{"id":"W4414567754","doi":"10.1016/j.mlwa.2025.100738","title":"Enhancing IDS performance through a comparative analysis of Random Forest, XGBoost, and Deep Neural Networks","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Hyperparameter; Random forest; Oversampling; Intrusion detection system; Artificial neural network; Reliability (semiconductor); Deep learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001899784,0.0001204862,0.0002890226,0.0001908406,0.000410617,0.00006620379,0.0002502459,0.00004361117,0.000007004763],"category_scores_gemma":[0.000008732603,0.0001004363,0.00005365882,0.002199677,0.00008427974,0.0002400783,0.0001240959,0.0002962315,7.699787e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001629895,"about_ca_system_score_gemma":0.00001371179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009681362,"about_ca_topic_score_gemma":0.0005438327,"domain_scores_codex":[0.9990961,0.00008531909,0.0002424187,0.000298138,0.0001173915,0.0001606367],"domain_scores_gemma":[0.9992028,0.0002230458,0.0001610187,0.0002902509,0.00008876799,0.00003405939],"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":[0.00007941404,0.00004188457,0.04790759,0.000025187,0.0002799208,2.614604e-7,0.00123915,0.9022366,0.00006719924,0.01992442,0.000007278489,0.02819108],"study_design_scores_gemma":[0.0004315343,0.00008826003,0.02055904,0.00001695791,0.0001614564,0.000002387624,0.00003141881,0.9757783,0.0001551691,0.0002245167,0.002455726,0.00009518018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1057052,0.000694267,0.8918253,0.000161007,0.00002056186,0.0002566453,6.023188e-7,0.00008682723,0.001249538],"genre_scores_gemma":[0.9889741,0.0001171491,0.01053209,0.0001159106,0.00002162259,0.0001359358,0.00001522187,0.000003412243,0.00008457188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8832689,"threshold_uncertainty_score":0.4095675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007243162782400938,"score_gpt":0.2491646181961229,"score_spread":0.2419214554137219,"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."}}