Intrusion detection is a mechanism used to protect the system, analyze and predict the behaviors of the users. An ideal intrusion detection system hard to achieve due to nonlinearity, irrelevant, and redundant features. In this study a new anomaly-based intrusion detection model is introduced. The suggested system is based on particle swarm optimization, nonlinear multi-class and multi-kernel support vector machine. particle swarm optimization is used as feature selection by applying a new formula to update the position and the velocity of a particle, the support vector machine is used as classifier. The proposed model is tested and compared with the other methods by using the dataset KDD99. the results indicate that the new method is able to achieve better accuracy rates than the previous methods.

Login Required

Please login to access the full PDF of this article.

🔑 Author Login