摘要
针对经典的Apriori算法对多值属性数据进行关联规则挖掘时效率低下的问题,提出了改进算法。算法通过对属性值进行二进制编码、增加行和属性值计数器等方式,对数据进行了压缩,并针对压缩的存储矩阵使用了新的频繁集生成算法。实验结果表明,改进算法相比经典Apriori算法执行效率更高,所需资源更少。
Aiming at the problem of low efficiency of mining quantitative association rules with the classical apriori algorithm, an improved algorithm was proposed. The improved algorithm compressed data by using binary encoding of attribute values, adding rows and attribute value counters. A new algorithm for generating frequent itemsets was used for the compressed matrix. Experimental results showed that the improved algorithm was more efficient and less spaced than the classical apriori algorithm.
出处
《新乡学院学报》
2015年第12期33-36,共4页
Journal of Xinxiang University
基金
安徽省高校省级自然科学研究重点项目(KJ2014A038)
关键词
数据挖掘
关联规则
频繁集
多值属性
data mining
quantitative association rules
frequent itemsets