Home // IMMM 2021, The Eleventh International Conference on Advances in Information Mining and Management // View article

An Effective Approach for Genetic-Fuzzy Mining Using the Graphics Processing Unit

Authors:
Chun-Hao Chen
Yu-Qi Huang
Tzung-Pei Hong

Keywords: association rule; genetic algorithm; fuzzy set; fuzzy association rule; graphics processing unit

Abstract:
Association analysis is an important technique for finding relationships among the given transactions. In real applications, since transactions may have quantitative values, the fuzzy-set theory was utilized for mining fuzzy association rules. To extract useful rules, the given membership functions were the critical factor. The genetic-fuzzy mining approaches were thus presented to obtain appropriate membership functions to mine fuzzy association rules. However, the evolution process was time-consuming. In this paper, we then propose an algorithm to reduce the processing time using the graphics processing unit (GPU), namely the GPU-based Genetic-Fuzzy Mining algorithm (GPU-GFM). It first collects the chromosomes from the population and the chromosomes generated by genetic operators. Then, chromosomes are sent to GPU to calculate the fitness values. As a result, a fitness value matrix is returned. At last, when reaching the termination condition, the best chromosome will be outputted for mining fuzzy association rules. Experiments were also conducted on simulation datasets to show the performance of the proposed approach.

Pages: 7 to 11

Copyright: Copyright (c) IARIA, 2021

Publication date: May 30, 2021

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-864-8

Location: Valencia, Spain

Dates: from May 30, 2021 to June 3, 2021