{"id":"W2051700230","doi":"10.1007/s11517-012-0903-y","title":"Signal feature extraction by multi-scale PCA and its application to respiratory sound classification","year":2012,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria; Toronto Metropolitan University","funders":"Mitacs","keywords":"Feature extraction; Pattern recognition (psychology); Principal component analysis; Computer science; SIGNAL (programming language); Dimensionality reduction; Artificial intelligence; Feature (linguistics); Speech recognition; Scale (ratio); Signal subspace; Dimension (graph theory); Signal processing; Data mining; Noise (video); Mathematics; Digital signal processing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006239084,0.0001567337,0.0002283306,0.00009570843,0.00008983348,0.0000134211,0.00007704803,0.0003125956,0.00002485514],"category_scores_gemma":[0.0002915014,0.0001236016,0.00007023841,0.0002870868,0.00003714796,0.00007100926,0.00004701236,0.0004144671,0.00002138766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004559519,"about_ca_system_score_gemma":0.00001133521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002296295,"about_ca_topic_score_gemma":1.116621e-7,"domain_scores_codex":[0.9988913,0.00004542748,0.0002412831,0.0002808388,0.000245534,0.0002956455],"domain_scores_gemma":[0.9991972,0.0001429155,0.00005973911,0.000104289,0.00005731001,0.0004384797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005396391,0.0003321888,0.07301968,0.0001100273,0.00005151068,0.000003246316,0.0002680939,0.00009632371,0.8365206,0.0003158048,0.001423003,0.08780562],"study_design_scores_gemma":[0.0009706332,0.0003652084,0.8125861,0.0002417132,0.00005402125,0.00008936996,0.0001082951,0.1140909,0.03146305,0.00002087861,0.0395081,0.0005017499],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4761114,0.00114775,0.5216376,0.0003605875,0.00007614448,0.0003038224,0.000003505324,0.0002896099,0.00006961431],"genre_scores_gemma":[0.9904316,0.0000363148,0.008348271,0.0006894376,0.0003812487,0.00004293098,0.00004460062,0.00001296698,0.00001261557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8050575,"threshold_uncertainty_score":0.5040328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03288723149230043,"score_gpt":0.3120649679746269,"score_spread":0.2791777364823264,"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."}}