Possibilistic C-Spherical Shell clustering algorithm based on conformai geometric algebra

In this paper, a new Possibilistic C-Spherical Shell clustering (PCSS) algorithm based on conformal geometric algebra is proposed. The probability and simplicity of using the conformal geometric algebra to analyse spherical shell clustering algorithm is discussed firstly. By the conformal geometric algebra theory, patterns and prototypes in spherical shell clustering can be represented as vectors, then the objective function for clustering analysis can be expressed effectively, and a new solution to minimize the objective function is deduced. The experimental results show that the proposed algorithm can cluster the spherical shell data effectively, and is robust for noise.