{"id":"W4414206350","doi":"10.3390/s25185728","title":"Bridging the Methodological Gap Between Inertial Sensors and Optical Motion Capture: Deep Learning as the Path to Accurate Joint Kinematic Modelling Using Inertial Sensors","year":2025,"lang":"en","type":"article","venue":"Sensors","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Inertial measurement unit; Mean squared error; Kinematics; Sagittal plane; Motion analysis; Gait; Units of measurement; Joint (building); Motion capture","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001523999,0.0003028986,0.0003909435,0.0002177674,0.0008459654,0.0004634527,0.0003354551,0.0001615943,0.00001431134],"category_scores_gemma":[0.0007981753,0.0001908079,0.0001406628,0.000612393,0.000130603,0.0002528728,0.0003136937,0.0007422274,0.00003896662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007304488,"about_ca_system_score_gemma":0.00003903501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000184577,"about_ca_topic_score_gemma":0.000008139034,"domain_scores_codex":[0.9967593,0.001176088,0.0005613947,0.0006025773,0.0004069881,0.0004936678],"domain_scores_gemma":[0.9982546,0.0008879743,0.0001853068,0.0003819469,0.0001469746,0.0001431918],"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":[0.00002937732,0.00002376469,0.0001293696,0.00004546093,0.00007056815,0.00003335219,0.003410324,0.9661212,0.007351044,0.00274751,0.00002724893,0.02001081],"study_design_scores_gemma":[0.0002582872,0.0000445936,0.001099103,0.0001134526,0.00008773112,0.00005988147,0.0006419811,0.9909943,0.00474806,0.001607794,0.00009411679,0.0002507229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5651162,0.0000238271,0.4313696,0.0027209,0.0001864305,0.000257852,9.698964e-7,0.0001096717,0.000214585],"genre_scores_gemma":[0.9772203,0.00001704938,0.0213603,0.0008496409,0.0003816973,0.00001029793,0.000004595677,0.00001851443,0.0001376309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4121041,"threshold_uncertainty_score":0.7780919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1208486458548973,"score_gpt":0.3288816744395837,"score_spread":0.2080330285846865,"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."}}