An Intrusion Detection Ensemble System Based on the Features Extracted by PCA and ICA

Intrusion detection system should be able to detect intrusion behaviors and learn novel intrusion types. In this paper, an intrusion detection ensemble system is proposed, which is integrated by two incremental SVM (support vector machine) subsystems. The two subsystems process the features extracted by PCA and ICA respectively. The intrusion information is represented by support vectors set and the weight of the integration is adjusted by genetic algorithm. Experiments show that the ensemble system combines the advantages of the two subsystems, and outperforms each of the subsystems and the standard SVM system.