The paper presents an improved support vector machine （SVM） by combining principal component analysis （PCA） and particle swarm optimization （PSO）. Then, the improved SVM is applied to the intrusion detection sys...The paper presents an improved support vector machine （SVM） by combining principal component analysis （PCA） and particle swarm optimization （PSO）. Then, the improved SVM is applied to the intrusion detection system （IDS） to improve the detection rate. First, PCA is used to reduce the dimension of feature vectors. Second, we use the PSO algorithm to optimize the punishment factor C and kernel parameters oin SVM. The experimental results indicate that the intrusion detection rate （97.752 8%） of improved SVM by combining PCA and PSO is higher than those （95.635 5%） of PSO-SVM and those （90.476 2%） of standard SVM with KDD Cup 1999 data set.展开更多
基金Supported by the Introduction of Key Discipline Talented People in the 11th Five-Year Plan of Tianjin (20090047)
文摘The paper presents an improved support vector machine （SVM） by combining principal component analysis （PCA） and particle swarm optimization （PSO）. Then, the improved SVM is applied to the intrusion detection system （IDS） to improve the detection rate. First, PCA is used to reduce the dimension of feature vectors. Second, we use the PSO algorithm to optimize the punishment factor C and kernel parameters oin SVM. The experimental results indicate that the intrusion detection rate （97.752 8%） of improved SVM by combining PCA and PSO is higher than those （95.635 5%） of PSO-SVM and those （90.476 2%） of standard SVM with KDD Cup 1999 data set.
