An optimized network intrusion detection model

intrusion detection is one of the important means to ensure network security. Aiming at the problem that the current network intrusion detection model can not obtain the ideal network intrusion detection effect, a network intrusion detection model based on feature selection is designed. Firstly, the evaluation criteria of network features are mapped to high-dimensional space for calculation through radial basis kernel function, then the relationship between network feature evaluation and subsequent network intrusion classifier is established, and the parameter design problem of classifier is solved in the feature selection stage. Finally, the network intrusion detection model is established, and the model is analyzed by KDD CUP99 data set. The results show that, The proposed method greatly improves the network intrusion detection rate, the false detection rate and missed detection rate of network intrusion are low, and the overall effect of network intrusion detection is significantly better than other current network intrusion detection models.