{"id":"W2795331216","doi":"10.1117/12.2295966","title":"Automated damage-sensitive feature extraction using unsupervised convolutional neural networks","year":2018,"lang":"en","type":"article","venue":"Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Support vector machine; Novelty detection; Feature (linguistics); Unsupervised learning; Test data; Feature learning; Machine learning; Deep learning; Novelty","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":[0.0001520994,0.0004058014,0.0004794257,0.0001326372,0.0005634378,0.0001583996,0.0001315148,0.0006442039,0.000002119101],"category_scores_gemma":[0.00008119288,0.0003360366,0.00008076064,0.0001964805,0.0003550311,0.0001957055,0.00009547068,0.0003861636,5.950009e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008287201,"about_ca_system_score_gemma":0.0000122017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004675531,"about_ca_topic_score_gemma":0.00006727453,"domain_scores_codex":[0.9984767,0.00003392014,0.000281202,0.0004519071,0.0001612939,0.0005949452],"domain_scores_gemma":[0.9992666,0.00007808755,0.0001012669,0.0002979399,0.0001717761,0.00008434617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000675511,0.00004424996,0.001885348,0.00159757,0.001252777,0.00009011317,0.001189649,0.108843,0.7935976,0.03606347,0.0480978,0.006662941],"study_design_scores_gemma":[0.0006128905,0.0002108664,0.0007397436,0.0001303308,0.0000716237,0.0002292811,0.002351763,0.9794583,0.01212034,0.0006867596,0.002903328,0.0004848102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647638,0.00103884,0.0269293,0.0001303483,0.003955806,0.0007552493,0.0000825078,0.002293797,0.00005032841],"genre_scores_gemma":[0.9957383,0.0001982062,0.003287245,0.00001961319,0.0006055628,0.00002041865,0.0000196174,0.00005790314,0.00005315666],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8706153,"threshold_uncertainty_score":0.9999092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01082749592005392,"score_gpt":0.2374454245919931,"score_spread":0.2266179286719392,"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."}}