{"id":"W4402827367","doi":"10.1007/978-3-031-61531-3_13","title":"Bridging the Gap Between Data and Outliers: Using Machine Learning to Automate Outlier Sensor Behaviour for Bridge Structural Health Monitoring","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in civil engineering","topic":"Structural Health Monitoring Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Carleton University; University of Toronto","funders":"","keywords":"Bridge (graph theory); Bridging (networking); Outlier; Anomaly detection; Computer science; Structural health monitoring; Data mining; Artificial intelligence; Machine learning; Engineering; Medicine; Structural engineering; Computer security","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":[0.0008158358,0.0007160669,0.0008235545,0.0008182497,0.0002648947,0.0009648813,0.001088649,0.0009637011,0.001378789],"category_scores_gemma":[0.003559049,0.000411562,0.0005382983,0.001087664,0.0004757287,0.001225402,0.0009827319,0.001732243,0.0008418542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002626978,"about_ca_system_score_gemma":0.0003094064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000997953,"about_ca_topic_score_gemma":0.00174555,"domain_scores_codex":[0.999365,0.00008912284,0.00004402746,0.0001699701,0.0002795767,0.00005217433],"domain_scores_gemma":[0.9985018,0.0008761385,0.0001562641,0.0001729958,0.0002599229,0.00003289357],"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":[0.0001676384,0.0001830495,0.003173135,0.0001864908,0.00006091921,0.0001732203,0.0001877514,0.08914713,0.03531345,0.003006072,0.00496394,0.8634372],"study_design_scores_gemma":[0.000004325668,0.0000795806,0.001850731,0.00001905577,0.00001565681,0.0001123902,0.00003416816,0.9732343,0.01361477,0.008569457,0.002448531,0.00001711383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02698628,0.0007139984,0.9687066,0.0002569495,0.0001101847,0.00002630821,0.000119705,0.001654269,0.001425679],"genre_scores_gemma":[0.4586388,0.001211412,0.531579,0.000268103,0.0001971333,0.0000830147,0.0007934984,0.0005718435,0.006657222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001378789,"threshold_uncertainty_score":0.004612446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05943268458310252,"score_gpt":0.3272213946153332,"score_spread":0.2677887100322306,"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."}}