{"id":"W4396523004","doi":"10.1123/jmpb.2023-0033","title":"Comparing Accelerometer Processing Metrics and Hyperparameter Optimization for Physical Activity Classification Accuracy Using Machine Learning Methods","year":2024,"lang":"en","type":"article","venue":"Journal for the Measurement of Physical Behaviour","topic":"Physical Activity and Health","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of Saskatchewan; University of Victoria; McGill University; Memorial University of Newfoundland","funders":"","keywords":"Hyperparameter; Accelerometer; Machine learning; Computer science; Artificial intelligence; Hyperparameter optimization; Pattern recognition (psychology); Support vector machine","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":[],"consensus_categories":[],"category_scores_codex":[0.001400609,0.0001986246,0.0005512726,0.0001633474,0.0004424893,0.0001681414,0.0001042741,0.00005581414,0.000001840921],"category_scores_gemma":[0.0005830033,0.0001285313,0.0003378982,0.0003421849,0.00007264392,0.0004706441,0.00004015634,0.0006472882,2.733024e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002632347,"about_ca_system_score_gemma":0.0001474984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001361172,"about_ca_topic_score_gemma":8.069267e-7,"domain_scores_codex":[0.9984711,0.0001266203,0.0002667832,0.0002696768,0.0005929633,0.0002728112],"domain_scores_gemma":[0.9980449,0.0009803064,0.0002777488,0.0001249127,0.0004350001,0.0001371267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001304341,0.002866027,0.002019404,0.001495215,0.0003507414,0.000001223913,0.001004699,0.007292178,0.6551871,0.0002972659,0.00001793755,0.3281638],"study_design_scores_gemma":[0.0007769035,0.000946499,0.004735505,0.0003292667,0.001252948,0.00001817694,0.00007322204,0.952288,0.0388886,0.0004376988,0.0001233257,0.0001298667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6422739,0.0002700664,0.3563401,0.0003874179,0.0001153202,0.0005730222,0.000005976542,0.00002573409,0.00000841433],"genre_scores_gemma":[0.9680956,0.00002477243,0.03129583,0.00001684314,0.0004705517,0.00004250863,0.000004795045,0.00003855769,0.00001051942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9449958,"threshold_uncertainty_score":0.5241355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.407289181552939,"score_gpt":0.4748862909891269,"score_spread":0.06759710943618796,"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."}}