Ensemble learning classifiers hybrid feature selection for enhancing performance of intrusion detection system

Abstract

Feature selection (FS) plays an important role in the construction of efficient ensemble classifiers; particularly for intrusion detection system (IDS). An IDS is a utilized in a network architecture to protect the availability of sensitive information. However, existing IDSs suffer from redundancy, high dimensionality, and high false alarm rate (FAR). Also, lots of models are constructed for outdated datasets, which makes them less flexible to deal with new assaults. Therefore, this paper proposes a new IDS relies on hybrid FS and ensemble classifiers. A hybrid FS approach consists of two techniques, hard-voting and mean. In contrast to recent papers, we use three different FS approaches: extra tree classifier importance as an embedded FS, recursive feature elimination (RFE) as a wrapper FS, and mutual information (MI) as a filter FS. Then, a hard-voting technique has been used to fuse output of these approaches and obtain a reduced subset of features. Since each feature has three weights, a mean technique has been utilized to assign one weight to each feature and obtain an optimal subset of features. The experimental outcomes, utilizing the modern InSDN dataset, confirm that the proposed hybrid FS with ensemble soft voting classifier achieves better results than other ensemble and individual classifiers due to several measures.