摘要
模糊网络中入侵特征较为多样化,无法通过固定的阈值进行合理判断。为了解决模糊网络入侵检测方法存在检测率低、误报率高和检测速度慢等问题,提出一种基于量子神经网络的层序列特征自动提取方法。在该算法中,通过对模糊网络进行层次划分,运用量子BP神经网络模型以量子形式形态的空间思维结构来提取信息,通过量子空间结构中量子门的移位与旋转变化对神经网络量子形态相位进行操作,完成多层序列特征自动提取。仿真实验表明,该算法具有较好高的检测率和检测效率,并且误报率较低。
The intrusion features in fuzzy network are diverse,so the intrusion features can not be reasonably judged withthe fixed threshold.A kind of layer sequence characteristics′automatic extraction method based on quantum neural network isput forward to solve the problems of low detection rate and high false rate and slow detection speed in the fuzzy network intru-sion detection methods.In this algorithm,the quantum BP neural network model is used to extract information in the spacethinking structure of quantum form by means of hierarchical division of fuzzy network,and the phase in quantum form of neuralnetwork is operated by means of quantum gate displacement and rotation changes in quantum space structure to complete auto-matic extraction of multilayered sequence features.The experimental simulation result show that the algorithm has better detec-tion rate,detection efficiency and low false alarm rate.
作者
朱闻亚
ZHU Wenya(School of Economics and Management,Wuhan University,Wuhan 430000,China;School of Mechanical and Electronic Information,Yiwu Industrial and Commercial College,Yiwu 322000,China)
出处
《现代电子技术》
北大核心
2017年第10期114-117,共4页
Modern Electronics Technique
基金
浙江省2015年度高等教育教学改革项目(JG2015343)
关键词
模糊网络
入侵检测
分层操作
特征自动提取
fuzzy network
intrusion detection
hierarchical operation
characteristic automatic extraction
