{"id":"W4365134853","doi":"10.1109/tnnls.2023.3264647","title":"Higher Order Polynomial Transformer for Fine-Grained Freezing of Gait Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Gait Recognition and Analysis","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Australian Research Council; Parkinson Canada","keywords":"Transformer; Discriminative model; Artificial intelligence; Computer science; Receiver operating characteristic; Feature learning; Deep learning; Bilinear interpolation; Machine learning; Pattern recognition (psychology); Computer vision; Voltage; Engineering","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":[0.0001517138,0.0001518749,0.0002402468,0.0002047788,0.0002106909,0.00004326676,0.00004099984,0.0001142976,0.00002825554],"category_scores_gemma":[0.000002906506,0.0001437099,0.0001404375,0.0004928685,0.00002334418,0.00008069305,2.309744e-7,0.0003003681,0.00000499845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001513496,"about_ca_system_score_gemma":0.000002982458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007088363,"about_ca_topic_score_gemma":0.0000703683,"domain_scores_codex":[0.9991814,0.00005220128,0.000276071,0.0001607028,0.00009583448,0.0002338092],"domain_scores_gemma":[0.9996233,0.0001560297,0.00004082264,0.00006920857,0.00004846363,0.00006216255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002988562,0.000008017651,0.00001323504,0.00009449121,0.00008320163,6.790605e-7,0.00006892243,0.9568375,0.005965793,0.000001393644,0.0001415858,0.03675527],"study_design_scores_gemma":[0.0005637814,0.0001090994,0.0001112805,0.00005499611,0.0000766819,0.00000434714,0.0001266815,0.9947946,0.00116133,0.00000104619,0.002840651,0.0001555183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2367728,0.00014683,0.7604803,0.00006606098,0.001613114,0.0002775028,0.0000156931,0.0004947185,0.0001330289],"genre_scores_gemma":[0.9984483,0.00007345284,0.00002179631,0.00001124134,0.0001938856,0.0000789611,0.00001150978,0.00004007518,0.001120843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7616755,"threshold_uncertainty_score":0.586032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01385227730591154,"score_gpt":0.2158337505440415,"score_spread":0.20198147323813,"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."}}