首页 | 本学科首页   官方微博 | 高级检索  
     

基于K-均值聚类的改进非选择算法研究
引用本文:屈建平,罗文坚,王煦法.基于K-均值聚类的改进非选择算法研究[J].计算机工程与应用,2005,41(28):29-32.
作者姓名:屈建平  罗文坚  王煦法
作者单位:中国科学技术大学计算机科学技术系,合肥,230027
基金项目:国家自然科学基金(编号:60404004);国家博士后科学基金(编号:2003034433);安徽省教育厅重点项目(编号:2004kj360zd)资助
摘    要:文章提出了一种基于K-均值聚类的改进非选择算法,其核心是对检测器集进行K-均值聚类,将检测器集分为多个子类,根据子类中心和待检测数据的亲和度选择若干个合适的子类进行实际检测。文中对算法的检测过程进行了分析,并给出了该算法用于入侵检测时的测试实验结果。实验结果表明,文章算法在检测速度上有明显改善。

关 键 词:人工免疫系统  非选择  K  -均值聚类
文章编号:1002-8331-(2005)28-0029-04
收稿时间:2005-05
修稿时间:2005-05

Research in Improved Negative Selection Algorithm Based on K-means Clustering
Qu Jianping,Luo Wenjian,Wang Xufa.Research in Improved Negative Selection Algorithm Based on K-means Clustering[J].Computer Engineering and Applications,2005,41(28):29-32.
Authors:Qu Jianping  Luo Wenjian  Wang Xufa
Affiliation:Department of Computer Science and Technology,University of Science and Technology of China,Hefei 230027
Abstract:An improved Negative Selection Algorithm based on K-means Clustering(KC-NSA) is proposed in this paper.The core of the algorithm lies on clustering the set of detectors to k subsets of detectors,and several appropriate subsets of detectors being selected to detect the data practically according to the affinities between the centers of k subsets and the data to be detected.The detecting process of KC-NSA is analyzed theoretically,and this algorithm is applied to network intrusion detection experiments.The experimental results prove that KC-NSA can improve the detection speed very much.
Keywords:Artificial Immune System  negative selection  K-means Clustering
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号