{"id":"W2790696131","doi":"10.1177/2055668318761523","title":"Classification-based Segmentation for Rehabilitation Exercise Monitoring","year":2018,"lang":"en","type":"article","venue":"Journal of Rehabilitation and Assistive Technologies Engineering","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Toronto Rehabilitation Institute","keywords":"Segmentation; Artificial intelligence; Computer science; Robustness (evolution); Rehabilitation; Classifier (UML); Computation; Pattern recognition (psychology); Machine learning; Demographics; Training set; Motion (physics); Medicine; Physical therapy; Algorithm","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":[0.0004286889,0.00009999637,0.0001483945,0.0004561451,0.0001149904,0.00008213644,0.0001642836,0.00007575511,0.000001475662],"category_scores_gemma":[0.001357311,0.000092579,0.00007298201,0.0002929931,0.00008539121,0.0006102615,0.00002030531,0.0001032234,0.000001618192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001039889,"about_ca_system_score_gemma":0.00003440816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.711563e-7,"about_ca_topic_score_gemma":2.089614e-7,"domain_scores_codex":[0.9991859,0.0000184857,0.0003594393,0.0001639884,0.000158835,0.0001133623],"domain_scores_gemma":[0.9980753,0.0008501427,0.0002715077,0.0001381133,0.0006342999,0.00003063507],"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":[0.0001262741,0.0002144698,0.01956269,0.0004176613,0.00006243956,0.000001493658,0.001592666,0.001194278,0.09493086,0.01749407,0.000793924,0.8636092],"study_design_scores_gemma":[0.004179059,0.007363706,0.4619901,0.001913436,0.000125947,0.00002458464,0.0130239,0.3272879,0.1589771,0.01840002,0.005798484,0.0009157258],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2082653,0.0001115306,0.7885375,0.002231747,0.0003810864,0.000233299,0.00000192,0.0002208229,0.00001680938],"genre_scores_gemma":[0.6401176,0.0000119144,0.3597755,0.000005113935,0.00004577009,0.00003463202,8.883421e-7,0.000004933735,0.000003596915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8626934,"threshold_uncertainty_score":0.3775262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01545848142487814,"score_gpt":0.268660536418438,"score_spread":0.2532020549935599,"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."}}