| 摘要: |
| 态势要素获取作为整个网络安全态势感知的基础，其质量的好坏将直接影响态势感知系统的性能。针对态势要素不易获取问题，提出了一种基于增强型概率神经网络的层次化框架态势要素获取方法。在该层次化获取框架中，利用主成分分析(PCA)对训练样本属性进行约简并对特殊属性编码融合处理，将其结果用于优化概率神经网络(PNN)结构，降低系统复杂度。以PNN作为基分类器，基分类器通过反复迭代、权重更替，然后加权融合处理形成最终的强多分类器。实验结果表明，该方案是有效的态势要素获取方法并且精确度达到95.53%，明显优于同类算法，有较好的泛化能力。 |
| 关键词: 网络安全 态势要素 数据处理 协同增强 概率神经网络 |
| DOI： |
|
| 基金项目:国家自然科学基金资助项目(61271260)；重庆市科委自然科学基金资助项目(cstc2015jcyjA40050)；重庆市教委科学技术研究项目(KJ120530) |
|
| Security situation element acquisition based on enhanced probabilistic neural network |
| LI Fangwei,WANG Sen,ZHU Jiang,ZHANG Haibo |
| () |
| Abstract: |
| Situation elements extraction is the basis of the whole network security situation awareness and its quality will directly affect the performance of the situation awareness system. To solve the problem that the situation element is difficult to extract,a method is proposed to extract the hierarchical frame situation elements based on the enhanced probabilistic neural network(PNN).In the hierarchical access frame,the principal component analysis(PCA) is used to reduct the training sample attribute and process the special attribute encoding fusion.The result is used to optimize the structure of PNN and reduce the system complexity.PNN is taken as the base classifier to form the final strong classifier by repeated iteration,weight replacement and weighted fusion.The experimental results show that the scheme is an effective method to obtain the situation factors and its accuracy is 95.53%,significantly better than other similar algorithms. |
| Key words: network security situational factors data handling synergistic enhancement probabilistic neural network(PNN) |
《电讯技术》编辑部 