Multiple Classifier Fusion With Cuttlefish Algorithm Based Feature Selection

Abstract

An intrusion detection system monitors whether the network event is malicious or normal for that network. Intrusion Detection Systems deal with a large amount of data, one of the crucial tasks of IDSs is to keep the best quality of features that represent the whole data and remove the redundant and irrelevant features.. Reducing the redundant information on a network packet shall improve the performance of the IDS A Wrapper based feature selection approach has been designed. The proposed model uses the cuttlefish algorithm (CFA) as a search strategy to ascertain the optimal subset of features and 3 different classifiers are used as a judgement on the selected features that are produced by the CFA. The NSL-KDD Cup 99 dataset is used to evaluate the proposed model. The results show that the feature subset obtained by using CFA gives a higher detection rate with a lower false alarm rate.