{"id":"W4322501043","doi":"10.3390/diagnostics13050879","title":"Using CCA-Fused Cepstral Features in a Deep Learning-Based Cry Diagnostic System for Detecting an Ensemble of Pathologies in Newborns","year":2023,"lang":"en","type":"article","venue":"Diagnostics","topic":"Infant Health and Development","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Bill and Melinda Gates Foundation","keywords":"Artificial intelligence; Cepstrum; Ensemble learning; Computer science; Pattern recognition (psychology); Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003576766,0.0005342662,0.0004000682,0.0005800315,0.0001877462,0.0003162195,0.0003946068,0.0004170539,0.0008016481],"category_scores_gemma":[0.0009514844,0.0001821699,0.0003253828,0.0003266503,0.0001324546,0.0003632497,0.0004146603,0.0005107402,0.0004516312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002802743,"about_ca_system_score_gemma":0.0006520085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003871722,"about_ca_topic_score_gemma":0.005285672,"domain_scores_codex":[0.9998111,0.00002327548,0.00001480185,0.00005346277,0.00006156092,0.00003580206],"domain_scores_gemma":[0.9997817,0.00005600601,0.00002548617,0.00001550569,0.00009921619,0.00002215921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005189967,0.0002080033,0.009510287,0.0001743786,0.00009781856,0.0004730035,0.0001538655,0.03184089,0.2065445,0.0008521085,0.003257596,0.7463686],"study_design_scores_gemma":[0.00003351059,0.0003508557,0.01510689,0.00005177535,0.0001406939,0.0005722174,0.00008597409,0.8928083,0.08726674,0.0006748267,0.002850729,0.00005756436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3222681,0.00141604,0.6678608,0.0004012415,0.0002607934,0.0001588959,0.0005327458,0.003399077,0.003702361],"genre_scores_gemma":[0.859153,0.0004592818,0.1375846,0.0001933002,0.00006268994,0.00009081371,0.0004511296,0.00004298098,0.001962158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003871722,"threshold_uncertainty_score":0.007698357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08644041638731675,"score_gpt":0.4154188374243178,"score_spread":0.3289784210370011,"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."}}