摘要
与广泛使用的BP网络模型相比,径向基函数神经网络具有训练时间短且不易收敛到局部最小的优点.将3种径向基神经网络应用到入侵检测中,用于入侵模式识别的分类和预测,从而提高入侵检测系统的检测率并降低误报率.
In this paper, three radial basis function neural network models are presented for intrusion detection classification and prediction. Compared with the widely used back propagation neural network, they take shorter time in training and hardly converge to local minimization. Thus, they increase detection rate and reduce false positive rate of an intrusion detection system.
出处
《江西师范大学学报（自然科学版）》
CAS
北大核心
2007年第3期297-301,共5页
Journal of Jiangxi Normal University(Natural Science Edition)
基金
广东省自然科学基金(06021484
04107411)
广东省科技计划(2005B16001095
2005B10101077)资助项目
