{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00318403,0.001689203,0.001876409,0.0009473807,0.0008823402,0.001265568,0.001843731,0.001224943,0.0007304303],"category_scores_gemma":[0.0153729,0.0004223784,0.0007549868,0.002090402,0.0009307732,0.002124523,0.001084449,0.00113635,0.0006177751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005060179,"about_ca_system_score_gemma":0.001281451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001785089,"about_ca_topic_score_gemma":0.001695395,"domain_scores_codex":[0.9970668,0.0008693024,0.0002475089,0.0005719755,0.0009635782,0.000280827],"domain_scores_gemma":[0.9943438,0.003410174,0.0003964389,0.0009805026,0.0007676429,0.0001015858],"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":[0.0005710619,0.0004950353,0.006472515,0.0004338948,0.0001294026,0.000491734,0.0003117248,0.3012036,0.02933595,0.00670158,0.0040785,0.649775],"study_design_scores_gemma":[0.00007256331,0.0003455232,0.00243601,0.00002107623,0.00005172279,0.0002451589,0.00008000408,0.9695907,0.01507846,0.009814212,0.002241318,0.0000232098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1695706,0.001219555,0.8251545,0.0006637935,0.0000857686,0.0002262514,0.0001187588,0.00157274,0.001388013],"genre_scores_gemma":[0.5806359,0.0005700391,0.4155135,0.0002133665,0.0002008876,0.0003899006,0.0004486983,0.0002353442,0.001792408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00318403,"threshold_uncertainty_score":0.01683897,"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."}}