| 基于互信息与随机森林的P2P流量识别 |
| |
| 引用本文： | 张颖超,陈康超.基于互信息与随机森林的P2P流量识别[J].淮海工学院学报,2012(3):16-19. |
| |
| 作者姓名： | 张颖超 陈康超 |
| |
| 作者单位： | 南京信息工程大学信息与控制学院,江苏南京210044 |
| |
| 摘 要： | 针对当前基于流特征的流量识别方法准确率较低的问题,提出一种基于互信息的P2P流量特征选择方法和基于该方法的随机森林技术在流量识别中的应用模型,将网络流数据流分为P2P流和非P2P流。实验证明,该方法具有较高的识别率,说明了采用随机森林技术进行P2P流量识别的有效性。
|
| 关 键 词： | 流量识别 互信息 随机森林 P2P |
P2P Traffic Identification Based on Mutual Information and Random Forests |
| |
| ZHANG Ying-chao,CHEN Kang-chao.P2P Traffic Identification Based on Mutual Information and Random Forests[J].Journal of Huaihai Institute of Technology:Natural Sciences Edition,2012(3):16-19. |
| |
| Authors: | ZHANG Ying-chao CHEN Kang-chao |
| |
| Affiliation: | (School of Information and Control,Nanjing University of Information Science ＆ Technology, Nanjing 210044, China) |
| |
| Abstract: | In respect to the low accuracy in current traffic identification based on the characteris- tics of traffic flow, we put forwards a P2P traffic selection method based on mutual information and an applicable traffic-identifying model of random forests （RF） algorithm, through which we classified the data packages on the Internet into the P2P class and the non-P2P class. Experiment results show that the method technology in identifying P2P has a high identification rate, which shows the effectiveness of RF traffic. |
| |
| Keywords: | traffic identification mutual information random forests P2P |
| 本文献已被 维普 等数据库收录！ |
