摘要
针对传统模型的网络流量异常检测正确率低,检测时间长的难题,设计了一种大数据环境下的网络流量异常检测模型。首先,对网络流量异常检测的研究现状进行分析,找到引起当前检测模型不足的原因;然后,采用HDOOP平台设计基于最小二乘支持向量机的网络流量异常检测模型;最后,在Maltab 2014平台下进行网络流量异常检测实验。实验结果表明,该模型可以准确对网络流量异常现象进行检测,获得了比其他模型更优的网络流量异常检测结果,具有更高的实际应用价值。
Since the traditional network traffic anomaly detection model has low detection accuracy and long detection time,a network traffic anomaly detection model in large data environment was designed.The research status of the network traffic anomaly detection is analyzed to find out the reason causing the poor performance of the current detection models.The HDOOP platform is used to design the network traffic anomaly detection model based on least square support vector machine.The network traffic anomaly detection experiment was carried out with Matlab 2014 platform.The experimental results show that the model can detect the network traffic anomaly phenomenon accurately,its network traffic anomaly detection result is better than that of other models,which has higher practical application value.
出处
《现代电子技术》
北大核心
2018年第3期84-87,共4页
Modern Electronics Technique
基金
贵州省科学技术联合基金项目(黔科合LH字[2016]7023号)~~
关键词
网络安全
流量异常检测
HDOOP平台
最小二乘支持向量机
大数据环境
检测模型
network security
traffic anomaly detection
HDOOP platform
least square support vector machine
large data environment
detection model
