基于关系矩阵和频集树的关联规则算法及动态更新算法  

Association rule and dynamic updating algorithms based on relationship matrix and frequency set tree

作　　者：毕岩[1] 章韵[1] 徐小龙[1] 

机构地区：[1]南京邮电大学计算机学院,江苏南京210023

出　　处：《南京邮电大学学报（自然科学版）》2015年第4期96-103,共8页Journal of Nanjing University of Posts and Telecommunications：Natural Science Edition

基　　金：国家自然科学基金(61472192)资助项目

摘　　要：将关联规则中自连接问题转化为矩阵运算,能使数据挖掘算法更为高效。以基于关系矩阵的SLIG算法为原型,增添树形结构,将关联规则内在关系通过自定义的频集树表示,同时针对后续的事务数据库更新以及最小支持度参数变化问题,拓展出动态更新算法。理论分析及实验结果分析均表明R-SLI算法在保证挖掘准确率的条件下,与Apriori算法相比,大大减少了挖掘时间,提高了挖掘效率。In order to make the association rule algorithm more efficient, this paper studied the SLIG algorithm based on relationship matrix, converted the self-connection problem to the matrix operation, and added the tree structure to define a frequency set tree to express the internal relations of frequency sets. The dynamic updating algorithms is presented to solve the problems of transaction database updating and the minimum support index changing. The theoretical analysis and the experimental result show that the improved algorithm can reduce the mining time and improve the mining efficiency.

关 键 词：关联规则 矩阵运算 频繁项目集 动态更新 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]