{"id":"W4415189941","doi":"10.20463/pan.2025.0020","title":"Quantifying the uncertainty of human activity recognition using a Bayesian machine learning method: a prediction study","year":2025,"lang":"en","type":"article","venue":"Physical Activity and Nutrition","topic":"Physical Activity and Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; McGill University","funders":"","keywords":"Activity recognition; Bayesian probability; Physical activity; Support vector machine; Bayesian inference; Naive Bayes classifier; Bayesian network","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":[0.01234857,0.00126514,0.0009225321,0.001276035,0.0004672648,0.001077771,0.0009773448,0.00108498,0.0006823146],"category_scores_gemma":[0.04461005,0.0003771909,0.0007741466,0.0008778434,0.0007691507,0.001581602,0.0009784289,0.001362156,0.000176072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009290118,"about_ca_system_score_gemma":0.000791205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009243509,"about_ca_topic_score_gemma":0.005369445,"domain_scores_codex":[0.9966686,0.001736616,0.0001426505,0.0006096232,0.000704025,0.0001383584],"domain_scores_gemma":[0.9552653,0.03882528,0.001834391,0.001525315,0.002239918,0.0003096724],"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":[0.00125227,0.0006241663,0.1444547,0.0002671909,0.0004389896,0.0001559093,0.000558394,0.671124,0.002626128,0.004837727,0.001152183,0.1725083],"study_design_scores_gemma":[0.00001462094,0.0001170026,0.01424293,0.00002573406,0.00002557108,0.00004880012,0.00003031016,0.9822257,0.0007629119,0.002349141,0.0001311572,0.00002617231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.572984,0.000884622,0.4240152,0.000348895,0.00005289167,0.0001345532,0.0002648877,0.0002632636,0.001051749],"genre_scores_gemma":[0.963753,0.0001797079,0.03541544,0.00003338024,0.00003904254,0.0000695617,0.0002418702,0.00001858989,0.0002494631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01234857,"threshold_uncertainty_score":0.06530625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1297859699138486,"score_gpt":0.4187761639849755,"score_spread":0.2889901940711269,"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."}}