摘要
提出了一种划分属性离散区间的新方法.针对这种划分,提出一种约简和去噪的方法.随后,建立了粗糙集和LVQ神经网络的联合模式识别系统.最后,比较了用该系统和仅用神经网络进行识别的效果,证明了该方法的有效性.
A new method of mapping the value of attribute into the discrete value with a fine value partition granularity is proposed firstly. Based on this method is a reduction searching algorithm and noise-reduction. Then a system of pattern recognition based on rough set and neural network is established. Finally, the effectiveness is verified those from neural networks. by comparing results obtained from the system with
出处
《海军工程大学学报》
CAS
北大核心
2006年第2期87-90,共4页
Journal of Naval University of Engineering
关键词
神经网络
粗糙集
信息熵
模式识别
neural network
rough set
entropy
pattern recognition
