{"id":"W4387682080","doi":"10.1109/access.2023.3324659","title":"Ergonomic Risk Prediction for Awkward Postures From 3D Keypoints Using Deep Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Ergonomics and Musculoskeletal Disorders","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Ground truth; Work (physics); Artificial intelligence; Musculoskeletal disorder; Position (finance); Deep learning; Machine learning; Human factors and ergonomics; Physical medicine and rehabilitation; Simulation; Poison control; Medicine; 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":[0.0003170242,0.001639597,0.0007358365,0.001149002,0.0002036515,0.000435826,0.0008979557,0.0009663242,0.001251677],"category_scores_gemma":[0.001102166,0.0003486992,0.0009154149,0.000506878,0.0002206566,0.0004352452,0.000737267,0.0009196549,0.0006349425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004993472,"about_ca_system_score_gemma":0.0004613129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01277095,"about_ca_topic_score_gemma":0.01581389,"domain_scores_codex":[0.9996991,0.00003332083,0.00001799809,0.0001144641,0.00006960824,0.00006558124],"domain_scores_gemma":[0.9996936,0.00008285402,0.00004890313,0.00003367557,0.0001076391,0.00003335012],"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":[0.0008156982,0.0005705194,0.03937496,0.0003018135,0.0002956223,0.0006368863,0.0001455538,0.5506342,0.02040149,0.0004452718,0.007465905,0.3789121],"study_design_scores_gemma":[0.00001134974,0.000178512,0.01234988,0.00005102523,0.00002883953,0.00009080152,0.00005232175,0.9824394,0.003476401,0.0005866583,0.000718917,0.00001584139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5845428,0.00288528,0.400263,0.0005328541,0.0004222612,0.0001643961,0.00432293,0.004198667,0.002667659],"genre_scores_gemma":[0.963073,0.0004959197,0.02955721,0.0001119833,0.00004220929,0.00008332538,0.004297795,0.00004513349,0.002293367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01277095,"threshold_uncertainty_score":0.02539325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04175603833350501,"score_gpt":0.356301644870119,"score_spread":0.314545606536614,"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."}}