{"id":"W3092928354","doi":"10.1016/j.trd.2020.102576","title":"Vehicular fuel consumption estimation using real-world measures through cascaded machine learning modeling","year":2020,"lang":"en","type":"article","venue":"Transportation Research Part D Transport and Environment","topic":"Vehicle emissions and performance","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Fuel efficiency; Computer science; Support vector machine; Artificial neural network; Categorical variable; Usability; Machine learning; Artificial intelligence; Estimation; Automotive engineering; 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":[0.0004852352,0.0008515068,0.0007871628,0.0006635633,0.0002624469,0.0006711832,0.0009877984,0.000663895,0.000667422],"category_scores_gemma":[0.00169174,0.000474089,0.0008475871,0.0006283327,0.0002732023,0.001054505,0.0005237492,0.0009855194,0.0003116624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005077764,"about_ca_system_score_gemma":0.0005126714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01039834,"about_ca_topic_score_gemma":0.01033452,"domain_scores_codex":[0.9996783,0.00005168161,0.00002057023,0.0001274558,0.00008064554,0.00004133949],"domain_scores_gemma":[0.999513,0.0002312203,0.00005782657,0.000069421,0.000115136,0.00001349341],"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":[0.00009614234,0.0001221798,0.004570661,0.00003779987,0.0000786618,0.00006058292,0.00002525163,0.9514994,0.00266052,0.0008272376,0.0002894952,0.03973217],"study_design_scores_gemma":[9.744662e-7,0.000008651246,0.0005735575,0.000001340703,0.000004786839,0.000004643588,0.000001305956,0.9986346,0.0005171518,0.0002056204,0.0000447923,0.000002518199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.293985,0.0003561284,0.7022476,0.00009900528,0.00008866901,0.00005525272,0.0003730987,0.0007653075,0.002029989],"genre_scores_gemma":[0.977406,0.0000922119,0.02140032,0.00001196203,0.00001248826,0.00003038229,0.0003357342,0.00001514953,0.0006958502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01039834,"threshold_uncertainty_score":0.0206756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1262303191769668,"score_gpt":0.3125266304904852,"score_spread":0.1862963113135184,"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."}}