Intrusion detection research based on improved PSO and SVM

Based on the thought of crossover operation and mutation operation in genetic algorithm, this paper improves particle swarm optimization algorithm. The improved particle swarm optimization algorithm is used to optimize penalty parameter c and kernel function parameters g of SVM and the optimized model named new-PSO-SVM is established. KDD Cup 99 intrusion detection data set is used to carry out experiment. The results show that PSO optimization improves the classification accuracy rate of SVM.