{"id":"W3120132237","doi":"10.1016/j.jbiomech.2021.110229","title":"Estimation of kinematics from inertial measurement units using a combined deep learning and optimization framework","year":2021,"lang":"en","type":"article","venue":"Journal of Biomechanics","topic":"Lower Extremity Biomechanics and Pathologies","field":"Engineering","cited_by":70,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Kinematics; Inertial measurement unit; Artificial intelligence; Computer science; Calibration; Accelerometer; Deep learning; Computer vision; Units of measurement; Sensor fusion; Gait; Mean squared error; Artificial neural network; Simulation; Mathematics; Physical medicine and rehabilitation; Medicine; Statistics","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":[0.0003274155,0.0001131258,0.0002672515,0.0001523737,0.0000396796,0.00004165902,0.00007302479,0.0001395638,0.00005624198],"category_scores_gemma":[0.0005985898,0.0001093442,0.00004454076,0.0004499034,0.00001017715,0.000113306,0.00004299215,0.0002077744,3.25781e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006801338,"about_ca_system_score_gemma":0.00005391591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002622556,"about_ca_topic_score_gemma":0.000001817748,"domain_scores_codex":[0.9989672,0.00005069684,0.0004706851,0.00007614622,0.0003277145,0.0001075244],"domain_scores_gemma":[0.9990221,0.00008470943,0.0002755998,0.00008812275,0.0004760981,0.00005341661],"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":[0.00002757503,0.00005053619,0.00000819614,0.0001623382,0.0001563189,0.00003528308,0.0006150422,0.5983979,0.3352912,0.0002653753,0.00002412415,0.06496614],"study_design_scores_gemma":[0.0002895303,0.00008568411,0.000002185792,0.00033228,0.00008025402,0.00003305518,0.0002688831,0.9230656,0.07296582,0.00274453,0.00003426073,0.00009788586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1428911,0.001094851,0.8554672,0.00002483012,0.0004378172,0.00003857287,0.00001570217,0.00002205475,0.000007812154],"genre_scores_gemma":[0.7128287,0.0004462102,0.2866383,0.000007715677,0.00004516071,3.798347e-7,0.00001601881,0.00001669496,8.806742e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5699375,"threshold_uncertainty_score":0.4458926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0300015315960435,"score_gpt":0.2366729121658772,"score_spread":0.2066713805698337,"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."}}