Research on a Network Traffic Classification Algorithm Based on GRU and CNN
In many cases,the accuracy of the hybrid algorithm of Recurrent Neural Network(RNN)combined with Convolutional Neural Network(CNN)is better than that of a single deep learning algorithm in traffic classification.Based on the original traffic data of CICIDS2017,this paper preprocesses the data first,and uses the CNN model to learn the spatial characteristics of the data flow.Then the CNN output of all packets in the stream is used as the input of the Gated Recurrent Unit(GRU)to learn the time characteristics of the network stream.Finally,the classification result is obtained through the Softmax classifier.After testing,the dual-network combination algorithm proposed in this paper can achieve high accuracy of data traffic classification with fewer steps in this data set.
NETL
NSTL
万方数据
