{"id":"W4293680188","doi":"10.3390/s22166193","title":"Data Augmentation for Deep-Learning-Based Multiclass Structural Damage Detection Using Limited Information","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Government of Ontario","keywords":"Structural health monitoring; Computer science; Identification (biology); Deep learning; Convolutional neural network; Field (mathematics); Scarcity; Machine learning; Artificial intelligence; Risk analysis (engineering); Data science; Engineering; Business","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001196156,0.0001032894,0.00007956895,0.0001271208,0.0003176241,0.00004598249,0.0001216266,0.00003322361,0.00001838058],"category_scores_gemma":[0.00006214804,0.0001147535,0.00002683376,0.0001536801,0.00001062167,0.0003828867,0.00004566789,0.0001871791,0.000001795774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002226985,"about_ca_system_score_gemma":0.000009938641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000025267,"about_ca_topic_score_gemma":0.00001638593,"domain_scores_codex":[0.9993534,0.00002920513,0.0001767995,0.000104304,0.0001436243,0.0001926339],"domain_scores_gemma":[0.9996423,0.00003952673,0.00005996913,0.0001864952,0.00004440634,0.00002737464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000317294,0.000001004072,0.0002161331,0.00003611439,0.00001291117,6.244081e-7,0.0003561207,0.9799544,0.008601456,0.00000474833,0.00001446528,0.01077027],"study_design_scores_gemma":[0.0005556546,0.00003508255,0.002120889,0.000004761745,0.00002151316,0.000004516474,0.001224612,0.9823285,0.008988677,0.00001407784,0.004567793,0.0001339213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9524755,0.000007478028,0.04582089,0.000009274188,0.001110969,0.0002536182,0.00007506014,0.0002154957,0.00003175005],"genre_scores_gemma":[0.9939539,7.354878e-7,0.005286975,0.00002502561,0.0001196291,0.00001752723,0.0005678246,0.00002171771,0.000006657564],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04147844,"threshold_uncertainty_score":0.4679511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01824623420957965,"score_gpt":0.250722101997159,"score_spread":0.2324758677875793,"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."}}