{"id":"W4309541269","doi":"10.36680/j.itcon.2022.050","title":"Hybrid feature selection framework for predicting bridge deck conditions","year":2022,"lang":"en","type":"article","venue":"Journal of Information Technology in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Bridge (graph theory); Artificial neural network; Feature selection; Engineering; Serviceability (structure); Random forest; Hyperparameter; Computer science; Selection (genetic algorithm); Bridge deck; Deck; Machine learning; Artificial intelligence; Structural 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":[0.001026607,0.0008084602,0.0007897207,0.001052024,0.000263745,0.0005207431,0.0008321846,0.0005989984,0.000798076],"category_scores_gemma":[0.001220319,0.0002383169,0.0009294827,0.0007423699,0.0001993163,0.0005392958,0.0003851955,0.0006384733,0.0002404633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005407105,"about_ca_system_score_gemma":0.0007656333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01265827,"about_ca_topic_score_gemma":0.009891285,"domain_scores_codex":[0.9996514,0.00008598749,0.00002468616,0.00008977547,0.00008452788,0.00006366362],"domain_scores_gemma":[0.9995568,0.0001922652,0.00003923196,0.00002118582,0.0001721171,0.00001837638],"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":[0.000347971,0.0003705783,0.01614614,0.00008528365,0.0002142847,0.000298101,0.00008561279,0.7316911,0.00667599,0.001336784,0.003464428,0.2392838],"study_design_scores_gemma":[0.000004552046,0.00002558945,0.001408174,0.000003123715,0.0000110196,0.00001287676,0.000007074356,0.9975821,0.0004613451,0.0003317108,0.0001480579,0.000004418137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2126562,0.0008724525,0.7822394,0.0003804182,0.00007369449,0.0001033204,0.0008746927,0.001600574,0.001199259],"genre_scores_gemma":[0.9344645,0.0001984665,0.06236602,0.00008293799,0.00004515173,0.0001364816,0.001074675,0.0000276092,0.001604189],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01265827,"threshold_uncertainty_score":0.02516919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003672905132079263,"score_gpt":0.2211650730778662,"score_spread":0.2174921679457869,"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."}}