Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044944261> ?p ?o ?g. }
- W3044944261 endingPage "120109" @default.
- W3044944261 startingPage "120109" @default.
- W3044944261 abstract "Impact echo (IE) is a common nondestructive evaluation (NDE) method to detect subsurface defects in concrete bridge decks. The conventional approach for analyzing the IE data requires user expertise to define analysis parameters that could hinder broad field implementation. In this paper, the feasibility of using deep learning models (DLMs) for autonomous subsurface defect detection in bridge decks using IE has been investigated. A set of eight laboratory-made reinforced concrete bridge specimens with artificial defects were constructed at the Federal Highway Administration Advanced Sensing Technology NDE laboratory. A total number of 2016 of IE data was collected from these specimens. A one-dimensional (1D) convolutional neural network (CNN), and a 1D recurrent neural network using bidirectional long-short term memory units, were developed and applied on the IE data. In addition, two-dimensional (2D) world renowned CNNs were applied on the 2D representatives of the IE data, i.e., spectrograms. The proposed 1D CNN was the most accurate model achieving an overall accuracy of 0.88 by classifying 0.70 of the defects and 0.95 of the sound regions correctly. The proposed 1DCNN was superior to previous machine learning models that were previously used for IE classification. The results of this study showed the feasibility and the potentials of the DLMs for subsurface defect detection." @default.
- W3044944261 created "2020-07-29" @default.
- W3044944261 creator A5002475266 @default.
- W3044944261 creator A5067820079 @default.
- W3044944261 date "2020-12-01" @default.
- W3044944261 modified "2023-10-17" @default.
- W3044944261 title "Deep learning models for bridge deck evaluation using impact echo" @default.
- W3044944261 cites W1504955719 @default.
- W3044944261 cites W1677182931 @default.
- W3044944261 cites W1965969913 @default.
- W3044944261 cites W2014549269 @default.
- W3044944261 cites W2036415868 @default.
- W3044944261 cites W2078047501 @default.
- W3044944261 cites W2079156732 @default.
- W3044944261 cites W2097117768 @default.
- W3044944261 cites W2108598243 @default.
- W3044944261 cites W2109987419 @default.
- W3044944261 cites W2128880484 @default.
- W3044944261 cites W2131774270 @default.
- W3044944261 cites W2188183693 @default.
- W3044944261 cites W2194775991 @default.
- W3044944261 cites W2307346736 @default.
- W3044944261 cites W2588727045 @default.
- W3044944261 cites W2613338636 @default.
- W3044944261 cites W2737163017 @default.
- W3044944261 cites W2741268125 @default.
- W3044944261 cites W2744334213 @default.
- W3044944261 cites W2756789966 @default.
- W3044944261 cites W2759792922 @default.
- W3044944261 cites W2803542800 @default.
- W3044944261 cites W2805039329 @default.
- W3044944261 cites W2837839554 @default.
- W3044944261 cites W2887597701 @default.
- W3044944261 cites W2888803582 @default.
- W3044944261 cites W2891201238 @default.
- W3044944261 cites W2891363856 @default.
- W3044944261 cites W2891519189 @default.
- W3044944261 cites W2899803215 @default.
- W3044944261 cites W2905163589 @default.
- W3044944261 cites W2913119512 @default.
- W3044944261 cites W2920377701 @default.
- W3044944261 cites W2942829333 @default.
- W3044944261 cites W2943686015 @default.
- W3044944261 cites W2945697543 @default.
- W3044944261 cites W2946369859 @default.
- W3044944261 cites W2963804033 @default.
- W3044944261 cites W4236607908 @default.
- W3044944261 cites W618618512 @default.
- W3044944261 cites W96161441 @default.
- W3044944261 doi "https://doi.org/10.1016/j.conbuildmat.2020.120109" @default.
- W3044944261 hasPublicationYear "2020" @default.
- W3044944261 type Work @default.
- W3044944261 sameAs 3044944261 @default.
- W3044944261 citedByCount "46" @default.
- W3044944261 countsByYear W30449442612021 @default.
- W3044944261 countsByYear W30449442612022 @default.
- W3044944261 countsByYear W30449442612023 @default.
- W3044944261 crossrefType "journal-article" @default.
- W3044944261 hasAuthorship W3044944261A5002475266 @default.
- W3044944261 hasAuthorship W3044944261A5067820079 @default.
- W3044944261 hasConcept C100776233 @default.
- W3044944261 hasConcept C108583219 @default.
- W3044944261 hasConcept C126322002 @default.
- W3044944261 hasConcept C127413603 @default.
- W3044944261 hasConcept C153180895 @default.
- W3044944261 hasConcept C154945302 @default.
- W3044944261 hasConcept C2779426996 @default.
- W3044944261 hasConcept C31258907 @default.
- W3044944261 hasConcept C41008148 @default.
- W3044944261 hasConcept C45273575 @default.
- W3044944261 hasConcept C50644808 @default.
- W3044944261 hasConcept C66938386 @default.
- W3044944261 hasConcept C71924100 @default.
- W3044944261 hasConcept C81363708 @default.
- W3044944261 hasConceptScore W3044944261C100776233 @default.
- W3044944261 hasConceptScore W3044944261C108583219 @default.
- W3044944261 hasConceptScore W3044944261C126322002 @default.
- W3044944261 hasConceptScore W3044944261C127413603 @default.
- W3044944261 hasConceptScore W3044944261C153180895 @default.
- W3044944261 hasConceptScore W3044944261C154945302 @default.
- W3044944261 hasConceptScore W3044944261C2779426996 @default.
- W3044944261 hasConceptScore W3044944261C31258907 @default.
- W3044944261 hasConceptScore W3044944261C41008148 @default.
- W3044944261 hasConceptScore W3044944261C45273575 @default.
- W3044944261 hasConceptScore W3044944261C50644808 @default.
- W3044944261 hasConceptScore W3044944261C66938386 @default.
- W3044944261 hasConceptScore W3044944261C71924100 @default.
- W3044944261 hasConceptScore W3044944261C81363708 @default.
- W3044944261 hasFunder F4320332393 @default.
- W3044944261 hasLocation W30449442611 @default.
- W3044944261 hasOpenAccess W3044944261 @default.
- W3044944261 hasPrimaryLocation W30449442611 @default.
- W3044944261 hasRelatedWork W2731899572 @default.
- W3044944261 hasRelatedWork W2732542196 @default.
- W3044944261 hasRelatedWork W2738221750 @default.
- W3044944261 hasRelatedWork W2999805992 @default.
- W3044944261 hasRelatedWork W3116150086 @default.
- W3044944261 hasRelatedWork W3133861977 @default.