Method of Choosing Optimal Features Used to Intrusion Detection System in Ad Hoc Network based on Immunity Algorithm
In order to improve the detection rate of new intruders in Ad Hoc Network > a new method of intrusion detection system (IDS) based on immune algorithm and back propagation neural network (BPNN) is developed in the paper, on the base of analysis on the network data. In this method, immune algorithm (IA) is used to preprocess the network data, extract key features and reduce dimensions of network data set by feature analysis, then BPNN is adopted to classify the data (program) and recognize intruders. Experimental results show that the method is feasible and efficient, and the detection right rate of intruders in Ad Hoc Network was above 97％.
Intrusion Detection System (IDS) Feature selection immunity algorithm (IA) back propagation neural network(BPNN)
SHI Guang GAO Li YU Guixian YU Shengqin YU Shengchen ZHANG Linang SHAO Tiejun
Computer Science Department of North China University of Science & Technology,Beijing,101601,China Beijing Zhao Fang Investment Trust Co.,Ltd.Beijing 100028,China Gu Yuan Earthquake Platform of Earthquake Bureau of Ning Xia Province.Gu Yuan 756000,China Beijing Information Science & Technology University,Beijing,100026,China
国际会议
太原
英文
180-183
2011-02-26（万方平台首次上网日期，不代表论文的发表时间）