{"id":"W4287392316","doi":"10.48550/arxiv.2101.03423","title":"DeepFilter: an ECG baseline wander removal filter using deep learning\\n techniques","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Similarity (geometry); Noise (video); Computer science; Deep learning; Artificial intelligence; Filter (signal processing); Ambulatory; Noise reduction; Baseline (sea); Cosine similarity; Code (set theory); Mean squared error; Speech recognition; Pattern recognition (psychology); Machine learning; Medicine; Statistics; Mathematics; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005215871,0.0009964117,0.0007477282,0.0007763078,0.0002931838,0.0006073629,0.00115328,0.001006134,0.004930402],"category_scores_gemma":[0.0009908982,0.0003651816,0.0008805518,0.0005959839,0.0002237792,0.0007567905,0.0009798827,0.0013442,0.001939501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006216395,"about_ca_system_score_gemma":0.0009921413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009477357,"about_ca_topic_score_gemma":0.01558543,"domain_scores_codex":[0.9997854,0.00001704429,0.00001217034,0.00005317592,0.00009712714,0.00003518615],"domain_scores_gemma":[0.9998349,0.00004989926,0.00001591658,0.00002885632,0.00005445123,0.00001583544],"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":[0.0003223293,0.0001765394,0.00158834,0.0001518437,0.0001809195,0.0001765102,0.00005858867,0.05821652,0.02938236,0.002171264,0.02078779,0.8867871],"study_design_scores_gemma":[0.00005817826,0.0001797394,0.00180454,0.00003695458,0.00005626045,0.0002187125,0.00002008668,0.9581534,0.02558483,0.002178164,0.01167192,0.00003728158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01740681,0.0009209482,0.970928,0.0002058033,0.0002131027,0.00009001855,0.0008396976,0.007853707,0.001541858],"genre_scores_gemma":[0.2298665,0.001395089,0.7376691,0.0007800184,0.0001764328,0.0002904909,0.006669243,0.0008503219,0.02230287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009477357,"threshold_uncertainty_score":0.01884437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09151217058095598,"score_gpt":0.236353732565772,"score_spread":0.144841561984816,"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."}}