Network traffic classification method based on deep forest

被引：2

作者：

Dai J. ^{[1
,2
]}

Wang T. ^{[2
,3
]}

Wang S. ^{[2
]}

机构：

[1] School of Information Science and Engineering, Jinling College, Nanjing University, Nanjing

[2] School of Electronic Science and Engineering, Nanjing University, Nanjing

[3] National Mobile Communications Research Laboratory, Southeast University, Nanjing

来源：

Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology | 2020年 / 42卷 / 04期

关键词：

Feature selection; Machine learning; Multi-grained cascade forest; Network traffic classification;

D O I：

10.11887/j.cn.202004006

中图分类号：

学科分类号：

摘要：

With the rapid development of network applications, the Internet traffic classification has a profound impact on the research fields of network resource allocation, traffic scheduling and network security. The traditional flow analysis method based on machine learning has strict requirements for the feature selection and distribution of network flows, which makes it difficult to accurately and stably classify the complex and changeable flow data in practical application. In order to solve the adverse impact of the complexity of sample features on the traffic classification, a new classification method based on deep forest, which utilizes the cascade forest of decision trees and the multi-grained scanning mechanisms aiming to improve classification performance in the case of limited scale of samples and features, was proposed. The machine learning algorithms including support vector machine, random forest and deep forest were trained and tested by using Moore, which is a flow data set in public domain. The experiment results show that the classification accuracy using deep forest model reaches 96.36%, which outperforms the other machine learning models. © 2020, NUDT Press. All right reserved.

引用

页码：30 / 34

页数：4

共 11 条

[1]

Marsch P, Bulakci O, Queseth O, Et al., 5G system design: architectural and functional considerations and long term research, (2018)

[2]

Dhote Y, Agrawal S, Deen A J., A survey on feature selection techniques for Internet traffic classification, Proceedings of International Conference on Computational Intelligence and Communication Networks (CICN), pp. 1375-1380, (2015)

[3]

Moore A W, Zuev D, Crogan M L., Discriminators for use in flow-based classification, (2005)

[4]

Aggarwal R, Singh N., A new hybrid approach for network traffic classification using SVM and Naïve Bayes algorithm, International Journal of Computer Science and Mobile Computing, 6, 6, pp. 168-174, (2017)

[5]

WANG Yong, ZHOU Huiyi, FENG Hao, Et al., Network traffic classification method basing on CNN, Journal on Communications, 39, 1, pp. 14-23, (2018)

[6]

Wang C, Xu T G, Qin X., Network traffic classification with improved random forest, Proceedings of 11th International Conference on Computational Intelligence and Security (CIS), pp. 78-81, (2015)

[7]

Fernandez-Delgado M, Cernadas E, Barro S, Et al., Do we need hundreds of classifiers to solve real world classification problems?, Journal of Machine Learning Research, 15, 1, pp. 3133-3181, (2014)

[8]

Zhou Z H, Feng J., Deep forest, National Science Review, 6, 1, pp. 74-86, (2018)

[9]

Zhou M, Zhang S Z, Qiu Y J, Et al., Entropy-based spammer detection, Proceedings of the 10th International Conference on Internet Multimedia Computing and Service, (2018)

[10]

Moore A W, Zuev D., Internet traffic classification using Bayesian analysis techniques, ACM SIGMETRICS Performance Evaluation Review, 33, 1, pp. 50-60, (2005)

← 1 2 →