{"id":"W2947659587","doi":"10.1109/jbhi.2019.2920356","title":"Separation of Fetal-ECG From Single-Channel Abdominal ECG Using Activation Scaled Non-Negative Matrix Factorization","year":2019,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Non-negative matrix factorization; Pattern recognition (psychology); Computer science; Artificial intelligence; Blind signal separation; Matrix decomposition; Electrocardiography; SIGNAL (programming language); Fetus; Independent component analysis; Channel (broadcasting); Medicine; Cardiology; Pregnancy","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":[0.0009891267,0.0001213068,0.000364644,0.0003395187,0.0000819092,0.00008169593,0.0002243009,0.0001377857,0.000006914651],"category_scores_gemma":[0.0000538122,0.00009780774,0.00005870995,0.0003449558,0.00006384517,0.001526967,0.00004331976,0.0002406554,0.000003371123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001297807,"about_ca_system_score_gemma":0.000378271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000430158,"about_ca_topic_score_gemma":0.000001576775,"domain_scores_codex":[0.997694,0.00007379871,0.001375922,0.00007725178,0.0006149188,0.0001641528],"domain_scores_gemma":[0.9972446,0.0001505193,0.001958422,0.000135439,0.0003261631,0.0001848608],"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":[0.001026268,0.002298674,0.006028133,0.003628799,0.0005754639,0.000009806021,0.1694618,0.009042974,0.1592502,0.002659409,0.005483917,0.6405346],"study_design_scores_gemma":[0.001047055,0.0009979935,0.001059031,0.0004145785,0.00001020105,0.00002724023,0.0005046357,0.9703012,0.0221358,0.003189411,0.0001884289,0.0001244825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2596318,0.0000152367,0.7390916,0.0007397773,0.0003019461,0.0001724179,0.000006005039,0.0000144208,0.00002687116],"genre_scores_gemma":[0.7288629,0.00004661179,0.2706094,0.0003672724,0.00009365269,6.62195e-7,0.000007560131,0.00000447408,0.000007403469],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9612582,"threshold_uncertainty_score":0.3988484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04086625933964426,"score_gpt":0.3411678111525153,"score_spread":0.300301551812871,"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."}}