{"id":"W4384933106","doi":"10.24425/mms.2020.132784","title":"Comparison of methods for correcting outliers in ECG-based biometric identification","year":2020,"lang":"en","type":"article","venue":"Metrology and Measurement Systems","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut national de la recherche scientifique; Noda Institute for Scientific Research","keywords":"Biometrics; Outlier; Computer science; Pattern recognition (psychology); Heartbeat; Artificial intelligence; Identification (biology); Anomaly detection; Autoencoder; Euclidean distance; Data mining; Artificial neural network; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002926634,0.00008465676,0.0005354147,0.0004951578,0.00004305564,0.000007572377,0.00004446266,0.00008729586,0.000001500408],"category_scores_gemma":[0.001553431,0.00007481051,0.00007346752,0.0007357859,0.00002972881,0.00001783756,0.000006134195,0.0000967418,9.49052e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000620701,"about_ca_system_score_gemma":0.00003441177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008502191,"about_ca_topic_score_gemma":0.000004638878,"domain_scores_codex":[0.9987291,0.0002563855,0.0004975651,0.000217301,0.0001617563,0.0001379103],"domain_scores_gemma":[0.9991848,0.0001970764,0.0002372098,0.0001082493,0.0001968991,0.00007570166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000194875,0.0001165284,0.8450099,0.0006256442,0.0001615287,3.978128e-7,0.0002591186,0.0005728779,0.123965,0.000007483533,0.00007513731,0.02901146],"study_design_scores_gemma":[0.005407683,0.001661493,0.113556,0.0002862072,0.001225883,0.000004185285,0.004064652,0.7036813,0.167267,0.000008380833,0.002583833,0.0002532959],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2609937,0.005884217,0.7314187,0.0005871331,0.0005639722,0.0004752822,0.000002095759,0.00002957296,0.00004539886],"genre_scores_gemma":[0.9947411,0.000006254757,0.005050911,0.00004414437,0.00007617302,0.00005203725,0.000006743861,0.000007978008,0.0000146573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7337474,"threshold_uncertainty_score":0.3050684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2594407871444844,"score_gpt":0.4610721295953862,"score_spread":0.2016313424509019,"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."}}