摘要
为了提高关联规则挖掘算法处理数据库的效率,在研究AprioriTid算法的基础上提出一种高效的关联规则挖掘算法AprioriTidD,在计算数据库中的频繁项集时依靠有效的裁剪减少无效项集的产生,并且可减少产生候选项集,从而有效地提高算法的效率.选取程序模拟超市购物产生的3个试验数据集,应用AprioriTidD算法对该数据集进行了关联规则挖掘,结果表明,运用AprioriTidD算法可以有效缩小Tid表,减少相关的计算量,提高数据挖掘的效率.
To improve the efficiency of the algorithm processing the database, a AprioriTidD algorithm was presented, which is a high - efficient algorithm of mining association rule based on the algorithm of AprioriTid, it reduced the table Tid by pruned some transaction and item to prevent the insignifieancy item generated. Three test data sets were chosen which were produced by the program to simulate data of supermarket, applying the data set on the AprioriTidD algorithm of mining association rules. Results show that the AprioriTidD is more efficient than the ApfiofiTid.
出处
《湖南科技大学学报（自然科学版）》
CAS
北大核心
2011年第4期60-64,共5页
Journal of Hunan University of Science And Technology：Natural Science Edition
基金
国家自然科学基金资助项目(61003151)
