{"id":"W4313056376","doi":"10.1109/ijcnn55064.2022.9892600","title":"Analysis of Augmentations for Contrastive ECG Representation Learning","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Encoder; Range (aeronautics); Noise (video); Representation (politics); Supervised learning; Natural language processing; Machine learning; Pattern recognition (psychology); Speech recognition; Image (mathematics); Artificial neural network; Engineering","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":[0.004309952,0.001289862,0.0008756029,0.0007248202,0.0004232363,0.0010452,0.001570293,0.001290253,0.002193279],"category_scores_gemma":[0.02247282,0.0004876793,0.0009820042,0.0004637055,0.001052176,0.002588897,0.001727223,0.002080783,0.0005526166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008496488,"about_ca_system_score_gemma":0.0008256729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001070773,"about_ca_topic_score_gemma":0.001299618,"domain_scores_codex":[0.9985173,0.0006126075,0.0001051446,0.00031027,0.000335319,0.0001193214],"domain_scores_gemma":[0.9878454,0.008831668,0.0006424884,0.001397274,0.001077712,0.0002054739],"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":[0.0009147167,0.0005868159,0.006345827,0.0005779862,0.0002511244,0.0002586071,0.0003001364,0.5255105,0.02587393,0.01707096,0.003156057,0.4191534],"study_design_scores_gemma":[0.00001638154,0.0002064538,0.0007511849,0.00003838509,0.00003868017,0.000101929,0.00001718053,0.9871547,0.005889669,0.004861098,0.0009120202,0.00001229023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1404417,0.003571065,0.8470009,0.0007317448,0.0001584804,0.0002624185,0.0002195922,0.002492428,0.00512169],"genre_scores_gemma":[0.8115923,0.0008737662,0.1836738,0.000301222,0.000131761,0.0003240044,0.0006090672,0.0002688284,0.002225145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004309952,"threshold_uncertainty_score":0.02279347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05764719685359893,"score_gpt":0.3430698317087837,"score_spread":0.2854226348551848,"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."}}