Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360616562> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4360616562 endingPage "477" @default.
- W4360616562 startingPage "464" @default.
- W4360616562 abstract "Impact echo (IE) is one of the most frequently used nondestructive evaluation (NDE) techniques for detecting subsurface defects such as delamination, honeycombing, and voids in concrete structures. In the conventional analysis of IE data, the time-domain signal is transformed into the frequency domain and the frequency content is used to estimate the presence and nature of the defect. Machine learning (ML) has been recently applied to the IE signal classification problem. However, because of the scarcity of labeled IE datasets, most existing work relies on relatively small training and test datasets without addressing the generalizability and transferability of the developed models. In this paper, we compare two approaches for automatic classification of IE signals: clustering based on expert-crafted features and deep learning (DL) from automatically extracted features. Next, we use the knowledge gained from a DL model trained on concrete specimens with available ground truth to make predictions about defects in a different specimen with completely different construction and characteristics (transfer learning). Finally, we examine our DL model to gain insights into the model working (explainability) and highlight the attributions that are significant in classifying a particular IE signal. Our findings demonstrate the utility of ML and DL for IE signal classification, but also highlight the need for high-quality labeled datasets for advancing ML and DL in NDE data analysis." @default.
- W4360616562 created "2023-03-24" @default.
- W4360616562 creator A5009334923 @default.
- W4360616562 creator A5057413558 @default.
- W4360616562 creator A5067820079 @default.
- W4360616562 date "2023-03-22" @default.
- W4360616562 modified "2023-09-26" @default.
- W4360616562 title "Classification of Impact Echo Signals Using Explainable Deep Learning and Transfer Learning Approaches" @default.
- W4360616562 cites W2091567885 @default.
- W4360616562 cites W2148143831 @default.
- W4360616562 cites W2169796211 @default.
- W4360616562 cites W2271738104 @default.
- W4360616562 cites W2888803582 @default.
- W4360616562 cites W2919778510 @default.
- W4360616562 cites W3044944261 @default.
- W4360616562 cites W3165707607 @default.
- W4360616562 doi "https://doi.org/10.1177/03611981231159404" @default.
- W4360616562 hasPublicationYear "2023" @default.
- W4360616562 type Work @default.
- W4360616562 citedByCount "0" @default.
- W4360616562 crossrefType "journal-article" @default.
- W4360616562 hasAuthorship W4360616562A5009334923 @default.
- W4360616562 hasAuthorship W4360616562A5057413558 @default.
- W4360616562 hasAuthorship W4360616562A5067820079 @default.
- W4360616562 hasConcept C103824480 @default.
- W4360616562 hasConcept C105795698 @default.
- W4360616562 hasConcept C108583219 @default.
- W4360616562 hasConcept C119857082 @default.
- W4360616562 hasConcept C124101348 @default.
- W4360616562 hasConcept C138885662 @default.
- W4360616562 hasConcept C140331021 @default.
- W4360616562 hasConcept C146849305 @default.
- W4360616562 hasConcept C150899416 @default.
- W4360616562 hasConcept C153180895 @default.
- W4360616562 hasConcept C154945302 @default.
- W4360616562 hasConcept C19118579 @default.
- W4360616562 hasConcept C199360897 @default.
- W4360616562 hasConcept C27158222 @default.
- W4360616562 hasConcept C2777714996 @default.
- W4360616562 hasConcept C2778341716 @default.
- W4360616562 hasConcept C2779412668 @default.
- W4360616562 hasConcept C2779843651 @default.
- W4360616562 hasConcept C2781067378 @default.
- W4360616562 hasConcept C31972630 @default.
- W4360616562 hasConcept C33923547 @default.
- W4360616562 hasConcept C41008148 @default.
- W4360616562 hasConcept C41895202 @default.
- W4360616562 hasConcept C61272859 @default.
- W4360616562 hasConcept C73555534 @default.
- W4360616562 hasConceptScore W4360616562C103824480 @default.
- W4360616562 hasConceptScore W4360616562C105795698 @default.
- W4360616562 hasConceptScore W4360616562C108583219 @default.
- W4360616562 hasConceptScore W4360616562C119857082 @default.
- W4360616562 hasConceptScore W4360616562C124101348 @default.
- W4360616562 hasConceptScore W4360616562C138885662 @default.
- W4360616562 hasConceptScore W4360616562C140331021 @default.
- W4360616562 hasConceptScore W4360616562C146849305 @default.
- W4360616562 hasConceptScore W4360616562C150899416 @default.
- W4360616562 hasConceptScore W4360616562C153180895 @default.
- W4360616562 hasConceptScore W4360616562C154945302 @default.
- W4360616562 hasConceptScore W4360616562C19118579 @default.
- W4360616562 hasConceptScore W4360616562C199360897 @default.
- W4360616562 hasConceptScore W4360616562C27158222 @default.
- W4360616562 hasConceptScore W4360616562C2777714996 @default.
- W4360616562 hasConceptScore W4360616562C2778341716 @default.
- W4360616562 hasConceptScore W4360616562C2779412668 @default.
- W4360616562 hasConceptScore W4360616562C2779843651 @default.
- W4360616562 hasConceptScore W4360616562C2781067378 @default.
- W4360616562 hasConceptScore W4360616562C31972630 @default.
- W4360616562 hasConceptScore W4360616562C33923547 @default.
- W4360616562 hasConceptScore W4360616562C41008148 @default.
- W4360616562 hasConceptScore W4360616562C41895202 @default.
- W4360616562 hasConceptScore W4360616562C61272859 @default.
- W4360616562 hasConceptScore W4360616562C73555534 @default.
- W4360616562 hasIssue "9" @default.
- W4360616562 hasLocation W43606165621 @default.
- W4360616562 hasOpenAccess W4360616562 @default.
- W4360616562 hasPrimaryLocation W43606165621 @default.
- W4360616562 hasRelatedWork W2946016983 @default.
- W4360616562 hasRelatedWork W2960456850 @default.
- W4360616562 hasRelatedWork W3006943036 @default.
- W4360616562 hasRelatedWork W3089025284 @default.
- W4360616562 hasRelatedWork W4200511449 @default.
- W4360616562 hasRelatedWork W4299487748 @default.
- W4360616562 hasRelatedWork W4312200629 @default.
- W4360616562 hasRelatedWork W4317565044 @default.
- W4360616562 hasRelatedWork W4382286161 @default.
- W4360616562 hasRelatedWork W4385957992 @default.
- W4360616562 hasVolume "2677" @default.
- W4360616562 isParatext "false" @default.
- W4360616562 isRetracted "false" @default.
- W4360616562 workType "article" @default.