{"id":"W4401501012","doi":"10.1186/s43065-024-00102-2","title":"Automated crack identification in structures using acoustic waveforms and deep learning","year":2024,"lang":"en","type":"article","venue":"Journal of Infrastructure Preservation and Resilience","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education, Libya","keywords":"Waveform; Convolutional neural network; Computer science; Acoustic emission; Process (computing); Artificial neural network; Identification (biology); Deep learning; Feature extraction; Feature (linguistics); Range (aeronautics); Pattern recognition (psychology); Beam (structure); Artificial intelligence; Time domain; Acoustics; Structural engineering; Engineering; Computer vision","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002397365,0.0005829753,0.0002924493,0.000895794,0.0001525907,0.0004109823,0.0004700421,0.0006883197,0.00083163],"category_scores_gemma":[0.0008191066,0.0003218919,0.0003483533,0.0003761503,0.0002609257,0.0009241741,0.0006388586,0.0006533104,0.0003961212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002921876,"about_ca_system_score_gemma":0.0004170459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001945789,"about_ca_topic_score_gemma":0.00365324,"domain_scores_codex":[0.999874,0.00001769932,0.000006744866,0.00003674382,0.00004721052,0.000017608],"domain_scores_gemma":[0.9996926,0.00009482551,0.00006946693,0.00004251988,0.0000814723,0.0000191361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001598584,0.0001635559,0.007362477,0.0001143498,0.00005286842,0.0001975631,0.0001089186,0.3862646,0.08649331,0.001969046,0.001305612,0.5158078],"study_design_scores_gemma":[0.000002160989,0.00001533518,0.001127411,0.000004718865,0.000002494284,0.00002027501,0.00001009008,0.9939289,0.004013563,0.0006883174,0.0001830905,0.000003593091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1125652,0.0002125667,0.8844671,0.0001298168,0.00003031559,0.00004063071,0.0001024846,0.001139638,0.00131233],"genre_scores_gemma":[0.7989989,0.0002589126,0.1980466,0.00006135655,0.00002895626,0.00004421581,0.0003657828,0.00006058218,0.002134643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001945789,"threshold_uncertainty_score":0.003868937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007961803454886516,"score_gpt":0.2748137805299959,"score_spread":0.2668519770751094,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}