{"id":"W4391932402","doi":"10.1080/10255842.2024.2317438","title":"A multi-branch convolutional neural network for snoring detection based on audio","year":2024,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics & Biomedical Engineering","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Convolutional neural network; Mel-frequency cepstrum; Preprocessor; Speech recognition; Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Deep learning; Frequency domain; Feature extraction; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001830343,0.0002939853,0.0004242595,0.0009751779,0.00006692559,0.00005941807,0.0001888976,0.0002802656,0.00002355066],"category_scores_gemma":[0.0002918711,0.0002771581,0.0002241218,0.001560854,0.00006184132,0.00007327113,0.00009453211,0.0007119428,0.00000876454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004949371,"about_ca_system_score_gemma":0.00006970997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000558522,"about_ca_topic_score_gemma":6.404109e-7,"domain_scores_codex":[0.9975577,0.0001255494,0.0004637743,0.0006584402,0.000479133,0.0007154173],"domain_scores_gemma":[0.998142,0.001138851,0.00003335435,0.0002867038,0.00008674071,0.0003123739],"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":[0.0001234118,0.00013163,0.00001174486,0.0006959566,0.0000973055,0.00007333176,0.00003388305,0.01402368,0.4598294,0.0004367594,0.00004834925,0.5244946],"study_design_scores_gemma":[0.001614382,0.0005237477,0.0002691102,0.0004172416,0.00003353862,0.00005073197,0.000002402011,0.9730667,0.01845076,0.000174309,0.0051584,0.000238667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00529452,0.0004127714,0.9867486,0.0003261394,0.006130019,0.0007023149,0.00001946545,0.0003628641,0.000003308205],"genre_scores_gemma":[0.2698616,0.000005353825,0.7282123,0.0001307881,0.001521931,0.0001535059,0.0000360652,0.00006942153,0.000009079765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.959043,"threshold_uncertainty_score":0.9999681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03844811159422055,"score_gpt":0.3696283273055721,"score_spread":0.3311802157113515,"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."}}