{"id":"W3137193012","doi":"10.1177/09544097211002665","title":"Procedure for combining field measurements and machine learning to quantify impact of different track parameters on ride quality of railway tracks","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Track (disk drive); Accelerometer; Ride quality; Quality (philosophy); Computer science; Field (mathematics); Transport engineering; Automotive engineering; Engineering; Simulation; Mechanical engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.003500342,0.0010707,0.0009047437,0.001852008,0.0008215362,0.001076152,0.001179337,0.0007538627,0.002682952],"category_scores_gemma":[0.0120748,0.0005418021,0.001221925,0.00141339,0.0004743665,0.0007244411,0.001179919,0.001424084,0.001465433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000602886,"about_ca_system_score_gemma":0.002411658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01277832,"about_ca_topic_score_gemma":0.009698318,"domain_scores_codex":[0.9984876,0.0003376353,0.0001410947,0.000450596,0.0004724712,0.0001107124],"domain_scores_gemma":[0.996185,0.001741347,0.0003616387,0.0005024009,0.00114428,0.00006527099],"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":[0.0003723839,0.0006393698,0.05171163,0.0002036644,0.0004831656,0.0002063768,0.0003330853,0.1958791,0.03011406,0.006160091,0.002639986,0.7112571],"study_design_scores_gemma":[0.00005254315,0.0003252443,0.02300009,0.00003488239,0.00009247635,0.0001078249,0.0001666836,0.949456,0.01857777,0.005074421,0.003021093,0.00009095177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03872924,0.00004633364,0.9578781,0.00009006758,0.00003157888,0.0003672934,0.0003888978,0.001322983,0.001145483],"genre_scores_gemma":[0.2794359,0.00006106645,0.7165531,0.00006771905,0.00002451579,0.0009192802,0.001007922,0.0001310987,0.00179942],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01277832,"threshold_uncertainty_score":0.02540785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03822036415177431,"score_gpt":0.2608889492548813,"score_spread":0.222668585103107,"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."}}