摘要
提出了基于BP-HMM模型的网络入侵检测方法,给出了该模型的训练和识别方法。由于纯粹的HMM建立的分类器不能兼顾每个模型对其对应目标有很强的识别能力和模型之间差异性的最大化,因此将BP神经网络集成到HMM框架中,用BP网络为HMM提供状态概率输出。通过BP网络的粗分类,克服了HMM的缺陷,提高了系统的分类识别能力。
A network intrusion detection framework and its associated algorithm based on BP-HMM are put forward, the training and identification methods of the algorithm are given. A sheer classifier based on HMM can't give attention to both the strong recognition ability tbr the corresponding objects and the maximizing difference lain in different models, so the BP neural network is used to provide state probability output for HMM in the HMM framework. With the rough sort of BP, the limitation of HMM is overcome; the ability of classification and identification is enhanced.
出处
《计算机工程》
CAS
CSCD
北大核心
2007年第10期131-133,163,共4页
Computer Engineering
关键词
BP-HMM
向量量化
前(后)向评估算法
任意路径方法
Back propagation-hidden Markov model
Vector Quantification
Forward(backward) evaluation algorithm
Any-path method