摘要
针对单独使用遗传算法不能在短时间内寻找到接近最优解的问题,采用改进的遗传算法来优化神经网络权值,能很好地与BP算法结合。用Matlab进行仿真实验,实验结果表明:改进的BP神经网络在入侵检测中有着巨大的应用潜力,识别率普遍达95%以上。
In view of the problem that the genetic algorithm can not be used alone in a short time to find a near optimal solution, this paper employs an improved genetic algorithm to optimize the neural network weights, producing a good combination with the BP algorithm. Matlab is used to conduct simulation experiments and the results show that the improved BP neural network has great application potential in detecting invasion with an identification rate of above 95%.
出处
《重庆理工大学学报（自然科学）》
CAS
2010年第2期83-86,共4页
Journal of Chongqing University of Technology：Natural Science
关键词
入侵检测系统
GABP神经网络
改进遗传算法
intrusion detection system
GABP neural network
improved genetic algorithm
