基于分辨矩阵和Apriori算法的关联规则挖掘研究与应用

Research and application of association rules mining algorithm based on discernibility matrix and apriori

为进一步提高关联规则挖掘的运行效率,在传统Apriori算法的基础上,提出了一种基于分辨矩阵和Apriori算法的关联规则挖掘算法。在数据预处理阶段,采用分辨矩阵对原始数据集进行属性约简,达到降维的目的;在关联规则挖掘阶段,采用位图来表示原始数据集,并在每一步运算过程中通过置信度阈值对特征集进行约简。应用实例和仿真实验表明,该方法在时间复杂度和空间复杂度都有了极大的改善,具有一定的应用价值。

An algorithm for mining association rules based on discernibility matrix and Apriori algorithm is proposed to further improve the efficiency of association rules mining.The discernibility matrix is applied to reduce the attribute of original data set.It represents the original data set as bitmap.It is to feature set reduction based on confidence threshold.The application examples and simulation results show that the method can improve the complexity of time and space.