HYBRID FEATRUE SELECTION FOR NETWORK INTRUSION

In Computer Communications, collecting and storing characteristics about connections into a data set is needed to analyze its behaviour. Generally this data set is multidimensional and larger in size. When this data set is used for classification it may end with wrong results and it may also occupy more resources especially in terms of time. Most of the features present are redundant and inconsistent and affect the classification. In order to improve the efficiency of classification these redundancy and inconsistency features must be eliminated. In this paper, we have proposed a new algorithm based on hybrid method to identify the significance of features. The Proposed hybrid method combines Information Gain and Genetic Algorithm to select features. Clustering is carried out on selected features for classification. The experiment is conducted with NLS-KDD network intrusion data set. It classifies the data set with good accuracy.