论文部分内容阅读
光纤通信网络流量类型众多,分类结果有助于网络异常事件的检测,为了获得高精度的网络流量分类结果,提出一种小波消噪和蜂群最小二乘支持向量机的光纤通信网络流量分类方法。首先对光纤通信网络流量的原始数据进行小波消噪,得到无噪的新训练样本集,然后采用最小二乘支持向量机对新训练样本集进行学习,并利用蜂群算法对最小二乘支持向量机参数进行选择,建立光纤通信网络流量的分类器。具体光纤通信网络流量分类实验结果表明,本文方法较大程度上减少光纤通信网络分类的错误,其分类正确率要优于其他的光纤通信网络流量分类方法。
There are many types of traffic in optical fiber communication networks, and the classification results are helpful to the detection of anomalous events in the network. In order to obtain high-precision network traffic classification results, a method of traffic classification based on wavelet denoising and bee-named least squares support vector machines . First of all, the original data of optical fiber communication network traffic is denoised by wavelet to get a new noise-free training sample set, then the least squares support vector machine is used to learn the new training sample set, and the bee colony algorithm is used to calculate the least squares support vector Machine parameter selection, the establishment of optical fiber communication network traffic classifier. Experimental results show that the method proposed in this paper can reduce the classification errors of optical fiber communication network to a great extent, and the classification accuracy rate is superior to other optical fiber communication network traffic classification methods.