{"id":"W4297900902","doi":"10.7717/peerj-cs.1081","title":"Minimizing features while maintaining performance in data classification problems","year":2022,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Feature (linguistics); Computer science; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Machine learning; Selection (genetic algorithm); Data mining; Reduction (mathematics); Dimensionality reduction; 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":[0.002029583,0.0001258329,0.0001295871,0.0003956711,0.00080293,0.0004241705,0.004371025,0.00002261725,0.00001841774],"category_scores_gemma":[0.00002733758,0.0001239451,0.00001994685,0.001792616,0.0001153265,0.00245892,0.004040695,0.0003154904,0.00002424227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001304042,"about_ca_system_score_gemma":0.0002369008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002187946,"about_ca_topic_score_gemma":0.00000855876,"domain_scores_codex":[0.9973835,0.00009291973,0.0002587256,0.0009506982,0.0008595742,0.0004546341],"domain_scores_gemma":[0.9984203,0.00006881542,0.0001238732,0.001212294,0.00008285182,0.00009186192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002053857,0.0003906916,0.01262339,0.00005916552,0.00000746698,0.00003644307,0.009400315,0.08733613,0.01156837,0.009457512,0.01302625,0.8560737],"study_design_scores_gemma":[0.0002109116,0.0000670363,0.03475063,0.00003749095,0.000001033557,0.00004834793,0.0001112903,0.9574881,0.000422633,0.0003080722,0.006369765,0.0001846621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2326741,0.0001624428,0.7559265,0.00552458,0.00233281,0.0005398008,0.00001580762,0.000396056,0.002427876],"genre_scores_gemma":[0.9004148,0.000009296375,0.09882585,0.0005315412,0.00005845213,0.00004818604,0.00003105361,0.000005579745,0.00007522286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.870152,"threshold_uncertainty_score":0.8122524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07281756164724634,"score_gpt":0.2739164239555219,"score_spread":0.2010988623082756,"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."}}