{"id":"W4378194571","doi":"10.1109/jbhi.2023.3272902","title":"Multi-Level Adversarial Spatio-Temporal Learning for Footstep Pressure Based FoG Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Australian Research Council; National Health and Medical Research Council; Parkinson Canada; National Natural Science Foundation of China; University of Sydney","keywords":"Computer science; Deep learning; Artificial intelligence; Discriminator; Adversarial system; Trajectory; Machine learning; Scheme (mathematics); Artificial neural network; Deep neural networks; Task (project management); Network architecture; Computer security; Engineering; Telecommunications","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":[0.0008157576,0.00008869103,0.0002422934,0.0003329451,0.0001256538,0.00003039931,0.00005619083,0.00008126512,0.00001646345],"category_scores_gemma":[0.00007522343,0.00007242057,0.00009375752,0.0002485148,0.00002908273,0.0001507176,0.000005968875,0.0002564784,0.00000719026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003134287,"about_ca_system_score_gemma":0.00008229927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008913642,"about_ca_topic_score_gemma":0.00002492821,"domain_scores_codex":[0.9987107,0.00001894611,0.0007881642,0.00003265702,0.0002465802,0.0002029334],"domain_scores_gemma":[0.9992611,0.00006942027,0.0002799733,0.00003580804,0.0001033105,0.0002504151],"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":[0.0001536962,0.0001083026,0.001117486,0.005229436,0.0004111644,0.000006852676,0.003219001,0.08047348,0.0003717328,0.000004952037,0.01769871,0.8912052],"study_design_scores_gemma":[0.001688218,0.0002473608,0.001447,0.0001099671,0.00004017251,0.0000113243,0.0003638132,0.9350383,0.0001256227,0.00001821618,0.06083167,0.00007837923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0493435,0.0001114896,0.9480773,0.0008882708,0.001232884,0.000182821,0.00003260045,0.0001087048,0.00002248421],"genre_scores_gemma":[0.9851142,0.000237183,0.01387705,0.0002473543,0.0004098073,0.0000051273,0.00004928847,0.0000123731,0.00004757263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9357708,"threshold_uncertainty_score":0.2953225,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06300356086924856,"score_gpt":0.3044785802258866,"score_spread":0.2414750193566381,"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."}}