摘要
针对传统基于机器学习的流量分类方法中特征选取环节的好坏会直接影响结果精度的问题,提出一种基于卷积神经网络的流量分类算法。首先,通过对数据进行归一化处理后映射成灰度图片作为卷积神经网络的输入数据,然后,基于LeNet-5深度卷积神经网络设计适于流量分类应用的卷积层特征面及全连接层的参数,构造能够实现流量的自主特征学习的最优分类模型,从而实现网络流量的分类。所提方法可以在避免复杂显式特征提取的同时达到提高分类精度的效果。通过公开数据集和实际数据集的系列仿真实验测试结果表明,与传统分类方法相比所提算法基于改进的CNN流量分类方法不仅提高了流量分类的精度,而且减少了分类所用的时间。
Since the feature selection process will directly affect the accuracy of the traffic classification based on the tra-ditional machine learning method, a traffic classification algorithm based on convolution neural network was tailored. First, the min-max normalization method was utilized to process the traffic data and map them into gray images, which would be used as the input data of convolution neural network to realize the independent feature learning. Then, an im-proved structure of the classical convolution neural network was proposed, and the parameters of the feature map and the full connection layer were designed to select the optimal classification model to realize the traffic classification. The tai-lored method can improve the classification accuracy without the complex operation of the network traffic. A series of simulation test results with the public data sets and real data sets show that compared with the traditional classification methods, the tailored convolution neural network traffic classification method can improve the accuracy and reduce the time of classification.
出处
《通信学报》
EI
CSCD
北大核心
2018年第1期14-23,共10页
Journal on Communications
基金
国家自然科学基金资助项目(No.61662018
No.61661015)
中国博士后科学基金资助项目(No.2016M602922XB)
广西自然科学基金资助项目(No.2016GXNSFAA380153)
桂林电子科技大学研究生教育创新计划基金资助项目(No.2018YJCX53
No.2018YJCX20)
桂林理工大学科研启动基金资助项目(No.GUTQDJJ20172000019)~~
关键词
流量分类
卷积神经网络
归一化
特征选择
network traffic classification, convolutional neural network, normalized, feature selection