{"id":"W4408692122","doi":"10.1117/12.3039622","title":"Development of deep learning models for motion artifact mitigation in wearable PPG devices","year":2025,"lang":"en","type":"article","venue":"","topic":"Ergonomics and Musculoskeletal Disorders","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Ted Rogers Centre for Heart Research; University of Toronto","funders":"","keywords":"Artifact (error); Computer science; Wearable computer; Wearable technology; Deep learning; Artificial intelligence; Motion (physics); Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002035259,0.00006108754,0.0001030283,0.0001223834,0.00004199243,0.000007628757,0.00005358551,0.00005833472,0.0001058611],"category_scores_gemma":[0.00001239714,0.00006180121,0.00003793327,0.0001085267,0.00001105497,0.00007624859,0.00001349726,0.00005164312,0.00001260131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000315646,"about_ca_system_score_gemma":0.00002422587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001072774,"about_ca_topic_score_gemma":0.001435493,"domain_scores_codex":[0.999409,0.00002270763,0.0002481645,0.0001531331,0.00003355511,0.0001333951],"domain_scores_gemma":[0.9997885,0.00004091004,0.00005531717,0.0000696302,0.00003149968,0.00001411124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001005847,0.0002403884,0.01616199,0.0001962139,0.0001025819,1.414422e-7,0.004099119,0.02820795,0.002583788,0.1539187,0.00006613046,0.7943224],"study_design_scores_gemma":[0.003818055,0.0001356895,0.6348793,0.0002371791,0.00004430817,3.141606e-7,0.01476454,0.277537,0.00721774,0.0504893,0.01035042,0.0005261822],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.752124,0.0001605878,0.1885236,0.0000933937,0.0001008053,0.000225804,3.283121e-7,0.00001696448,0.05875456],"genre_scores_gemma":[0.9888945,0.000007884171,0.009345753,0.00006058184,0.000003672826,0.00008112833,0.00001417074,0.000005875967,0.001586452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7937962,"threshold_uncertainty_score":0.252018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02308423981077524,"score_gpt":0.3010340750080483,"score_spread":0.2779498351972731,"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."}}