{"id":"W4220850844","doi":"10.3389/fnbot.2022.836779","title":"Building Effective Machine Learning Models for Ankle Joint Power Estimation During Walking Using FMG Sensors","year":2022,"lang":"en","type":"article","venue":"Frontiers in Neurorobotics","topic":"Muscle activation and electromyography studies","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Ankle; Joint (building); Ground reaction force; Ground truth; Convolutional neural network; Deep learning; Gait; Pattern recognition (psychology); Machine learning; Simulation; Physical medicine and rehabilitation; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001952711,0.0001987818,0.0002709571,0.0004397166,0.0004482361,0.00003371446,0.00009478121,0.00003825747,0.000004433177],"category_scores_gemma":[0.00007744752,0.0002485949,0.00009770184,0.0004550087,0.00002037343,0.0002093725,0.00007849557,0.0004486315,6.586653e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003259285,"about_ca_system_score_gemma":0.000007467148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008736363,"about_ca_topic_score_gemma":0.000001071182,"domain_scores_codex":[0.9988164,0.00008914591,0.0002701127,0.0002476301,0.0001903846,0.0003863225],"domain_scores_gemma":[0.9996637,0.00007261868,0.00007296888,0.0001228998,0.00002819163,0.00003964671],"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":[0.00002577406,0.00001854293,0.001484699,0.00008151217,0.00005390856,0.000006358513,0.0007631458,0.986158,0.007269881,0.00008649015,0.0001081162,0.003943643],"study_design_scores_gemma":[0.0005383036,0.00006302215,0.002985246,0.00002390179,0.00002277169,0.00001031695,0.0002851703,0.9925123,0.002290125,0.0008942267,0.0001353628,0.0002392464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.474626,0.0003001889,0.5235603,0.00002925097,0.0008012854,0.0004254205,0.000005594,0.0001913456,0.0000605923],"genre_scores_gemma":[0.9155553,0.0000316645,0.08419834,0.00002291618,0.0000267367,0.00007779497,0.000007047387,0.00006695785,0.00001325487],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4409293,"threshold_uncertainty_score":0.9999966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01442805663940766,"score_gpt":0.2182186241995086,"score_spread":0.2037905675601009,"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."}}