{"id":"W4402464079","doi":"10.11159/cist24.174","title":"Feature Selection and Classification Performance: A Multi-Dataset Comparative Analysis Using Boruta Algorithm and Random Forest","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Centre National pour la Recherche Scientifique et Technique","keywords":"Random forest; Computer science; Feature selection; Selection (genetic algorithm); Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Statistical classification; Algorithm; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006534659,0.0001484803,0.0002711976,0.0006617505,0.0002674543,0.001035753,0.000302405,0.00003642615,1.349896e-7],"category_scores_gemma":[0.0000308329,0.0001027022,0.00002305386,0.002903945,0.0001495213,0.0004949219,0.0002026395,0.00022492,1.244167e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728983,"about_ca_system_score_gemma":0.00003865982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001095059,"about_ca_topic_score_gemma":0.000001141661,"domain_scores_codex":[0.9986981,0.00001511683,0.0001830724,0.0004942,0.0003775184,0.0002319524],"domain_scores_gemma":[0.9993783,0.0001307198,0.00007731748,0.00009506993,0.0001932626,0.0001253785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001923883,0.0004171002,0.03953813,0.003869858,0.001939421,0.00001535171,0.004334487,0.3994615,0.01718926,0.2080607,0.003651398,0.3213304],"study_design_scores_gemma":[0.0002309062,0.00006368941,0.007049555,0.0001256392,0.00004108403,0.00004961106,0.000006604185,0.9917925,0.0001832159,0.000005351035,0.0003344922,0.0001173345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1447731,0.001980557,0.8516368,0.0002982751,0.0006147529,0.0005443018,0.00001877341,0.0001102167,0.00002318782],"genre_scores_gemma":[0.9544019,0.0001200608,0.04526137,0.00001200049,0.00005918655,0.00001499292,0.000001486596,0.000005203053,0.0001237949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8096288,"threshold_uncertainty_score":0.9987791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02222257093869221,"score_gpt":0.2777503685963036,"score_spread":0.2555277976576114,"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."}}