Open AccessParallel Design of Apriori Algorithm Based on the Method of “Determine Infrequent Items & Remove Infrequent Itemsets”
Author(s) -
Suo Dongnan,
Zhaopeng Zhang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/634/1/012065
Subject(s) - apriori algorithm , association rule learning , data mining , computer science , a priori and a posteriori , process (computing) , fault (geology) , algorithm , association (psychology) , big data , gsp algorithm , philosophy , epistemology , seismology , geology , operating system
In the method of fault association rule diagnosis, Apriori algorithm has low efficiency for big data processing. In this paper, aiming at the defects of Apriori algorithm, MapReduce computing framework is used to optimize the Apriori association rule algorithm. This method improves the accuracy of association mining in fault diagnosis. In the process of optimization, this paper proposes the method of “Determine Infrequent Items & Remove Infrequent Itemsets”. Through experiments, this method effectively reduces the computational space needed by Apriori algorithm in association rule mining, and improves the computing speed.