{"id":"W4403016311","doi":"10.1016/j.buildenv.2024.112127","title":"Interpretable general thermal comfort model based on physiological data from wearable bio sensors: Light Gradient Boosting Machine (LightGBM) and SHapley Additive exPlanations (SHAP)","year":2024,"lang":"en","type":"article","venue":"Building and Environment","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation of Korea","keywords":"Boosting (machine learning); Gradient boosting; Wearable computer; Artificial intelligence; Computer science; Machine learning; Thermal; Random forest; Meteorology; Geography; Embedded system","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":[0.0005253993,0.0004289862,0.000476716,0.0002923047,0.0001686761,0.000446306,0.0006106909,0.0004817895,0.001143268],"category_scores_gemma":[0.001122545,0.0001498141,0.000456595,0.0002001623,0.0002233891,0.0006507464,0.0003797124,0.0006120889,0.0001607722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003277736,"about_ca_system_score_gemma":0.0003842957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001974319,"about_ca_topic_score_gemma":0.002504996,"domain_scores_codex":[0.9998446,0.00004844818,0.000009821934,0.00005394959,0.00002703639,0.0000162395],"domain_scores_gemma":[0.9997492,0.000108778,0.00002932638,0.0000244116,0.00007298315,0.00001531203],"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":[0.000213533,0.0001925386,0.003829253,0.0001412,0.0001397275,0.0001579152,0.0002325229,0.7458065,0.01132247,0.01487595,0.002558036,0.2205303],"study_design_scores_gemma":[0.000002637268,0.0000226478,0.0004253188,0.000003368819,0.00001113756,0.0000134412,0.000004113111,0.9962592,0.0004571449,0.002646567,0.0001508972,0.000003553448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05989015,0.0002393383,0.9378399,0.0002116666,0.00004641908,0.00002638669,0.00008532435,0.0005123237,0.001148471],"genre_scores_gemma":[0.9340834,0.0001435201,0.06396755,0.00009386544,0.00003973099,0.00004880699,0.0001460789,0.00003007668,0.001447033],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001974319,"threshold_uncertainty_score":0.003925681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02503073017309419,"score_gpt":0.226082032785518,"score_spread":0.2010513026124238,"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."}}