{"id":"W2923142038","doi":"10.1371/journal.pone.0213584","title":"Performance comparison of linear and non-linear feature selection methods for the analysis of large survey datasets","year":2019,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Institute on Aging; SFU Community Trust Endowment Fund; Simon Fraser University; Spencer Foundation; University of Michigan; University of Wisconsin-Madison; AGE-WELL; National Science Foundation","keywords":"Feature selection; Linear model; Computer science; Feature (linguistics); Context (archaeology); Linear regression; Contrast (vision); Variable (mathematics); Selection (genetic algorithm); Data mining; Pattern recognition (psychology); Artificial intelligence; Machine learning; Mathematics","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":[0.0005554078,0.00005792454,0.0004265232,0.00005707825,0.00005877898,0.000001596837,0.00003702304,0.00004056636,0.00002483764],"category_scores_gemma":[0.0001333842,0.00003841124,0.00005150471,0.00035082,0.00002380621,0.00002318081,0.00002969734,0.00007981496,0.000001027232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007706903,"about_ca_system_score_gemma":0.000009918186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007310205,"about_ca_topic_score_gemma":0.00008377922,"domain_scores_codex":[0.9994827,0.00003489388,0.0001506543,0.0001076377,0.0001375858,0.00008656035],"domain_scores_gemma":[0.99912,0.0004256669,0.00009293648,0.0001334714,0.0002054697,0.00002247872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000647357,0.001102807,0.9833702,0.0005536295,0.002895122,2.808341e-8,0.00007101427,0.00003602808,0.009167316,0.000005950937,0.001630641,0.0005198715],"study_design_scores_gemma":[0.000909169,0.000374612,0.729238,0.00006421888,0.002034124,1.456806e-7,0.00006002652,0.2478936,0.01862832,0.000001114863,0.000756491,0.00004009726],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967103,0.0008474373,0.0008136181,0.0002359339,0.00001444357,0.0003615078,0.0009854424,0.000004239756,0.00002705672],"genre_scores_gemma":[0.9705163,0.0003948378,0.02769833,0.00005481111,0.00004336886,0.00001119108,0.001180777,0.000005653282,0.00009473613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2541322,"threshold_uncertainty_score":0.1566365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08651065112234753,"score_gpt":0.3913258380175523,"score_spread":0.3048151868952048,"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."}}