{"id":"W4390832791","doi":"10.48550/arxiv.2401.05365","title":"Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Istituto Nazionale per l'Assicurazione Contro Gli Infortuni sul Lavoro","keywords":"Wearable computer; Computer science; Anticipation (artificial intelligence); Action (physics); Haptic technology; Motion (physics); Human–computer interaction; Artificial intelligence; Motion capture; Machine learning; Kinematics; SAFER; Computer security; Embedded system","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":[0.000365409,0.0006918965,0.0004992615,0.000381457,0.0001333666,0.0003406824,0.0005763497,0.000566132,0.001385787],"category_scores_gemma":[0.001319557,0.0002514043,0.0003895053,0.0001973204,0.0002784918,0.0005417353,0.0007042928,0.0005622376,0.0004668096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00021801,"about_ca_system_score_gemma":0.0003766607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002292801,"about_ca_topic_score_gemma":0.002990721,"domain_scores_codex":[0.999707,0.00005006795,0.00001509922,0.0001058388,0.00008501865,0.00003696521],"domain_scores_gemma":[0.9997354,0.0001118419,0.00005032342,0.00002913955,0.00004904978,0.00002424563],"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":[0.000702198,0.0004249687,0.008132948,0.0002887254,0.0001199604,0.0004890458,0.0003312357,0.143974,0.07107525,0.002451107,0.002472327,0.7695383],"study_design_scores_gemma":[0.00001388632,0.0002408724,0.006562343,0.00003300318,0.00003218708,0.0001918937,0.00004551382,0.9778447,0.01043813,0.003433911,0.00114154,0.00002203076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0666279,0.0006549751,0.9292129,0.0002500247,0.0001102192,0.00005278618,0.0001292253,0.001303315,0.001658684],"genre_scores_gemma":[0.903755,0.0004110437,0.09241877,0.0001332522,0.00009057566,0.00006527062,0.0001698598,0.00003238096,0.002923726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002292801,"threshold_uncertainty_score":0.00463587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4574780105570351,"score_gpt":0.3913472901757465,"score_spread":0.06613072038128864,"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."}}