{"id":"W4411613687","doi":"10.1016/j.eswa.2025.128731","title":"Contrastive and self-supervised learning for open-set damage classification in structural health monitoring with incomplete and imbalanced vibration data","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Jiangsu Province; KU Leuven","keywords":"Computer science; Structural health monitoring; Artificial intelligence; Set (abstract data type); Machine learning; Open set; Data set; Vibration; Supervised learning; Pattern recognition (psychology); Structural engineering; Mathematics; Artificial neural network; 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":[0.004917452,0.000894458,0.001746558,0.001488597,0.0005746298,0.001095064,0.002370349,0.001924544,0.001213275],"category_scores_gemma":[0.0096537,0.0005057236,0.001063982,0.0008488294,0.001145129,0.002060873,0.002056226,0.001880944,0.0003965656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007525718,"about_ca_system_score_gemma":0.000868472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002406579,"about_ca_topic_score_gemma":0.00385376,"domain_scores_codex":[0.9981711,0.0006577965,0.0001377288,0.0005517207,0.0003251928,0.0001565273],"domain_scores_gemma":[0.9914214,0.006271,0.0004452935,0.0007561078,0.0009008834,0.0002052586],"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":[0.001122751,0.0009439661,0.007361121,0.0003149663,0.0003086184,0.0002085585,0.0003094563,0.3016776,0.01409169,0.007098433,0.004032679,0.6625301],"study_design_scores_gemma":[0.0000124053,0.00006426569,0.0006174739,0.000006776597,0.00001240382,0.00002345878,0.000009952501,0.9959544,0.001407917,0.001717244,0.0001675746,0.000006111685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1050017,0.0008044302,0.8914203,0.0002770202,0.00009436488,0.0001021293,0.0002259848,0.001140331,0.0009336877],"genre_scores_gemma":[0.7669323,0.0001898954,0.2291981,0.0002166205,0.0001758833,0.0001749323,0.0009270048,0.0001681135,0.002016999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004917452,"threshold_uncertainty_score":0.02600634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04166158333456722,"score_gpt":0.3453157598843263,"score_spread":0.3036541765497591,"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."}}