摘要
文中研究了构建IDS时重要输入特征的鉴别问题,在介绍一种基于效能等级的重要特征排序算法(PFRM)基础上,提出一种基于遗传算法的最小特征子集选取算法(FSSGA)。分析了两种算法的特点,并采用相同数据集对其进行实验比较。实验结果表明,与PFRM相比,FSSGA算法在特征减少和攻击检测方面具有更好的性能。
This paper addresses the issue of identifying important input features in building an intrusion detection system (IDS). An algorithm named PFRM was first introduced and then a new algorithm (FSSGA) based on GA is proposed. The characteristics of both algorithms were analyzed. The experimental result using the same dataset shows that the performance of FSSGA is much better than PFRM.
出处
《计算机应用》
CSCD
北大核心
2003年第7期13-14,17,共3页
journal of Computer Applications