{"id":"W2042583062","doi":"10.1371/journal.pone.0088825","title":"Effective Dysphonia Detection Using Feature Dimension Reduction and Kernel Density Estimation for Patients with Parkinson’s Disease","year":2014,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Fundamental Research Funds for the Central Universities; Program for New Century Excellent Talents in University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Pattern recognition (psychology); Linear discriminant analysis; Artificial intelligence; Kernel principal component analysis; Support vector machine; Receiver operating characteristic; Classifier (UML); Feature vector; Principal component analysis; Dimensionality reduction; Kernel density estimation; Computer science; Feature selection; Maximum a posteriori estimation; Mathematics; Statistics; Kernel method; Machine learning; Maximum likelihood","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":[0.0008482173,0.0003946377,0.0005639091,0.001001172,0.0001633,0.0004521637,0.000206593,0.00044116,0.0005017237],"category_scores_gemma":[0.00235642,0.0001576006,0.0003832745,0.0003723591,0.0001635041,0.000326974,0.0003679116,0.0002685857,0.0002361041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571861,"about_ca_system_score_gemma":0.0002214466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000784746,"about_ca_topic_score_gemma":0.001048579,"domain_scores_codex":[0.9996308,0.0001261043,0.00004514144,0.00007781219,0.00009202347,0.00002814623],"domain_scores_gemma":[0.9994665,0.0003000526,0.00007018408,0.00003241773,0.0001048764,0.00002601203],"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":[0.001818454,0.0002708995,0.1287822,0.0004720208,0.0002078319,0.001025486,0.0003777899,0.009509718,0.1165351,0.0005301062,0.001961946,0.7385085],"study_design_scores_gemma":[0.0001015308,0.0009583324,0.5335287,0.00007109724,0.000267694,0.003063382,0.0003715557,0.4250844,0.03209905,0.001380546,0.002947128,0.0001266962],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8413827,0.002398366,0.1541959,0.0002399616,0.00007139836,0.0001163782,0.0003181609,0.0004751217,0.0008018684],"genre_scores_gemma":[0.9662582,0.0004895345,0.03251752,0.00003382716,0.00002822659,0.00005226219,0.0002534095,0.00001601625,0.000351094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001001172,"threshold_uncertainty_score":0.004485846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01044502887431127,"score_gpt":0.2189926377762949,"score_spread":0.2085476089019836,"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."}}