{"id":"W3037146579","doi":"10.1016/j.neunet.2020.06.015","title":"Heart sound classification based on improved MFCC features and convolutional recurrent neural networks","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":331,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Mel-frequency cepstrum; Computer science; Convolutional neural network; Recurrent neural network; Feature extraction; Pattern recognition (psychology); Artificial intelligence; Cepstrum; Speech recognition; Deep learning; Feature (linguistics); Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001188135,0.000230779,0.0003050069,0.00007524173,0.0001629383,0.00005859929,0.00007674196,0.0001905549,0.00002254378],"category_scores_gemma":[0.00005822512,0.000197514,0.000197719,0.0003643618,0.0001336054,0.00009756735,0.00002583063,0.000655507,0.000001370849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002644982,"about_ca_system_score_gemma":0.00001733663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005117979,"about_ca_topic_score_gemma":0.000001663664,"domain_scores_codex":[0.9986741,0.0001055858,0.0002667539,0.0004358919,0.0002196939,0.0002979673],"domain_scores_gemma":[0.9991895,0.0001468324,0.0001026028,0.0001900389,0.00009603112,0.0002750122],"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":[0.01095781,0.0009412506,0.1368266,0.0004299911,0.0004755369,0.0001000008,0.0005548566,0.3213176,0.01279281,0.002129322,0.289472,0.2240023],"study_design_scores_gemma":[0.000876438,0.0006409588,0.1477726,0.00003383272,0.00005642426,0.00002102183,0.00001774923,0.8494401,0.00007578947,0.00003353828,0.0008706622,0.0001608875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6821698,0.009623324,0.2098114,0.08417113,0.003024945,0.005522734,0.0001073799,0.003417994,0.002151337],"genre_scores_gemma":[0.988013,0.00007817025,0.0004627203,0.01021693,0.0009058645,0.00005907215,0.0002214875,0.00002499031,0.00001774265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5281225,"threshold_uncertainty_score":0.8054389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02812600443625967,"score_gpt":0.2769781050157802,"score_spread":0.2488521005795206,"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."}}