An Efficient Feature Selection for Intrusion Detection System Using B-HKNN and C² Search Based Learning Model

With the emergence of big data era, the dimensions of data are enhanced exponentially and it becomes a difficult task to handle information of high dimensions in various sectors like text mining, machine learning and data analysis. Redundant and inappropriate feature enhances the complexities in dimensions that further results in poor performances. In the intrusion detection system, the feature selection is considered as one of the most significant processes to improve the performances of the system. Due to high dimensional data, there occurs a drop in accuracy and efficiency. To overcome such drawback, this paper proposes three major phases namely the data pre-processing, feature selection and classification phases. In data-pre processing phase, the input data comprising of various noise signals, high dimensional and redundant data, numerous irrelevant features etc. are extracted. The second phase involves the selection of features using cooperative and competitive (C²) search based learning algorithm. In the classification phase, the extracted features are classified optimally using Bonferroni based Hybrid k-nearest neighbour (B-HkNN) algorithm thereby obtaining an optimal intrusion detection system. Furthermore, the proposed approach based on intrusion detection system is evaluated by the standard CICIDS2017 and ADFA-LD datasets to determine the accuracy and efficiency of the system.