On the design of hardware architectures for parallel frequent itemsets mining

作者：

Highlights：

• It is proposed a search strategy for Frequent Itemsets Mining based on equivalence class partitioning.

• It is presented two hardware architectures that efficiently exploits the search strategy proposed.

• The hardware architectures proposed can deal with an arbitrary number of items and transactions.

• The hardware architectures proposed can be scaled for obtaining better processing times.

摘要

•It is proposed a search strategy for Frequent Itemsets Mining based on equivalence class partitioning.•It is presented two hardware architectures that efficiently exploits the search strategy proposed.•The hardware architectures proposed can deal with an arbitrary number of items and transactions.•The hardware architectures proposed can be scaled for obtaining better processing times.

论文关键词：Frequent itemsets mining,Data streams,Custom architectures,FPGAs,ECLAT

论文评审过程：Received 22 March 2019, Revised 5 March 2020, Accepted 5 April 2020, Available online 16 April 2020, Version of Record 27 April 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113440