基于云PSO 的RVM入侵检测

入侵检测可为计算机网络信息提供安全保障,在其方法研究中,由于相关向量机(RVM)具有高稀疏性且预测中使用概率因素,在网络入侵检测中优于支持向量机.然而RVM的核函数参数是经验估计的,为此,提出一种基于云模型的粒子群优化算法的RVM方法,即采用云粒子群算法确定RVM的核参数,构建RVM分类模型,再采用一对一分类方法进行多类检测分类.经入侵检测实验研究,所得结果表明所提出的方法优于基于常规相关向量机的检测方法,且具有更高的入侵检测精度.

Intrusion detection using relevance vector machine based on cloud particle swarm optimization

Intrusion detection can protect computer network information. In the research based on this method, due to the relevance vector machine(RVM) has high sparseness and uses probability factor in predict, which is superior to the support vector machine(SVM) in the network intrusion detection. However, the kernel function parameters of RVM are estimated by experience. Therefore, a kind of RVM method based on the cloud particle swarm optimization(PSO) algorithm is proposed, which adopts the CPSO algorithm to determine the kernel parameter of RVM, then builds RVM model and uses the one-against-one classification method to finish multi-class intrusion detection. The experimental researches on intrusion detection show that the proposed method is superior to the common RVM-based detection method and has high prediction accuracy in intrusion detection.