杂草算法优化支持向量机的网络入侵检测

为了解决支持向量机(优化SVM)在网络入侵检测中的参数优化问题,以提高网络入侵检测性能,提出一种入侵杂草(IWO)算法SVM的网络入侵检测模型(IWO-SVM)。首先将SVM参数编码为入侵杂草,以检测率作为优化目标函数,然后通过模拟杂草入侵种子的生长过程找到最SVM的最优参数,从而最优网络入侵检测模型,后在采用KDD99数据集性能测试。结果表明IWO-SVM是一种检测检测率高、速度快的网络入侵检测模型。

Network intrusion detection based on support vector machine optimized by invasive weed optimization algorithm

In order to solve the parameters optimization problems of support vector machine （ SVM） in network intru_sion detection and improve the network intrusion detection performance, this paper proposed a network intrusion detection model based on support vector machine optimized by invasive weed optimization algorithm. Firstly the parameters of SVM are encoded as invasion weeds, and k intrusion detection rate is taken as fitness function, and then the optimal parame_ters of SVM are found through simulation growth of weed seeds, and the optimal intrusion detection model is established, finally the simulation test is carried out with KDD99 data set. The results showed that the IWO-SVM is a high detection ratio and fast speed intrusion detection model.