{"id":"W4409310266","doi":"10.1016/j.autcon.2025.106180","title":"Deep learning-driven multi-level data fusion framework for predictive maintenance and structural health monitoring of concrete bridge decks","year":2025,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Infrastructure Maintenance and Monitoring","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"Portage College","funders":"","keywords":"Bridge (graph theory); Structural health monitoring; Engineering; Computer science; Sensor fusion; Structural engineering; Forensic engineering; Civil engineering; Artificial intelligence; Data mining; Construction engineering; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0001937769,0.0001533156,0.0002526177,0.0001933255,0.0001278746,0.00002911177,0.0001427588,0.0001364712,0.000002273589],"category_scores_gemma":[0.0002630697,0.0001624362,0.00002572411,0.0002275043,0.00008813204,0.0003323743,0.00007252736,0.0002692975,3.450727e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001768284,"about_ca_system_score_gemma":0.00004727144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004524824,"about_ca_topic_score_gemma":0.00001249876,"domain_scores_codex":[0.998927,0.00003869787,0.000428806,0.0002570245,0.0001061893,0.0002422705],"domain_scores_gemma":[0.9993295,0.0001346875,0.0001580919,0.0002313746,0.000109224,0.00003711872],"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":[0.0001305903,0.000004561552,0.3293243,0.001283152,0.0001547781,0.000001568661,0.003088469,0.09006298,0.004269352,0.008719573,0.0001648479,0.5627958],"study_design_scores_gemma":[0.0006548556,0.00002588251,0.371334,0.0006232248,0.00001244424,0.000009142977,0.0007222258,0.6238703,0.001140826,0.001411896,0.00008190953,0.0001133148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3919305,0.000255194,0.6054098,0.00003813033,0.001818566,0.0003373398,0.00004717807,0.0001424387,0.00002089906],"genre_scores_gemma":[0.8145258,0.0001889155,0.1850727,0.00000711528,0.0001038191,0.00002665024,0.00005467713,0.00001426538,0.000005999467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5626825,"threshold_uncertainty_score":0.6623956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02559687811240352,"score_gpt":0.3050019855148063,"score_spread":0.2794051074024028,"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."}}