{"id":"W2733439154","doi":"10.1371/journal.pone.0180318","title":"Validation of accuracy of SVM-based fall detection system using real-world fall and non-fall datasets","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Simon Fraser University; Mitacs; Canada Research Chairs","keywords":"Accelerometer; Poison control; Fall prevention; Medicine; Injury prevention; Physical medicine and rehabilitation; Support vector machine; Falling (accident); Artificial intelligence; Waist; Accidental fall; Young adult; Suicide prevention; Wearable computer; Machine learning; Computer science; Medical emergency; Gerontology; Body mass index; Surgery; Internal medicine","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":[0.0005573463,0.0001466137,0.0004018068,0.0002334029,0.0001976213,0.0001946688,0.0005791816,0.00006903509,0.000001457474],"category_scores_gemma":[0.0002443028,0.0001563096,0.00004988217,0.0001600577,0.00006308691,0.001238584,0.0002409754,0.0001007903,0.000009051783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009249875,"about_ca_system_score_gemma":0.00008273607,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006986666,"about_ca_topic_score_gemma":0.002129133,"domain_scores_codex":[0.9984016,0.00014291,0.000452915,0.0003752872,0.0004575823,0.0001697159],"domain_scores_gemma":[0.9971777,0.0002947739,0.00101359,0.001144529,0.0002929169,0.00007654545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000878878,0.0009822557,0.06552957,0.002647067,0.0002951038,0.00001248556,0.0004816409,0.00005544881,0.911712,0.0001171658,0.0000291331,0.01805026],"study_design_scores_gemma":[0.001042205,0.0001297573,0.03373363,0.001709264,0.0001219473,0.000006610185,0.00003903706,0.1439363,0.8189692,0.00003346113,0.00002137184,0.0002572109],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8974633,0.00001344184,0.101409,0.00005078812,0.0001201175,0.0004471576,0.0001286823,0.00006622605,0.0003012665],"genre_scores_gemma":[0.9943776,0.000005080314,0.005471787,0.00001083531,0.00005777158,0.00001740702,0.00003078253,0.0000127037,0.00001607391],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1438808,"threshold_uncertainty_score":0.9996259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1018743187568561,"score_gpt":0.2945495375058662,"score_spread":0.1926752187490101,"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."}}