An Intrusion Detection Method Based on WPSO-SVM and KPCA
Lei Li · Journal of Information and Computational Science · 2014
With the spread of internet, the applications based on Internet are developing fast. However, it is generally accepted that internet security plays an increasing important role in our information society. As a significant measure, intrusion detection technique seems necessary. The traditional Intrusion Detection System has a high leaking and false alarm rate. We propose a new model based on Kernel Principal Component Analysis and Weight Particle Swarm Optimization-Support Vector Machine in this paper. The Kernel Principal Component Analysis method can be used in extracting the feature of nonlinear datasets, in order to reduce dimension. The Weight Particle Swarm Optimization helps to optimize the parameters in the Support Vector Machine. In the result, the model in this paper has a good performance.