Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891391275> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2891391275 endingPage "489" @default.
- W2891391275 startingPage "482" @default.
- W2891391275 abstract "Abstract Feature extraction and feature selection are vital steps to construct an intelligent diagnosis system for classifying the weld flaws from an X-ray image. Deep learning has been successfully used in image analysis and automatic object recognition. It has good performance for learning more representative hierarchical features that are more sensitive to classification. However, there are still few applications of deep learning in feature learning for classifying different weld flaws, and few studies have been performed to compare the feature classification ability of different feature extraction methods. In this paper, we developed a model based on a deep convolutional neural network (DCNN) to extract the deep features directly from X-ray images. To validate the effectiveness of deep features, we cropped patches from the X-ray images as the learning dataset. Furthermore, considering the imbalance of the number of patches with different weld flaws, we used 3 types of resampling methods for 3 balanced datasets. Using the datasets, we compared the classification ability of 5 types of features extracted using traditional methods and deep learning. The best results were obtained for the deep features from the proposed DCNN model, achieving an accuracy of 97.2%, which is considerably higher than that obtained using the traditional feature extraction methods. We believe that the proposed model could be used to help workers evaluate X-ray images more intelligently." @default.
- W2891391275 created "2018-09-27" @default.
- W2891391275 creator A5020554327 @default.
- W2891391275 creator A5037592037 @default.
- W2891391275 creator A5039480817 @default.
- W2891391275 creator A5069815704 @default.
- W2891391275 date "2019-01-01" @default.
- W2891391275 modified "2023-10-17" @default.
- W2891391275 title "Deep features based on a DCNN model for classifying imbalanced weld flaw types" @default.
- W2891391275 cites W1968405583 @default.
- W2891391275 cites W1976554299 @default.
- W2891391275 cites W1976644809 @default.
- W2891391275 cites W1982271772 @default.
- W2891391275 cites W1986959058 @default.
- W2891391275 cites W1989180599 @default.
- W2891391275 cites W2015452969 @default.
- W2891391275 cites W2018963090 @default.
- W2891391275 cites W2030832258 @default.
- W2891391275 cites W2044465660 @default.
- W2891391275 cites W2050202310 @default.
- W2891391275 cites W2065410047 @default.
- W2891391275 cites W2069289135 @default.
- W2891391275 cites W2074866945 @default.
- W2891391275 cites W2102423238 @default.
- W2891391275 cites W2118978333 @default.
- W2891391275 cites W2132763323 @default.
- W2891391275 cites W2141697870 @default.
- W2891391275 cites W2148143831 @default.
- W2891391275 cites W2155995258 @default.
- W2891391275 cites W2171827999 @default.
- W2891391275 cites W2172928000 @default.
- W2891391275 cites W2175342987 @default.
- W2891391275 cites W2253429366 @default.
- W2891391275 cites W2283340597 @default.
- W2891391275 cites W2283853326 @default.
- W2891391275 cites W2299565249 @default.
- W2891391275 cites W2549196305 @default.
- W2891391275 cites W2613000917 @default.
- W2891391275 cites W2622826443 @default.
- W2891391275 cites W2735326783 @default.
- W2891391275 cites W2738563279 @default.
- W2891391275 cites W2757455114 @default.
- W2891391275 cites W2767827638 @default.
- W2891391275 doi "https://doi.org/10.1016/j.measurement.2018.09.011" @default.
- W2891391275 hasPublicationYear "2019" @default.
- W2891391275 type Work @default.
- W2891391275 sameAs 2891391275 @default.
- W2891391275 citedByCount "78" @default.
- W2891391275 countsByYear W28913912752019 @default.
- W2891391275 countsByYear W28913912752020 @default.
- W2891391275 countsByYear W28913912752021 @default.
- W2891391275 countsByYear W28913912752022 @default.
- W2891391275 countsByYear W28913912752023 @default.
- W2891391275 crossrefType "journal-article" @default.
- W2891391275 hasAuthorship W2891391275A5020554327 @default.
- W2891391275 hasAuthorship W2891391275A5037592037 @default.
- W2891391275 hasAuthorship W2891391275A5039480817 @default.
- W2891391275 hasAuthorship W2891391275A5069815704 @default.
- W2891391275 hasConcept C127413603 @default.
- W2891391275 hasConcept C153180895 @default.
- W2891391275 hasConcept C154945302 @default.
- W2891391275 hasConcept C19474535 @default.
- W2891391275 hasConcept C41008148 @default.
- W2891391275 hasConcept C78519656 @default.
- W2891391275 hasConceptScore W2891391275C127413603 @default.
- W2891391275 hasConceptScore W2891391275C153180895 @default.
- W2891391275 hasConceptScore W2891391275C154945302 @default.
- W2891391275 hasConceptScore W2891391275C19474535 @default.
- W2891391275 hasConceptScore W2891391275C41008148 @default.
- W2891391275 hasConceptScore W2891391275C78519656 @default.
- W2891391275 hasFunder F4320321001 @default.
- W2891391275 hasFunder F4320335777 @default.
- W2891391275 hasLocation W28913912751 @default.
- W2891391275 hasOpenAccess W2891391275 @default.
- W2891391275 hasPrimaryLocation W28913912751 @default.
- W2891391275 hasRelatedWork W1978450727 @default.
- W2891391275 hasRelatedWork W2033914206 @default.
- W2891391275 hasRelatedWork W2146076056 @default.
- W2891391275 hasRelatedWork W2163831990 @default.
- W2891391275 hasRelatedWork W2378160586 @default.
- W2891391275 hasRelatedWork W2899084033 @default.
- W2891391275 hasRelatedWork W3003836766 @default.
- W2891391275 hasRelatedWork W3107474891 @default.
- W2891391275 hasRelatedWork W4244943737 @default.
- W2891391275 hasRelatedWork W2289108895 @default.
- W2891391275 hasVolume "131" @default.
- W2891391275 isParatext "false" @default.
- W2891391275 isRetracted "false" @default.
- W2891391275 magId "2891391275" @default.
- W2891391275 workType "article" @default.