【作者】 高海华； 王行愚； 杨辉华；

【Author】 GAO Haihua1,WANG Xingyu1 ,YANG Huihua1,2(1: College of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237;2: Department of Computer,Guilin University of Electronic Technology,Guilin 541004)

【机构】 华东理工大学信息科学与工程学院；

【摘要】 群智能中的每个个体产生一个特征子集,结合支持向量机(SVM)使用该特征子集所对应的数据集进行分类,正确分类结果作为该个体的适应度,通过群智能的优化搜索实现最优入侵特征选择。其中群智能主要采用粒子群算法和蚁群算法,支持向量机采用基于粒度的网格搜索策略获得最优参数。最后以KDD99数据集进行验证,结果表明基于群智能的网络入侵特征选择方法能有效降低虚警率,提高检测精度。更多还原

【Abstract】 Every individual in the swarm of Swarm Intelligence (SI) produces a feature subset candidate, the fitness of each individual is defined as the correct classification percentage by SVM using a training set whose patterns are represented using only the selected subset of features. Through SI optimization, intrusion feature selection and classification are achieved. Particle Swarm optimization (PSO) and Ant Colony Optimization (ACO) algorithm are adopted as the implementation of SI. The results of experiment demonstrate that applying SI-SVM in Intrusion Detection can be an effective way for feature selection and detection via using the KDD cup 99 dataset.更多还原