J4 ›› 2015, Vol. 42 ›› Issue (4): 107-113.doi: 10.3969/j.issn.1001-2400.2015.04.018

• 研究论文 • 上一篇    下一篇

利用E-IGA-RBF的网络信息内容安全事件态势预测

葛琳;季新生;江涛   

  1. (国家数字交换系统工程技术研究中心,河南 郑州  450002)
  • 收稿日期:2014-03-12 出版日期:2015-08-20 发布日期:2015-10-12
  • 通讯作者: 葛琳
  • 作者简介:葛琳(1978-),女,国家数字交换系统工程技术研究中心博士研究生,E-mail: lingesnow@126.com.
  • 基金资助:

    国家高技术研究发展计划(863)资助项目(2011AA010605);国家科技重大专项资助项目(2012ZX03006002-010)

Situation prediction of network information content  security incidents using E-IGA-RBF

GE Lin;JI Xinsheng;JIANG Tao   

  1. (National Digital Switching System Engineering and Technological Research Center, Zhengzhou  450002, China)
  • Received:2014-03-12 Online:2015-08-20 Published:2015-10-12
  • Contact: GE Lin

摘要:

针对径向基函数神经网络的优化问题,提出了一种基于精英选择模型的免疫遗传算法,对径向基函数神经网络的结构和参数进行优化.模型采用精英选择策略,确保优良基因得以保留进入下一代.同时,通过退火因子的扰动,在一定程度上增加了变异的多样性,提高了整个算法的收敛速度和局部搜索能力.实验结果表明,利用该算法进行信息内容安全事件的态势预测,具有有效性和可靠性,较现有算法具有更加优良的性能.

关键词: 信息内容安全事件, 态势预测, 径向基函数神经网络, 免疫遗传算法, 精英选择模型, 模拟退火算法

Abstract:

In order to resolve the problem of optimizing RBF, an elitist model-immune genetic algorithm is put forward to optimize the structure and parameters of the RBF neural network. The model uses elite selection strategy and adds the factor of simulated annealing. It ensures good genes to be retained into the next generation. At the same time, it increases the diversity of variation to a certain extent through the disturbance of the annealing factor. And the model improves the convergence rate and local search capacity of the whole algorithm. Experimental results are used to demonstrate the effectiveness and reliability of the algorithm when predicting the situation of network information content security incidents.

Key words: information content security incidents, situation prediction, radial-basis-function(RBF) neural network, immune genetic algorithm(IGA), elitist selection model, simulated annealing algorithm

中图分类号: 

  • TP391