-29" @default.
• W4280498637 title "DRCDCT-net: a steel surface defect diagnosis method based on a dual-route cross-domain convolution-transformer network" @default.
• W4280498637 cites W2033890762 @default.
• W4280498637 cites W2072007842 @default.
• W4280498637 cites W2076844371 @default.
• W4280498637 cites W2092072518 @default.
• W4280498637 cites W2092901587 @default.
• W4280498637 cites W2147141800 @default.
• W4280498637 cites W2183341477 @default.
• W4280498637 cites W2194775991 @default.
• W4280498637 cites W2292481059 @default.
• W4280498637 cites W2435760661 @default.
• W4280498637 cites W2742452090 @default.
• W4280498637 cites W2746325398 @default.
• W4280498637 cites W2798836702 @default.
• W4280498637 cites W2922466521 @default.
• W4280498637 cites W2982083293 @default.
• W4280498637 cites W2985883399 @default.
• W4280498637 cites W3012374719 @default.
• W4280498637 cites W3033082321 @default.
• W4280498637 cites W3036193431 @default.
• W4280498637 cites W3087751617 @default.
• W4280498637 cites W3099620610 @default.
• W4280498637 cites W3100824474 @default.
• W4280498637 cites W3108566774 @default.
• W4280498637 cites W3130198311 @default.
• W4280498637 cites W3134329517 @default.
• W4280498637 cites W3134639409 @default.
• W4280498637 cites W3139248563 @default.
• W4280498637 cites W3158191900 @default.
• W4280498637 cites W3164495892 @default.
• W4280498637 cites W3171119157 @default.
• W4280498637 cites W3174027023 @default.
• W4280498637 cites W3194860875 @default.
• W4280498637 cites W3202525453 @default.
• W4280498637 cites W3208023024 @default.
• W4280498637 cites W3210048667 @default.
• W4280498637 cites W3211749075 @default.
• W4280498637 cites W3211977731 @default.
• W4280498637 cites W4200431899 @default.
• W4280498637 doi "https://doi.org/10.1088/1361-6501/ac6fb2" @default.
• W4280498637 hasPublicationYear "2022" @default.
• W4280498637 type Work @default.
• W4280498637 citedByCount "5" @default.
• W4280498637 countsByYear W42804986372023 @default.
• W4280498637 crossrefType "journal-article" @default.
• W4280498637 hasAuthorship W4280498637A5027669223 @default.
• W4280498637 hasAuthorship W4280498637A5038766727 @default.
• W4280498637 hasAuthorship W4280498637A5055720455 @default.
• W4280498637 hasConcept C108583219 @default.
• W4280498637 hasConcept C119599485 @default.
• W4280498637 hasConcept C119767625 @default.
• W4280498637 hasConcept C119857082 @default.
• W4280498637 hasConcept C124101348 @default.
• W4280498637 hasConcept C124952713 @default.
• W4280498637 hasConcept C127413603 @default.
• W4280498637 hasConcept C138885662 @default.
• W4280498637 hasConcept C142362112 @default.
• W4280498637 hasConcept C150899416 @default.
• W4280498637 hasConcept C153180895 @default.
• W4280498637 hasConcept C154945302 @default.
• W4280498637 hasConcept C165801399 @default.
• W4280498637 hasConcept C170154142 @default.
• W4280498637 hasConcept C18555067 @default.
• W4280498637 hasConcept C190729725 @default.
• W4280498637 hasConcept C2776401178 @default.
• W4280498637 hasConcept C2780980858 @default.
• W4280498637 hasConcept C41008148 @default.
• W4280498637 hasConcept C41895202 @default.
• W4280498637 hasConcept C45347329 @default.
• W4280498637 hasConcept C50644808 @default.
• W4280498637 hasConcept C66322947 @default.
• W4280498637 hasConcept C71924100 @default.
• W4280498637 hasConcept C81363708 @default.
• W4280498637 hasConceptScore W4280498637C108583219 @default.
• W4280498637 hasConceptScore W4280498637C119599485 @default.
• W4280498637 hasConceptScore W4280498637C119767625 @default.
• W4280498637 hasConceptScore W4280498637C119857082 @default.
• W4280498637 hasConceptScore W4280498637C124101348 @default.
• W4280498637 hasConceptScore W4280498637C124952713 @default.
• W4280498637 hasConceptScore W4280498637C127413603 @default.
• W4280498637 hasConceptScore W4280498637C138885662 @default.
• W4280498637 hasConceptScore W4280498637C142362112 @default.
• W4280498637 hasConceptScore W4280498637C150899416 @default.
• W4280498637 hasConceptScore W4280498637C153180895 @default.
• W4280498637 hasConceptScore W4280498637C154945302 @default.
• W4280498637 hasConceptScore W4280498637C165801399 @default.
• W4280498637 hasConceptScore W4280498637C170154142 @default.
• W4280498637 hasConceptScore W4280498637C18555067 @default.
• W4280498637 hasConceptScore W4280498637C190729725 @default.
• W4280498637 hasConceptScore W4280498637C2776401178 @default.
• W4280498637 hasConceptScore W4280498637C2780980858 @default.

• next