{"id":"W2623931658","doi":"10.1007/978-3-319-54858-6_13","title":"Unsupervised Novelty Detection Techniques for Structural Damage Localization: A Comparative Study","year":2017,"lang":"en","type":"book-chapter","venue":"Conference proceedings of the Society for Experimental Mechanics","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Novelty detection; Novelty; Computer science; Cluster analysis; Artificial intelligence; Unsupervised learning; Pattern recognition (psychology); Machine learning; Support vector machine; Mixture model; Structural health monitoring; Key (lock); Scale (ratio); 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":[0.0001715953,0.0005274197,0.0006366495,0.0000471477,0.0005512314,0.000117094,0.0008715147,0.0004622566,0.000009758885],"category_scores_gemma":[0.00002096374,0.0004552185,0.0006747764,0.00002994501,0.0001126378,0.0002483587,0.0002275634,0.0003521766,3.205165e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004484282,"about_ca_system_score_gemma":0.00005011773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001073455,"about_ca_topic_score_gemma":0.00000449855,"domain_scores_codex":[0.998467,0.000002106133,0.0004982165,0.0004185873,0.0003137013,0.0003004261],"domain_scores_gemma":[0.9984563,0.00003633587,0.0004694734,0.0003051653,0.0006622071,0.00007049184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009418784,0.0002407273,0.00005065031,0.009554559,0.003650825,4.504335e-7,0.07335638,0.00006332543,0.4906234,0.3823836,0.01049544,0.02863879],"study_design_scores_gemma":[0.0007982355,0.001094994,0.00001292468,0.0006465749,0.0002335905,0.000003953623,0.004502339,0.05754433,0.8920166,0.03988531,0.002517987,0.0007431337],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5959297,0.006176376,0.1638691,0.000372926,0.02330422,0.1473864,0.004831746,0.01443383,0.04369558],"genre_scores_gemma":[0.9874741,0.0000421977,0.009857359,0.00001475737,0.0002687145,0.0008445234,0.00001873737,0.0001211054,0.001358452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4013932,"threshold_uncertainty_score":0.99979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05896131872516759,"score_gpt":0.3251391628254722,"score_spread":0.2661778441003047,"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."}}