{"id":"W4285094540","doi":"10.1002/eng2.12551","title":"Unsupervised machine and deep learning methods for structural damage detection: A comparative study","year":2022,"lang":"en","type":"article","venue":"Engineering Reports","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":59,"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; Novelty; Machine learning; Bridge (graph theory); Support vector machine; Mixture model; Autoencoder; Key (lock); Pattern recognition (psychology); Deep learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001837614,0.0006567392,0.0005650034,0.001837374,0.0002234894,0.0005551513,0.0005955907,0.0008871842,0.0007689452],"category_scores_gemma":[0.004026278,0.000211347,0.000627444,0.001106937,0.0003595477,0.001484837,0.0005700155,0.0006875484,0.0002196807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005554326,"about_ca_system_score_gemma":0.0005156873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002489163,"about_ca_topic_score_gemma":0.002666448,"domain_scores_codex":[0.9987662,0.0003587388,0.00007577775,0.0001871169,0.0005440922,0.00006819591],"domain_scores_gemma":[0.9967327,0.001549805,0.0002522194,0.0003288363,0.001068508,0.00006781281],"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":[0.0002956646,0.0004674125,0.01210392,0.0004655799,0.000307915,0.0001067852,0.00011817,0.2036629,0.0106871,0.006354543,0.002954493,0.7624755],"study_design_scores_gemma":[0.00001171683,0.0001815435,0.007427076,0.00002951164,0.00004090535,0.00008750674,0.00004135096,0.9836202,0.004847387,0.00203846,0.001651997,0.00002245836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2697324,0.01281271,0.7060291,0.0008378198,0.0002143409,0.0001353215,0.0002418444,0.001122578,0.008874034],"genre_scores_gemma":[0.8208162,0.003867961,0.1714167,0.0001596318,0.0001499505,0.00008271188,0.0004520282,0.00007103109,0.002983885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002489163,"threshold_uncertainty_score":0.009718359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02080694065390774,"score_gpt":0.3394611451769585,"score_spread":0.3186542045230507,"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."}}