详细信息
基于BPSO-SVM的网络入侵特征选择和检测 ( EI收录)
Selection and Detection of Network Intrusion Feature Based on BPSO-SVM
文献类型:期刊文献
中文题名:基于BPSO-SVM的网络入侵特征选择和检测
英文题名:Selection and Detection of Network Intrusion Feature Based on BPSO-SVM
作者:高海华[1];杨辉华[1];王行愚[1]
机构:[1]华东理工大学信息科学与工程学院,上海200237
年份:2006
卷号:32
期号:8
起止页码:37
中文期刊名:计算机工程
外文期刊名:Computer Engineering
收录:CSTPCD;;EI(收录号:2006229912533);Scopus;北大核心:【北大核心2004】;CSCD:【CSCD2011_2012】;
基金:国家自然科学基金资助项目(69974014);国家重点基础研究发展规划项目(2002CB312200);教育部高校博士点基金资助项目(20040251010)
语种:中文
中文关键词:二进制粒子群优化;支持向量机;异常检测;特征选择
外文关键词:Binary particle swarm optimization(BPSO); Support vector machines(SVM); Anomaly detection, Feature selection
摘要:采用改进的二进制粒子群优化进行入侵特征子集选择,粒子群中每个粒子代表一个选择的特征子集,结合支持向量机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粒子的适应度,通过粒子群优化实现最优入侵特征选择。改进的BPSO方法中通过引入粒子群依概率整体变异来避免陷入局部最优,同时采用粒子禁忌搜索列表来扩大粒子搜索范围和避免重复计算;SVM中采用基于粒度的网格搜索来获得最优核参数。最后用KDD 99标准数据集进行实验研究,结果表明该方法能获得满意的检测效果。
In the proposed algorithm, every particle in the swarm stands for a selected subset of features, The fitness of particle is defined as the correct classification percentage by SVM using a training set whose patterns are represented using only the selected subset of features. Thus through particle swarm optimization to achieve intrusion feature selection and classification. A probabilistic mutation of BPSO is adopted to avoid local optimal and a tabu search table is used to enlarge particle swarm's search space and avoid repeated compntation. The results of experiment demonstrate that applying a hybrid of BPSO-SVM in intrusion detection System can be an effective way for feature selection and detecting intrusions via using the data sets of KDD cup 99.
参考文献:
正在载入数据...
