{"id":"W2188762462","doi":"10.1109/biocas.2015.7348282","title":"Machine learning based detection of compensatory balance responses to lateral perturbation using wearable sensors","year":2015,"lang":"en","type":"article","venue":"","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Wearable computer; Support vector machine; Balance (ability); Computer science; Artificial intelligence; Gait analysis; Population; Inertial measurement unit; Dynamic balance; Machine learning; Gait; Physical medicine and rehabilitation; Engineering; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002846428,0.0003006083,0.0003579758,0.0005914112,0.0001107392,0.0002622386,0.0001775798,0.0003179089,0.0005142392],"category_scores_gemma":[0.001022543,0.0000952589,0.0001986074,0.0004090627,0.0001082011,0.0002514532,0.0001735647,0.0001321904,0.0002085185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018583,"about_ca_system_score_gemma":0.0001144541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006965097,"about_ca_topic_score_gemma":0.001186851,"domain_scores_codex":[0.9998054,0.00004469265,0.00001870013,0.00004604446,0.00006641769,0.00001880819],"domain_scores_gemma":[0.9996974,0.000122483,0.00006343817,0.00002037437,0.00008046049,0.00001593333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001243408,0.0007080204,0.1324514,0.000280348,0.0001783776,0.0003579615,0.0002519264,0.0221596,0.2275954,0.0003565604,0.001195767,0.6132212],"study_design_scores_gemma":[0.00004836727,0.001279361,0.3246076,0.00003415414,0.00008058157,0.0008648211,0.0001856664,0.630803,0.0406024,0.0006121976,0.0008418669,0.00003997646],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.895453,0.0003417337,0.1026018,0.00006377907,0.00005016294,0.00007259915,0.0002001873,0.0003651376,0.000851562],"genre_scores_gemma":[0.9785287,0.0001106572,0.02071661,0.00001651662,0.0000200142,0.00004296233,0.0001222227,0.000004809175,0.0004373543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0006965097,"threshold_uncertainty_score":0.001720309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05699728430221037,"score_gpt":0.3567520966250448,"score_spread":0.2997548123228345,"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."}}