14 March 2013 Bloom filter based frequent patterns mining over data streams
Author Affiliations +
Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 87685V (2013) https://doi.org/10.1117/12.2012477
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore
Abstract
A data streams synopses structure FPCBF, which is based on bloom filter, is proposed in this paper. Each unit of vector BF[e] in FPCBF is a two-tuples. The transactions insert operation (InsertTran) and 1-frequent patterns pregeneration operation (PreGenFP) is defined. Then, A data streams frequent patterns mining algorithm BFFPM which is based on FPCBF is proposed in this paper. The BFFPM algorithm contains two parts: 1-frequent patterns generation and r-frequent patterns generation. The problem of computing the 1-frequent patterns generation is transformed into the problem of computing the longest common sub-sequence α i LCS of k setting identifier sequence in BF[e] in FPCBF. In the same way, the problem of computing the r-frequent patterns generation is transformed into the problem of computing the longest common sub-sequence LCS r , which is the longest common sequence of the identifier sequence α i LCS ,…, i r LCS α + of r items. The IBM synthesizes data generation which output customers shopping a data are adopted as experiment data. The FPCBF algorithm not only has high precision for mining frequent patterns, but also has low memory requirement
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
JunShan Tan, JunShan Tan, Zhufang Kuang, Zhufang Kuang, Guogui Yang, Guogui Yang, "Bloom filter based frequent patterns mining over data streams", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87685V (14 March 2013); doi: 10.1117/12.2012477; https://doi.org/10.1117/12.2012477
PROCEEDINGS
7 PAGES


SHARE
Back to Top