Method Used to Detect New Intruders in Wireless Network-Genetic Algorithms and Back Propagation Neural Network

摘要：

In order to improve the detection rate of new intruders in wireless network intrusion detection system (IDS), and to solve the problem that the back propagate neural network (BP neural network) is invalid when these initial weight and threshold values of BP neural network are chosen impertinently (Objective), Genetic Algorithms (GA)s characteristic of getting global optimization value is combined with BPs characteristic of getting precise local value with gradient method. After getting an approximation of global optimal value of weight and threshold values of BP neural network by GA, the approximation is used as first parameter of BP neural network, to train (educate) the BP neural network again (in other words, learning). The educated BP neural network was used to recognize new intruders in wireless network. Experiment results shown that this method was useful and applicable, and the detection right rate of new intruders in Wireless Network was above 98％.

关键词： Detecting new intruders Wireless Networks genetic algorithms back propagation neural network global optimization value

作者: CAO De-sheng FAN Yu-tao

作者单位: Department of Computer,North China Institute of Science and Technology,Yanjiao Beijing-East,101601,China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 217-220

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）