{"id":"W2890576388","doi":"10.1007/s41666-019-00061-4","title":"DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders","year":2019,"lang":"en","type":"preprint","venue":"Journal of Healthcare Informatics Research","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Toronto Rehabilitation Institute; University of Toronto","funders":"","keywords":"Autoencoder; Computer science; Artificial intelligence; Anomaly detection; Convolutional neural network; Pattern recognition (psychology); Modalities; Deep learning; Anomaly (physics); Perspective (graphical); Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002844337,0.0002869056,0.0005337769,0.001305058,0.0004513998,0.0004661273,0.001877506,0.000454771,0.000009264118],"category_scores_gemma":[0.0001466695,0.0002372552,0.0002221754,0.0008215792,0.0001839522,0.0009081512,0.0009319459,0.003474946,0.00006087879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001155778,"about_ca_system_score_gemma":0.004745226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007498077,"about_ca_topic_score_gemma":0.001227535,"domain_scores_codex":[0.9950613,0.0002497797,0.001583873,0.0002584679,0.002229248,0.0006172867],"domain_scores_gemma":[0.9918414,0.0003752392,0.001689703,0.0009263595,0.004783735,0.0003835268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00207486,0.001790002,0.03212875,0.02400278,0.00217283,0.000394405,0.06591062,0.3481289,0.0002985717,0.05600867,0.02419641,0.4428932],"study_design_scores_gemma":[0.001105602,0.003336316,0.003290738,0.001377745,0.00002826402,0.0009257689,0.003033785,0.9560695,0.001840001,0.01617611,0.0120834,0.0007327863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02442786,0.0001907881,0.9704174,0.002786622,0.0004186099,0.001071411,0.00001473799,0.00008228036,0.0005902999],"genre_scores_gemma":[0.8335031,0.0004619165,0.165414,0.0002171574,0.0001954084,0.00008668505,0.00001872727,0.00002276351,0.00008030119],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8090752,"threshold_uncertainty_score":0.9988241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05296658435555367,"score_gpt":0.3612514232270916,"score_spread":0.3082848388715379,"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."}}