{"id":"W4393220926","doi":"10.1016/j.jtherbio.2024.103828","title":"Enhancing thermal comfort prediction in high-speed trains through machine learning and physiological signals integration","year":2024,"lang":"en","type":"article","venue":"Journal of Thermal Biology","topic":"Aerodynamics and Fluid Dynamics Research","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Education and Child Care","funders":"National Natural Science Foundation of China","keywords":"HVAC; Thermal comfort; Computer science; Simulation; Random forest; Train; Ventilation (architecture); Wearable computer; Automotive engineering; Artificial intelligence; Environmental science; Air conditioning; Engineering; Meteorology; Mechanical 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":[0.0002886103,0.000589206,0.0003571229,0.0003024724,0.0001688174,0.000504105,0.0002464759,0.0004459998,0.0009225897],"category_scores_gemma":[0.001052998,0.0001468527,0.0003467114,0.0002700828,0.0001199891,0.0004822782,0.0003481162,0.0005305106,0.0003507541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001659672,"about_ca_system_score_gemma":0.0003625612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002797243,"about_ca_topic_score_gemma":0.003431833,"domain_scores_codex":[0.9998908,0.00002356929,0.000004942306,0.00003428952,0.00002149306,0.00002502033],"domain_scores_gemma":[0.9997949,0.00009414047,0.000023806,0.00001208114,0.00005818152,0.00001687131],"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":[0.0007964293,0.0007175042,0.02671519,0.0001665803,0.0001745452,0.0001932414,0.0001816065,0.4437943,0.06807126,0.0007774238,0.002029277,0.4563826],"study_design_scores_gemma":[0.000007325062,0.00009761422,0.01345268,0.000009757983,0.00002753604,0.00003010011,0.00002005095,0.9803331,0.005331122,0.000403735,0.0002742927,0.00001251745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4933195,0.0007463243,0.5000572,0.0004068781,0.0002168848,0.0000663598,0.000311019,0.0008908936,0.003984883],"genre_scores_gemma":[0.9857615,0.0001112014,0.01310825,0.00004672478,0.00004673758,0.00002261047,0.0001223836,0.00002424205,0.0007562294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002797243,"threshold_uncertainty_score":0.005561948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01930948855205489,"score_gpt":0.2811273609308478,"score_spread":0.2618178723787929,"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."}}