The incremental method for fast computing the rough fuzzy approximations

作者:

Highlights:

摘要

AbstractThe lower and upper approximations are basic concepts in rough fuzzy set theory. The effective computation of approximations is very important for improving the performance of related algorithms. This paper proposed and proved two incremental methods for fast computing the rough fuzzy approximations, one starts from the boundary set, the other is based on the cut sets of a fuzzy set. Then some illustrative examples are conducted. Consequently, two algorithms corresponding to the two incremental methods are put forward respectively. In order to test the efficiency of algorithms, some experiments are made on a large soybean data set from UCI. The experimental results show that the two incremental methods effectively reduce the computing time in comparison with the traditional non-incremental method [1].

论文关键词:Rough fuzzy sets,Lower approximation,Upper approximation,Knowledge discovery,Data mining

论文评审过程:Received 19 February 2010, Revised 31 August 2010, Accepted 31 August 2010, Available online 7 September 2010.

论文官网地址:https://doi.org/10.1016/j.datak.2010.08.005