《计算机应用研究》|Application Research of Computers

一种基于抗原软子空间聚类的否定选择算法

Improved negative selection algorithm based on antigen soft subspace clustering

免费全文下载 (已被下载 次)  
获取PDF全文
作者 刘正军,高江锦,杨韬
机构 1.四川大学 计算机学院,成都 610065;2.西华师范大学 教育信息技术中心,四川 南充 637002
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2018)03-0680-05
DOI 10.3969/j.issn.1001-3695.2018.03.009
摘要 否定选择算法(NSA)是免疫检测器生成的重要算法。传统否定选择算法在亲和力计算过程中未考虑不同种类抗原关键特征与冗余特征之间的差异性,存在算法检测性能较低的问题。对此,提出了一种基于抗原软子空间聚类的否定选择算法(ASSC-NSA)。该算法首先利用抗原软子空间聚类计算出不同种类抗原的各个关键特征及其权值,然后通过这些关键特征引导检测器生成以有效地减少冗余特征的影响,从而提高算法检测性能。实验结果表明,在BCW与KDDCup数据集上,相对于经典的否定选择算法,ASSC-NSA能在误报率无明显变化的情况下显著地提高检测率。
关键词 否定选择算法;软子空间聚类;异常检测
基金项目 国家自然科学基金资助项目(61572334)
国家重点研发计划资助项目(2016YFB0800604)
南充市应用技术研究与开发资金资助项目(16YFZJ0011)
本文URL http://www.arocmag.com/article/01-2018-03-009.html
英文标题 Improved negative selection algorithm based on antigen soft subspace clustering
作者英文名 Liu Zhengjun, Gao Jiangjin, Yang Tao
机构英文名 1.CollegeofComputerScience,SichuanUniversity,Chengdu610065,China;2.EducationInformationTechnologyCenter,ChinaWestNormalUniversity,NanchongSichuan637002,China
英文摘要 Negative selection algorithm(NSA) is an important method of detector-generation.Traditional NSAs ignored the difference of key characteristic and redundant characteristic of different kinds of antigens in the process of affinity-computing, which led to the poor performance. To solve this problem, this paper proposed an improved negative selection algorithm based on antigen soft subspace clustering(ASSC-NSA). First, by utilizing the antigen soft subspace clustering algorithm, ASSC-NSA found out all key characteristics and their weights of different kinds of antigens. Then, using the key characteristics to guide the detectors generation, thus it could eliminate the adverse influence of redundant characteristics and improve the detection rate. Compared with classical NSAs, the experimental result on BCW and KDDCup data set shows that ASSC-NSA improves the detection rate significantly with the similar false alarm rate.
英文关键词 negative selection algorithm; soft subspace clustering; anomaly detection
参考文献 查看稿件参考文献
  [1] Aragón V S, Esquivel S C, Coello C A C. An immune algorithm with power redistribution for solving economic dispatch problems[J] . Information Sciences, 2015, 295(C):609-632.
[2] Li Dong, Liu Shulin, Zhang Hongli. Negative selection algorithm with constant detectors for anomaly detection[J] . Applied Soft Computing, 2015, 36:618-632.
[3] Gong Tao. High-precision immune computation for secure face recognition[J] . International Journal of Security and Its Applications, 2012, 6(2):293-297.
[4] Hart E, Timmis J. Application areas of AIS:the past, the present and the future[J] . Applied Soft Computing, 2008, 8(1):191-201.
[5] Silva G C, Palhares R M, Caminhas W M. Immune inspired fault detection and diagnosis:a fuzzy-based approach of the negative selection algorithm and participatory clustering[J] . Expert Systems with Applications, 2012, 39(16):12474-12486.
[6] 李涛. 基于免疫的计算机病毒动态检测模型[J] . 中国科学, F辑:信息科学, 2009, 39(4):422-430.
[7] Fakhari S N S, Ziabari M T. A self adaptive algorithm for classification based on negative selection technique[J] . Artificial Intelligence and Application, 2014, 1(2).
[8] Forrest S, Perelson A S, Allen L, et al. Self-nonself discrimination in a computer[M] . [S. l. ] :IEEE Computer Society, 1994:202-212.
[9] Gonzalez F A, Dasgupta D, Nino L F. A randomized real-valued ne-gative selection algorithm[C] //Proc of the 2nd International Confe-rence on Artificial Immune Systems. 2003:261-272.
[10] Ji Zhou, Dasgupta D. V-detector:an efficient negative selection algorithm with probably adequate detector coverage[J] . Information Sciences, 2009, 19(9):1390-1406.
[11] Gong Maoguo, Zhang Jian, Ma Jingjing, et al. An effcient negative selection algorithm with further training for anomaly detection[J] . Knowledge-Based Systems, 2012, 30:185-191.
[12] 陈文, 李涛, 刘晓洁, 等. 一种基于自体集层次聚类的否定选择算法[J] . 中国科学, F辑:信息科学, 2013, 43(5):611-625.
[13] Zeng Jinquan, Liu Xiaojie, Li Tao, et al. A self-adaptive negative selection algorithm used for anomaly detection[J] . Progress in Na-tural Science, 2009, 19(2):261-266.
[14] Li Dong, Liu Shulin, Zhang Hongli. A negative selection algorithm with online adaptive learning under small samples for anomaly detection[J] . Neurocomputing, 2015, 149(C):515-525.
[15] Beyer K, Goldstein J, Ramakrishnan R, et al. When is “nearest neighbor” meaningful[C] //Proc of International Conference on Database Theory. Berlin:Springer, 1999:217-235.
[16] Zhu Lin, Cao Longbing, Yang Jie, et al. Evolving soft subspace clustering[J] . Applied Soft Computing, 2014, 14(1):210-228.
[17] UCI数据集[EB/OL] . http://archive. ics. uci. edu/ml/datasets. html.
收稿日期 2016/11/18
修回日期 2017/1/4
页码 680-684
中图分类号 TP309.5;TP301.6
文献标志码 A