{"id":"W2022760441","doi":"10.1016/j.neucom.2013.07.033","title":"New approaches for spectro-temporal feature extraction with applications to respiratory sound classification","year":2013,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"Nanyang Technological University","keywords":"Pattern recognition (psychology); Kurtosis; Computer science; Feature extraction; Sample entropy; Artificial intelligence; Support vector machine; Speech recognition; Cluster analysis; Auscultation; Entropy (arrow of time); RSS; Audio signal; Frequency domain; Euclidean distance; Histogram; Mathematics; Statistics; Computer vision; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000985028,0.0001217371,0.000148358,0.0001600821,0.0001526937,0.00005896602,0.00006700286,0.00006708264,0.000005426859],"category_scores_gemma":[0.00001559354,0.0001035514,0.00008214793,0.0003889169,0.00001709776,0.0001286012,0.00001153173,0.0001673462,0.00001535799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003127841,"about_ca_system_score_gemma":0.00005145244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001110181,"about_ca_topic_score_gemma":0.00000238202,"domain_scores_codex":[0.9991918,0.00002074531,0.0001591198,0.0003201446,0.0001378082,0.0001704063],"domain_scores_gemma":[0.9993923,0.00005907943,0.0001070392,0.0002138092,0.00009072265,0.0001371058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000363573,0.000334053,0.03947913,0.000375608,0.000176573,0.000004012481,0.0009502658,0.0004028502,0.1784184,0.01389351,0.05413418,0.7114678],"study_design_scores_gemma":[0.002841216,0.001905811,0.6438512,0.0002047319,0.0002557653,0.0001375999,0.0008902643,0.005297887,0.0681061,0.00841016,0.2672862,0.0008130171],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07180972,0.00004727688,0.9209508,0.002323999,0.00002935282,0.00280247,0.000001831382,0.0003588731,0.001675645],"genre_scores_gemma":[0.8267089,0.000001158866,0.1712287,0.0007400765,0.0005117285,0.0005667686,0.00002946348,0.00002518453,0.0001879413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7548992,"threshold_uncertainty_score":0.4222703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07218826976064648,"score_gpt":0.315645904783708,"score_spread":0.2434576350230616,"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."}}