Feature selection based on Rough set and modified genetic algorithm for intrusion detection

In the Network Intrusion Detection, the large number of features increases the time and space cost, besides the irrelative redundant characteristics make the detection accuracy dropped. In order to improve detection accuracy and efficiency, a new Feature Selection method based on Rough Sets and improved Genetic Algorithms is proposed for Network Intrusion Detection. Firstly, the features are filtered by virtue of the Rough Sets theory; then in the remaining feature subset, the Optimal subset will be found out through the Genetic Algorithm improved with Population Clustering approach for the best ultimate optimized results. Finally, the effectiveness of the algorithm is tested on the classical KDD CUP 99 data sets, using the SVM classifier for performance evaluation. The experiment shows that the new method improves the accuracy and efficiency in Network Intrusion Detection compared with the related researches of the intrusion detection system.