计算机与数字工程2019，Vol.47Issue(10)：2387-2391,5.DOI:10.3969/j.issn.1672-9722.2019.10.002
一种基于机器学习的P2P网络流量识别算法研究∗
Study on P2P Network Flow Recognition Algorithm Based on Machine Learning
摘要
Abstract
In order to improve the accuracy of P2P network traffic recognition,this paper uses the dragonfly algorithm to opti?mize the weight and threshold of Elman neural network. A P2P network traffic recognition model based on DA-Elman machine learn?ing is proposed. The five characteristic attributes of the TCP traffic ratio,the number of connections to different IP numbers,the av?erage packet length,the uplink traffic ratio,and the total number of packets are used as inputs to the DA-Elman model,and the network traffic type is used as the DA-Elman output. Compared with PSO-Elman,GA-Elman,and Elman,the research results show that DA-Elman can effectively improve the accuracy of P2P network traffic recognition,with an accuracy rate of 98.4252%, providing new methods and approaches for P2P network traffic identification.关键词
机器学习/Elman神经网络/粒子群算法/遗传算法/网络流量识别Key words
machine learning/Elman neural network/particle swarm optimization algorithm/genetic algorithm/network traffic recognition分类
信息技术与安全科学引用本文复制引用
袁华兵..一种基于机器学习的P2P网络流量识别算法研究∗[J].计算机与数字工程,2019,47(10):2387-2391,5.基金项目
国家自然科学基金项目(编号:61634004)资助. （编号:61634004）
