Frequent Itemsets Mining in Data Streams Using Reconfigurable Hardware

被引：3

作者：

Bustio, Lazaro ^{[1
,2
]}

Cumplido, Rene ^{[2
]}

Hernandez, Raudel ^{[1
]}

Bande, Jose M. ^{[1
]}

Feregrino, Claudia ^{[2
]}

机构：

[1] Adv Technol Applicat Ctr, 7a 21812 E-218 & 222 Rpto Siboney, Havana 12200, Cuba

[2] Natl Inst Astrophys Opt & Elect, Luis Enrique Erro 1, Puebla 72840, Mexico

来源：

NEW FRONTIERS IN MINING COMPLEX PATTERNS | 2016年 / 9607卷

关键词：

Data mining; Frequent itemsets mining; Data streams; Reconfigurable hardware; Parallel algorithms; TOP-K ELEMENTS; ALGORITHMS; ISSUES;

D O I：

10.1007/978-3-319-39315-5_3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Data streams are unbounded and infinite flows of data arriving at high rates which cannot be stored for offline processing. Because of this, classical approaches for Data Mining cannot be used straightforwardly in data stream scenario. This paper introduces a single-pass hardware-based algorithm for frequent itemsets mining on data streams that uses the top-k frequent 1-itemsets. Experimental results of the hardware implementation of the proposed algorithm are also presented and discussed.

引用

页码：32 / 45

页数：14

共 39 条

[1]

[Anonymous], 1994, P INT C VERY LARGE D

[2]

[Anonymous], CEUR WORKSHOP P

[3]

[Anonymous], 2010, 1 AS NETFPGA DEV WOR

[4]

[Anonymous], GLOBAL J COMPUT SCI

[5]

[Anonymous], INT J COMPUT

[6]

[Anonymous], 2005, P 1 INT WORKSH OP SO, DOI DOI 10.1145/1133905.1133907

[7]

[Anonymous], SOFTWARE FREQUENT PA

[8]

[Anonymous], 2007, DATA STREAMS MODELS, DOI DOI 10.1007/978-0-387-47534-9_4

[9]

[Anonymous], IBM QUEST MARKET BAS

[10]

Babcock B., 2002, PODS, P1, DOI [DOI 10.1145/543613.543615, 10.1145/543613.543615]

← 1 2 3 4 →