一种基于AC-RBF神经网络的网络安全态势预测方法

发布时间：2018-04-18 11:42

本文选题：自适应聚类径向基函数(AC-RBF)神经网络 + 网络安全态势预测(NSSP)　；参考：《重庆邮电大学学报(自然科学版)》2014年05期

【摘要】：为了准确地把握网络安全发展态势,提出了一种基于自适应聚类径向基函数(adaptive clustering radical basis function,AC-RBF)神经网络的网络安全态势预测(network security situation prediction,NSSP)方法。该方法对网络安全态势样本自适应聚类,获得了神经网络隐层节点数,采用梯度下降法训练神经网络,寻找网络安全态势样本之间的非线性映射关系,利用该关系对未来时刻网络安全态势进行了预测。仿真实验表明,相对于K-均值RBF神经网络及支持向量机(support vector machine,SVM)预测模型,该方法在神经网络规模较小的情况下,不仅能够反映网络安全态势的总体趋势,而且还提高了预测精度,能够提供给网络安全管理员一个直观的网络安全态势图。
[Abstract]:In order to accurately grasp the development of network security, a network security situation prediction method based on adaptive clustering radical basis function AC-RBF neural network is proposed.Based on the adaptive clustering of network security situation samples, the number of hidden layer nodes of neural network is obtained, and the gradient descent method is used to train the neural network to find the nonlinear mapping relationship between the network security situation samples.The relationship is used to predict the situation of network security in the future.The simulation results show that compared with the K- mean RBF neural network and support vector machine SVM prediction model, this method can not only reflect the general trend of the network security situation, but also can reflect the overall trend of the network security situation in the case of the smaller scale of the neural network.Moreover, the prediction accuracy is improved, which can provide an intuitionistic network security situation map for the network security administrator.
【作者单位】：重庆邮电大学移动通信技术重庆市重点实验室;
【基金】：国家自然科学基金(61271260,61301122) 教育部科学研究重点项目(212145) 重庆市教委科学技术研究项目(KJ1400405)~~
【分类号】：TN915.08;TP18

【参考文献】