高平均模糊效用项集挖掘算法  

High average fuzzy utility itemset mining algorithm

作　　者：王斌 李晓华 周伟 胡克勇 WANG Bin;LI Xiao-hua+;ZHOU Wei;HU Ke-yong(School of Information and Control Engineering,Qingdao University of Technology,Qingdao 266520,China)

机构地区：[1]青岛理工大学信息与控制工程学院,山东青岛266520

出　　处：《计算机工程与设计》2024年第5期1398-1405,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(61902205)。

摘　　要：为解决高模糊效用项集挖掘算法中存在的挖掘结果中含有大量无效的长项集以及搜索空间过大的问题,提出一种高平均模糊效用项集挖掘算法HAFUIM(high average fuzzy utility itemset mining algorithm)。定义平均模糊效用,考虑项集的模糊效用和长度的关系,解决倾向于挖掘长项集的问题;提出平均模糊上限模型和4种剪枝性质,缩小搜索空间;设计平均模糊列表结构用于存储必要的效用信息,减少数据库扫描次数。通过仿真实验验证了所提算法的可行性和高效性。To solve the problems of a large number of invalid long itemset in mining results and excessive search space in the high fuzzy utility itemset mining algorithm,the HAFUIM(high average fuzzy utility itemset mining algorithm)was proposed.The average fuzzy utility was defined,the relationship between the fuzzy utility and the length of the itemset was considered,and the problem of tending to mine the long itemset was solved.An average fuzzy upper bound model and four pruning properties were proposed,which effectively narrowed the search space.The average fuzzy list structure was designed to store the necessary utility information and reduce the number of database scans.The results of simulation experiments show that the proposed algorithm is feasible and efficient.

关 键 词：数据挖掘 项集挖掘 高模糊效用 平均模糊效用 平均模糊上限模型 平均模糊列表 剪枝策略 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]