{"id":"W7132967582","doi":"","title":"Development and Validation of Deep Learning Models for Motion Artifact Mitigation in Wearable PPG Devices","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute","funders":"","keywords":"Photoplethysmogram; Wearable computer; Accelerometer; Artifact (error); Interpretability; Deep learning; Wearable technology; Motion (physics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004738622,0.0004181156,0.0005081025,0.0005865576,0.0001719315,0.00009519121,0.0001189155,0.0003873429,0.0000176808],"category_scores_gemma":[0.0002151068,0.000549812,0.00007756412,0.000472873,0.00001533466,0.0005718613,0.0000315154,0.0003588753,0.000004605191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004057087,"about_ca_system_score_gemma":0.0001090814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001849917,"about_ca_topic_score_gemma":0.0004162099,"domain_scores_codex":[0.9979884,0.00007476582,0.0007673695,0.0004858598,0.0002962067,0.0003874204],"domain_scores_gemma":[0.9988146,0.0003384839,0.0003734766,0.0001515741,0.0002478822,0.00007396442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009615253,0.00004946711,0.006442759,0.005995943,0.0001264362,9.738726e-7,0.02467735,0.6841813,0.2020234,0.0003816324,9.282548e-7,0.07602369],"study_design_scores_gemma":[0.0007237766,0.00005593852,0.004610389,0.003357037,0.0001010761,5.465959e-7,0.008801232,0.1625402,0.8181736,0.001080776,0.0000448683,0.0005106343],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8517806,0.001691878,0.143797,0.00002018585,0.0004306615,0.0009487194,0.000001990862,0.00005039915,0.001278602],"genre_scores_gemma":[0.9780599,0.0003044158,0.02015612,0.000001528499,0.00006486177,0.0002311639,0.0003619797,0.00006314756,0.0007568388],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6161502,"threshold_uncertainty_score":0.9996954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02743515156404914,"score_gpt":0.2864595569002105,"score_spread":0.2590244053361614,"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."}}