{"id":"W4390196927","doi":"10.54254/2753-8818/28/20230401","title":"Using upsampling CONV-LSTM with metadata embedding for respiratory sound classification","year":2023,"lang":"en","type":"article","venue":"Theoretical and Natural Science","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Upsampling; Computer science; Speech recognition; Artificial intelligence; Auscultation; Convolutional neural network; Embedding; Respiratory sounds; Wheeze; Medicine; Respiratory system; Internal medicine","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":[0.0003429768,0.001038393,0.0005180439,0.0005068523,0.0002324338,0.0003945489,0.0007942939,0.0007857078,0.001831454],"category_scores_gemma":[0.0008628166,0.0002515875,0.0005577381,0.0005137454,0.0001836965,0.001192211,0.0005588175,0.0009232131,0.001114893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004383161,"about_ca_system_score_gemma":0.0006796994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007533706,"about_ca_topic_score_gemma":0.009925996,"domain_scores_codex":[0.9998162,0.00002408791,0.00001497684,0.00005935997,0.00004593865,0.00003947569],"domain_scores_gemma":[0.9998001,0.00005404195,0.00001988031,0.00002590178,0.00008724486,0.00001280095],"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":[0.0004090182,0.0003773315,0.003075609,0.0001783515,0.0001170922,0.0002502056,0.00007751369,0.1117501,0.04360026,0.001287542,0.01210293,0.8267739],"study_design_scores_gemma":[0.00001220853,0.00008672394,0.0006577202,0.00001458342,0.00002592008,0.0000558737,0.00001850923,0.989052,0.008135494,0.0008311144,0.001098086,0.00001168583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2663659,0.005323322,0.7044022,0.001244697,0.001258051,0.0001734777,0.001794079,0.01217881,0.007259393],"genre_scores_gemma":[0.8572046,0.001156609,0.1264999,0.0005294247,0.0002122931,0.0001150478,0.003964143,0.0001675088,0.01015042],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007533706,"threshold_uncertainty_score":0.01497972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0786082404058917,"score_gpt":0.3967162927872392,"score_spread":0.3181080523813475,"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."}}