Support vector machines with immune clonal parameter optimized for intrusion detection
The paper proposes a hybrid methodology that exploits support vector machines (SVM) and immune clonal selection algorithm (ICSA) in intrusion detection. Support vector machines (SVM) has been successfully applied to a wide range of applications. However, some parameters in SVM are usually selected by man's experience, which hampered its efficiency in practical application. To improve the capability of the SVM classifier, we propose immunity clonal selection algorithm (ICSA) to optimize the parameter of SVM. The dataset kddcup99 is our experiment data. The experimental result shows that the intrusion detection based on SVM with immune clonal parameter optimized can give higher recognition accuracy than the general SVM.
Author's Name: Chen, Z., Wang, S.
Volume: Volume 4
Issues: Issue 4
Keywords: Data classification, Immune clonal selection, Intrusion detection, Support vector machines