基于启发式SVM的入侵检测系统研究

文章针对支持向量机参数一直存在根据经验确定不足的问题,提出将启发式支持向量机快速学习算法应用于入侵检测系统中。为了使支持向量分类机获得更好的分类性能,该算法提出以启发式规则选取对分类器最有利的样本进行训练,以确定支持向量机的参数,并采用内积矩阵分解算法提高分类速度,达到提高学习速度的目的。实验表明该算法在入侵检测系统中的应用优于标准支持向量机算法。

Study on intrusion detection system based on heuristic support vector classification machines

This article advances that put the fast learning algorithm of heuristic support vector machine applied in intrusion detection system that aiming at the problem of determining deficiency by experience which exist in the parameters of support vector machines. In order to make support vector classifier obtain better classification performance, this thesis uses heuristic rules to select the most advantageous samples, and determine the parameters of SVM by train them. In order to improve the learning speed, it uses the inner product matrix decomposing algorithm to improve the classifying speed. The results of experiment show that the intrusion detection system (IDS) based on the heuristic support vector classification machines possesses better than the IDS based on Standards SVM.