RBF神经网络在关联数据一致性挖掘中的应用

Application of RBF Neural Network in Mining the Consistency of Associated Data

为提升对数据规则的挖掘效果,本文将神经网络应用于关联数据一致性规则的挖掘。通过径向基函数神经网络预测网络关联数据的规则属性,并利用粗糙集对预测结果实施离散化处理,生成粗糙规则。实验结果表明:在不同数据属性值以及不同的元素数量下,本文的方法挖掘网络关联数据的一致性规则所用的时间较少。

In order to improve the mining effect of data rules,this paper applies neural network to mining consistency rules of associated data.Radial basis function neural network is used to predict the rule attributes of network associated data,and rough set is used to discretize the prediction results to generate rough rules.The experimental results show that under different data attribute values and different element numbers,the method takes less time to mine the consistency rules of network associated data.