Abstract: Aiming at the clustering of the categorical data and by extending the kernel method to the fast efficient fuzzy c-means clustering algorithm‚a fuzzy kernel c-means （FKCM） clustering algorithm based on the kernel func-tion was constructed．In this algorithm‚the empirical kernel matrix is applied in order to fully utilize the dissimilarity information among the data．Unlike the fuzzy k-mode algorithm‚the modes in the new algorithm need not be directly calculated in each iteration‚thus improving the precision and stability of the clustering algorithm and making the new algorithm insensitive to the selection of mode（centroid） initialization．A simulation was finally carried out on the actu-al linearly and nonlinearly separable categorical data sets‚which demonstrates the effectiveness of the proposed algo-rithm．

Key words:  categorical data, clustering, data mining, fuzzy c-means, kernel method