TY - JOUR ID - TI - Proposed Hybrid CorrelationFeatureSelectionForestPanalizedAttribute Approach to advance IDSs AU - Doaa Nteesha Mhawi PY - 2021 VL - 7 IS - 4 SP - 405 EP - 420 JO - Karbala International Journal of Modern Science مجلة كربلاء العالمية للعلوم الحديثة SN - 2405609X 24056103 AB - NetworkIntrusionDetectionSystem(NIDS), widely used network infrastructure. Although many datamininghas been used to increase the effectiveness of IDSs, current ID still struggle to perform well. therfore;proposed a new NIDS focused on feature_selection. The proposedCorrelationFeatureSelection_ForestPanalizedAttributes(CFS_FPA) used for dimensionality_reduction andselects the optimal_subset. based on two steps: frst check each feature with a target(class) and chooseonly features that most effective by applying CFS flter using a statistical_method, then applied FPA toselect only features will enhance ID and reduce_dimensionality. proposal tested with the NSLKDDexperimental results of accuracy 0.997% and 0.004 FAR, wherein UNSWNB15_dataset accuracy and FARare 0.995%, 0.008 consequently.

ER -