Title :
P2P Traffic Classification Method Based on the PNN
Author :
Chang Lei ; Li Feng
Author_Institution :
Dept. of Comput. Sci. & Telecommun. Eng., Jiangsu Univ., Zhenjiang, China
Abstract :
A method of classifying the P2P traffic based on the Probabilistic Neural Network is proposed. Firstly, we utilize "WinPcap" to capture the network packets and then the core characteristics of the obtained data are analyzed with the help of the tool. Based on the above work, the P2P traffic classification system was realized. It makes full use of the advantage of the PNN which has a high convergence rate and strong classification ability. Meanwhile, the complexity of the system is reduced efficiently. The verification results show that the scheme is better than others in the flexibility, adaptability and accuracy.
Keywords :
neural nets; peer-to-peer computing; telecommunication traffic; P2P traffic classification method; PNN; convergence rate; core characteristics; network packets; probabilistic neural network; Accuracy; Artificial neural networks; Bayesian methods; Complexity theory; Feature extraction; Peer to peer computing; Probabilistic logic;
Conference_Titel :
Wireless Communications, Networking and Mobile Computing (WiCOM), 2011 7th International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6250-6
DOI :
10.1109/wicom.2011.6040526
