{"id":"W4408529537","doi":"10.1038/s41598-025-93447-x","title":"Enhancing malware detection with feature selection and scaling techniques using machine learning models","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wycliffe College","funders":"Debreceni Egyetem","keywords":"Feature selection; Computer science; Normalization (sociology); Artificial intelligence; Preprocessor; Linear discriminant analysis; Machine learning; Malware; Boosting (machine learning); Gradient boosting; Pattern recognition (psychology); Data mining; Model selection; Principal component analysis; Data pre-processing; Feature (linguistics); Scaling; Random forest; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002446833,0.001520707,0.001113745,0.002053286,0.0004424312,0.001074338,0.0006108179,0.0005672035,0.0006181066],"category_scores_gemma":[0.005522968,0.0002367684,0.001085192,0.001218936,0.0003124552,0.001481692,0.0005872026,0.000903923,0.0005866611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000442155,"about_ca_system_score_gemma":0.0006302326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002019128,"about_ca_topic_score_gemma":0.002103327,"domain_scores_codex":[0.9990152,0.0002996575,0.0000667794,0.0002239426,0.0003094708,0.00008483059],"domain_scores_gemma":[0.9978829,0.001100579,0.0002082803,0.0003076525,0.0004482815,0.00005233388],"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":[0.0003286913,0.000660899,0.03128111,0.0002069488,0.0002604617,0.0001733699,0.0001386893,0.2249567,0.02291054,0.001373774,0.005351202,0.7123576],"study_design_scores_gemma":[0.00001607789,0.0002308079,0.006765167,0.00002392138,0.00005998968,0.0001278415,0.00005605536,0.9744275,0.01461258,0.001919744,0.001734068,0.00002625619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3856282,0.002335028,0.6013424,0.0007961383,0.0003103028,0.0003192452,0.0006679128,0.005945405,0.002655459],"genre_scores_gemma":[0.8041705,0.0005566244,0.1929584,0.0001324754,0.00009858645,0.0001592812,0.0009301445,0.00009090761,0.0009030888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002446833,"threshold_uncertainty_score":0.01294023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009857232811341644,"score_gpt":0.2476275985927596,"score_spread":0.2377703657814179,"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."}}