{"id":"W4390573466","doi":"10.48550/arxiv.2401.01013","title":"A Novel Transformer-Based Self-Supervised Learning Method to Enhance Photoplethysmogram Signal Artifact Detection","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Université de Montréal","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Transformer; Machine learning; Boosting (machine learning); Semi-supervised learning; Labeled data; Pattern recognition (psychology); Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006713156,0.0006073733,0.0007648799,0.0009255699,0.0001963883,0.0001044522,0.0003532182,0.0005787302,0.0002552439],"category_scores_gemma":[0.0001485179,0.0007083356,0.0006835393,0.001414542,0.00006259148,0.00008236396,0.0002610908,0.002160349,0.0002690299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201157,"about_ca_system_score_gemma":0.0007956482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001327605,"about_ca_topic_score_gemma":0.0002539276,"domain_scores_codex":[0.9967731,0.0002290076,0.0003777451,0.001769959,0.000249148,0.0006010141],"domain_scores_gemma":[0.9977475,0.0006553435,0.0001573036,0.0007107776,0.0002635871,0.0004654684],"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":[0.001224261,0.001199472,0.0008298837,0.002986113,0.0008665831,0.0008600088,0.001479006,0.6512094,0.2976153,0.0001348176,0.000162053,0.04143305],"study_design_scores_gemma":[0.001600393,0.0008394149,0.0004979013,0.001521153,0.002083189,0.00001958494,0.0001442617,0.7328809,0.2467293,0.0005438612,0.01213534,0.001004591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4046079,0.00003883782,0.5913948,0.001557076,0.0002782354,0.001076105,0.00002270031,0.0008584408,0.0001658178],"genre_scores_gemma":[0.983791,0.00003498586,0.0128751,0.002434508,0.0001763112,0.00002207743,0.00005081851,0.0001196504,0.0004955801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.579183,"threshold_uncertainty_score":0.9995368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05945955498789388,"score_gpt":0.2694447775835405,"score_spread":0.2099852225956466,"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."}}