Improving the Computer Network Intrusion Detection Performance Using the Relevance Vector Machine with Chebyshev Chaotic Map

A novel computer network intrusion detection approach based on the relevance vector machine (RVM) classification is proposed, where a Chebyshev chaotic map is introduced as the inner training noise signal. According to the known distribution property of the Chebyshev map, the iteration process of RVM classifier can be derived and be realized easily. Compared with the support vector machine (SVM) classification method, it can be found from the simulation results that the proposed approach can reach higher detection probabilities under different kinds of intrusion signals, and the corresponding computational complexity can be reduced efficiently, which guarantee the reliability of this RVM-based approach with Chebyshev chaotic map.