基于QPSO优化投影寻踪的网络入侵检测方法  

Network intrusion detection method based on QPSO optimization projection pursuit algorithm

作　　者：朱丽华[1] 刘以安[1] 魏敏[1] 

机构地区：[1]江南大学信息工程学院,江苏无锡214122

出　　处：《计算机工程与应用》2011年第28期80-82,134,共4页Computer Engineering and Applications

基　　金：教育部重点科学研究基金项目(No.105087)

摘　　要：为了提高入侵检测系统的检测率,降低误报率,提出应用QPSO搜索投影寻踪最优投影方向的入侵检测算法,并利用投影寻踪和聚类相结合的思想将网络检测数据的多特征属性投影到低维进行聚类识别判定。对训练样本中的数据进行预处理并且归一化,获取最优投影方向,让样本数据投影到低维空间,对检测数据进行聚类判定。实验结果表明,该方法能很有效地提高入侵检测性能。Existing intrusion detection systems have many problems such as detection rate,false positive rate.An intrusion detection based on optimization projection pursuit algorithm is proposed.Aimed at the optimization problem of calculating the best projected vector of projection pursuit,a method is used based on QPSO.Optimization projection pursuit algorithm is im- plemented to project the data of feature from high dimension to low dimension, then the category of the network data is determined by the clustering algorithm.The algorithm includes data preconditioning, data normalized, the best projected vector calculation,data project to low dimension,and finally inspects data categorization.The experimental results show that the performance of the present method is feasible and effective.

关 键 词：投影寻踪 入侵检测 量子粒子群算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]