NECLATCLOSED: A vertical algorithm for mining frequent closed itemsets

被引：16

作者：

Aryabarzan, Nader ^{[1
,2
]}

Minaei-Bidgoli, Behrouz ^{[3
]}

机构：

[1] Islamic Azad Univ, Dept Comp Engn, Sci & Res Branch, Tehran, Iran

[2] Islamic Azad Univ, Dept Comp Engn, Marvdasht Branch, Marvdasht, Iran

[3] Iran Univ Sci & Technol, Sch Comp Engn, Tehran, Iran

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2021年 / 174卷

关键词：

Data mining; Frequent itemset; Closed itemset; Vertical; Association rule; EFFICIENT ALGORITHM; PATTERNS;

D O I：

10.1016/j.eswa.2021.114738

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Frequent closed itemsets provide a lossless and concise collection of all frequent itemsets to reduce the runtime and memory requirement of frequent itemsets mining tasks. This study presents an algorithm named NECLAT-CLOSED for fast mining of frequent closed itemsets. We introduce concepts and techniques based on the vertical database format and employ them in the mining process. The experimental results show that NECLATCLOSED outperforms the leading algorithms in terms of runtime and memory usage, especially runtime, in most cases.

引用

页数：11

共 64 条

[1]

Agrawal R., 1993, SIGMOD Record, V22, P207, DOI 10.1145/170036.170072

[2]

Agrawal R., 1994, P 20 INT C VER LARG, V1215, P487

[3] A Parallel MapReduce Algorithm to Efficiently Support Itemset Mining on High Dimensional Data [J].