{"id":"W7114793754","doi":"10.1155/atr/8828434","title":"Prediction of Traction Power Consumption for Rail Transit Based on Ensemble Learning Hybrid Time Series Models","year":2025,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Traction (geology); Random forest; Energy consumption; Electricity; Ensemble learning; Sliding window protocol; Traction motor; Mean absolute percentage error; Mean absolute error; Energy (signal processing)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004712927,0.0006819164,0.0005634771,0.0005609037,0.0002382128,0.0004423751,0.0004604691,0.0003902008,0.0006549577],"category_scores_gemma":[0.0009354897,0.0002123718,0.000626961,0.0005414005,0.00009922859,0.0006391557,0.0002513157,0.0006010512,0.0001818976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003522742,"about_ca_system_score_gemma":0.0004068662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01787269,"about_ca_topic_score_gemma":0.0187141,"domain_scores_codex":[0.9998096,0.00003530777,0.00001324218,0.00005880727,0.00005732919,0.00002578274],"domain_scores_gemma":[0.9997154,0.0001230213,0.00003773416,0.00003206571,0.00007926127,0.00001253299],"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":[0.00005780966,0.00008266902,0.006213024,0.00001668092,0.00006685541,0.00004052847,0.00001799339,0.9303375,0.001794509,0.0002635007,0.0004989796,0.06060994],"study_design_scores_gemma":[5.233466e-7,0.000006248856,0.0004879282,5.625022e-7,0.000003292005,0.000001850766,0.000001711186,0.9992815,0.0001476805,0.00004493876,0.00002258543,0.000001267686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.664121,0.0003714476,0.3308271,0.0001902019,0.00009358819,0.00003259415,0.0004232065,0.001127956,0.002812995],"genre_scores_gemma":[0.9874713,0.00009155418,0.01135583,0.000013621,0.00001455776,0.00001699031,0.0002992388,0.00001222466,0.0007247006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01787269,"threshold_uncertainty_score":0.0355373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008635384076985917,"score_gpt":0.2085522766478459,"score_spread":0.19991689257086,"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."}}