Genetic-fuzzy mining with type-2 membership functions
Yu Li, Chun-Hao Chen, Tzung‐Pei Hong, Yeong-Chyi Lee · 2014
In this paper, a type-2 genetic-fuzzy mining algorithm is proposed for mining a set of type-2 membership functions for mining fuzzy association rules. It first encodes the type-2 membership functions of each item into a chromosome. The quantitative transactions are then transformed into fuzzy values according to the type-2 membership functions. Each chromosome is then evaluated by the number of large 1-itemsets and the suitability factor. The suitability factor consists of three sub-factors - coverage, overlap and difference which are used to avoid three bad types of membership functions. Experiments on a simulated dataset are also conducted to show the effectiveness of the proposed approach.