A Parameter Selection Approach for Mixtures of Kernels Using Immune Evolutionary Algorithm and its Application to IDSs

Supervised anomaly intrusion detection systems (IDSs) based on Support Vector Machines (SVMs) classification technique have attracted much more attention today. In these systems, the characteristics of kernels have great in- fluence on learning and prediction results for IDSs. How- ever, selecting feasible parameters can be time-consuming as the number of parameters and the size of the dataset in- crease. In this paper, an immune evolutionary based ker- nel parameter selection approach is proposed. Through the simulation of the denial of service attacks in mobile ad-hoc networks (MANETs), the result dataset is used for compar- ing the prediction performance using different types of ker- nels. At the same time, the parameter selection efficiency of the proposed approach is also compared with the differen- tial evolution algorithm.