基于支持矩阵的频繁集增量更新算法改进研究

Improvement Research about Frequent Itemsets Incremental Updating Algorithm Based on Support Matrix

针对FUP算法在频繁集增量更新时,剪枝效率低下以及候选集验证速度慢的缺陷,提出了基于支持矩阵的频繁集增量更新的高效挖掘算法—SMFUP算法.该算法不仅采用支持矩阵进行整体剪枝来提高剪枝效率,而且进一步结合频繁2项集矩阵加快候选频繁集的验证速度,从而使算法的增量更新效率大大提高.最后通过实验证明了算法改进的有效性.

The efficiency is greatly reduced when the algorithm named FUP is used in incremental updating frequent sets. Because it ＇s low speed of candidate frequent set validation and pruning. The algorithm named SMFUP based on support matrix is put forward,using for efficiently mining incremental updating frequent item sets. The efficiency of the algorithm is greatly increased,because it is not only used to support matrix to speed up pruning; but also used 2- frequent item sets and support matrix to speed up candidate frequent set validation. Finally,the experiments show that the algorithm has a better performance than the FUP algorithm.