摘要
传统网络异常识别方法速度慢、准确率低。为此,笔者提出基于相似度聚类的网络异常快速识别方法,经过详细分析相似度聚类算法,提出网络异常快速识别五步流程;并对网络安全权限机制识别和签名机制进行强化设计。实验对比表明,提出的识别方法能在短时间内识别网络异常,准确率高,对于保证网络安全有重要意义。
The traditional network anomaly identification method is slow and has low accuracy. This paper proposes a network anomaly fast recognition method based on similarity clustering. After analyzing the similarity clustering algorithm in detail, a five-step process for network anomaly fast identification is proposed. The network security authority mechanism identification and signature mechanism are enhanced. The experimental comparison shows that the identification method can identify network anomalies in a short time, and the accuracy is high, which is of great significance for ensuring network security.
作者
李伟民
Li Weimin(Department of Computer Science,Sias International University,Zhengzhou University,Xinzheng Henan 451100,China)
出处
《信息与电脑》
2019年第9期117-118,共2页
Information & Computer
基金
基于机器学习的电动汽车续航里程估计的研究(项目编号:182102210549)
关键词
相似度聚类
网络异常
异常识别
快速识别
识别方法
similarity clustering
network anomaly
anomaly identification
quick identification
recognition methods
