A Possibilistic C-Means Clustering Algorithm Based on Kernel Methods

A novel fuzzy clustering algorithm, called kernel possibilistic c-means model (KPCM), is proposed. KPCM algorithm is based on kernel methods and possibilistic c-means (PCM) algorithm and it is the extension of PCM algorithm. Different from PCM and FCM which are based on Euclidean distance, the proposed model is based on kernel-induced distance by using kernel methods. Furthermore, with kernel methods the input data can be mapped implicitly into a high-dimensional feature space where possibilistic c-means clustering is carried out. FCM, PCM and KPCM are performed numerical experiments on data sets. The experimental results show the better performance of KPCM.