{"id":"W4214612808","doi":"10.22541/au.164576816.69587551/v1","title":"Unsupervised Machine and Deep Learning Methods for Structural Damage Detection: A Comparative Study","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Novelty detection; Computer science; Artificial intelligence; Unsupervised learning; Cluster analysis; Structural health monitoring; Machine learning; Novelty; Support vector machine; Bridge (graph theory); Autoencoder; Mixture model; Pattern recognition (psychology); Deep learning; Key (lock); Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004939475,0.0004332554,0.0006310681,0.0002069173,0.000361433,0.00009118039,0.0002960195,0.000168229,0.0001410386],"category_scores_gemma":[0.0000469565,0.0004188818,0.00008881917,0.0001473423,0.00003148329,0.00007292069,0.0006521062,0.00151032,3.618988e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003006702,"about_ca_system_score_gemma":0.00001586813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002954752,"about_ca_topic_score_gemma":0.0001025958,"domain_scores_codex":[0.9982324,0.0003586187,0.000424384,0.0005020173,0.0001588009,0.000323766],"domain_scores_gemma":[0.9989654,0.00040084,0.00008462449,0.000370132,0.00006866999,0.0001103298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002822097,0.00003525898,0.01134886,0.002694058,0.0008541976,0.00001206761,0.02453564,0.12799,0.001696953,0.0001605416,0.00005403678,0.8303362],"study_design_scores_gemma":[0.0006884529,0.0005583096,0.05569417,0.00002658718,0.000105045,0.00001181078,0.003301052,0.9323668,0.0025563,0.002432674,0.001565123,0.0006936204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.936451,0.001456389,0.05512675,0.00001225387,0.001655892,0.002722663,0.00001993934,0.00225814,0.0002969361],"genre_scores_gemma":[0.7850319,0.00005320596,0.2137584,0.000005755143,0.0001546954,0.0008491347,0.00003364639,0.00006317437,0.00005013475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8296425,"threshold_uncertainty_score":0.9998263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05958733908923293,"score_gpt":0.4197605115710785,"score_spread":0.3601731724818455,"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."}}