A Minimal Subset of Features Using Correlation Feature Selection Model for Intrusion Detection System

The intrusion detection system (IDS) research field has grown tremendously in the past decade. Current IDS uses all data features to detect intrusions. Some of the features may be irrelevant and redundant to the detection process. The purpose of this study is to identify a minimal subset of relevant features to design effective intrusion detection system. A proposed minimal subset of features is built by selecting common features from six search methods with correlation feature selection method. The paper presents empirical comparison between 7 reduced subsets and the given complete set of features. The simulation results have shown slightly better performance using only 12 proposed features compared to others.