{"id":"W4412515242","doi":"10.3390/buildings15142539","title":"Personalized Human Thermal Sensation Prediction Based on Bayesian-Optimized Random Forest","year":2025,"lang":"en","type":"article","venue":"Buildings","topic":"Color perception and design","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Natural Science Foundation of Xiamen City","keywords":"Random forest; Thermal sensation; Bayesian probability; Artificial intelligence; Computer science; Thermal; Machine learning; Thermal comfort; Meteorology; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004186891,0.0001579813,0.0002070275,0.0002587318,0.0002184565,0.00004919957,0.00010798,0.000162136,0.005608136],"category_scores_gemma":[0.00005233628,0.0001495317,0.0001536306,0.0002214995,0.00007138228,0.00005311989,0.0000116289,0.0001622102,0.0001278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008855751,"about_ca_system_score_gemma":0.00003136225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009298956,"about_ca_topic_score_gemma":0.000008725555,"domain_scores_codex":[0.9987914,0.0002101978,0.0002556745,0.0003444116,0.0001796163,0.0002186778],"domain_scores_gemma":[0.999364,0.0001781588,0.00007977383,0.0002631526,0.00005928213,0.00005565781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.04316687,0.002648948,0.05548461,0.000182445,0.0006523763,0.00008373449,0.01055506,0.02268622,0.1640911,0.232129,0.4209235,0.04739616],"study_design_scores_gemma":[0.1113161,0.001338266,0.6011575,0.0004150016,0.0004755091,0.00001529955,0.001524698,0.172427,0.001408714,0.00376662,0.1050018,0.001153452],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5837692,0.00003691445,0.292941,0.001773142,0.001011472,0.0009429844,0.00002168285,0.0005133162,0.1189903],"genre_scores_gemma":[0.9854271,0.000001526011,0.001349125,0.001978096,0.0001401866,0.0001358065,0.00005804816,0.00001934225,0.01089073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.545673,"threshold_uncertainty_score":0.9953009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0195409847390242,"score_gpt":0.3109981565520436,"score_spread":0.2914571718130194,"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."}}