{"id":"W2618086225","doi":"10.1186/s12984-017-0255-9","title":"Feature selection for elderly faller classification based on wearable sensors","year":2017,"lang":"en","type":"article","venue":"Journal of NeuroEngineering and Rehabilitation","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Accelerometer; Feature selection; Artificial intelligence; Standard deviation; Support vector machine; Feature (linguistics); Computer science; Feature vector; Acceleration; Pattern recognition (psychology); Wearable computer; Sensitivity (control systems); Mathematics; Engineering; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001157481,0.000744545,0.0009645729,0.001632231,0.0002515276,0.0004886921,0.0004163391,0.0003632005,0.001335088],"category_scores_gemma":[0.003801871,0.0001453806,0.001020481,0.000969032,0.000182726,0.0003648065,0.0003197817,0.0003745215,0.0003678104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004161482,"about_ca_system_score_gemma":0.0004519678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003792445,"about_ca_topic_score_gemma":0.002991096,"domain_scores_codex":[0.9995442,0.0001070393,0.00005013499,0.0001036594,0.0001331227,0.00006179909],"domain_scores_gemma":[0.9985458,0.0007530642,0.0001853134,0.00007170605,0.0003900113,0.00005415078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002730709,0.001081266,0.1817519,0.000366309,0.0005153641,0.0004996334,0.0002054913,0.0697464,0.03365605,0.0002794749,0.005643195,0.7035241],"study_design_scores_gemma":[0.0001256985,0.001161337,0.2140097,0.00008690615,0.0002676885,0.0005255386,0.000168061,0.7682385,0.0130659,0.0008081234,0.00148481,0.00005767331],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8578207,0.0008075707,0.13818,0.0002557518,0.00007932166,0.0002073501,0.001055155,0.0008715225,0.000722627],"genre_scores_gemma":[0.9723728,0.0001301409,0.02602677,0.00003645354,0.00003667741,0.0001308024,0.0009227128,0.00002065331,0.0003229224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003792445,"threshold_uncertainty_score":0.007540703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0227803725971979,"score_gpt":0.3365670524859618,"score_spread":0.3137866798887639,"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."}}