基于区间概念格的频繁闭项集挖掘算法  

Mining Algorithm for Frequent Closed Itemsets Based on Interval Concept Lattice

作　　者：郑文彬 何秋红 ZHENG Wen-bin;HE Qiu-hong(College of Computer Science,Minnan Normal University,Zhangzhou 363000,China;Key Laboratory of Granular Computing and Its Application in Fujian,Minnan Normal University,Zhangzhou 363000,China)

机构地区：[1]闽南师范大学计算机学院,福建漳州363000 [2]闽南师范大学福建省粒计算及其应用重点实验室,福建漳州363000

出　　处：《内蒙古民族大学学报（自然科学版）》2018年第6期475-479,共5页Journal of Inner Mongolia Minzu University：Natural Sciences

基　　金：福建省教育厅中青年教师教育科研项目(JB13376)

摘　　要：传统的频繁闭项集挖掘算法计算过程过于繁琐复杂,耗费时间较长,计算结果不准确.为了解决这一问题,基于区间概念格研究了一种新的频繁闭项集挖掘算法,给出了计算公式,对算法的操作流程进行设计,共分为设计预定代码、小概念层次筛选操作定位、分析和处理子集数据以及建立数据关联.为检验设计算法的可行性,与传统频繁闭项集挖掘算法进行了对比,设计了对比实验,由实验结果可知,相较于传统算法,基于区间概念格的频繁闭项集挖掘算法计算过程更加简单,耗时更短,准确性更高,具有广阔的市场发展空间.The traditional frequent closed itemsets mining algorithm is too cumbersome, complex to process, takes a long time and the result is not always accurate. In order to solve this problem, a new algorithm of frequent closed term set mining was studied based on interval concept lattice. The calculation formula is presented. The operation flow of the designed algorithm is divided into design code, small concept level screening operation, analysis and processing of subset data and data association. In order to test the feasibility of this algorithm, compared with the traditional frequent closed itemset mining algorithm, a contrast experiment was designed. Compared with the traditional algorithm, the computation process of frequent closed term mining algorithm based on interval concept lat- tice was found to be simpler, shorter and more accurate, having a broad market development exhibition space.

关 键 词：区间概念 概念格 频繁闭项 挖掘算法 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]