An intuitionistic fuzzy possibilistic C-means clustering based on genetic algorithm

Abstract

In fuzzy clustering algorithm, fuzzy possibilistic C-means clustering algorithm (FPCM) is widely used. However, the method is sensitive to its parameters and the clustering accuracy and robustness is poor. In order to overcome the above problems, this paper presents an intuitionistic fuzzy possibilistic C-means clustering based on genetic algorithm (IFPCM-GA). IFPCM-GA does not only retain the advantages of FPCM, but also uses a kernel function to replace the Euclidean distance to enhance the robustness of the algorithm. We get an intuitionistic fuzzy possibilistic C-means clustering algorithm (IFPCM) by using the intuitionistic fuzzy set theory to the fuzzy possibilistic C-means clustering algorithm induced by kernel metric. Taking into account the hesitation degree of data, IFPCM can obtain a more accurate membership matrix and cluster centers to enhance the clustering performance. IFPCM-GA uses genetic algorithm to search the optimal parameters of IFPCM, which can avoid the poor clustering results. The experimental results show that IFPCM-GA has a strong robustness and can obtain more accurate clustering results compared with the existing algorithms.