Abstract:  In order to get the optimal clustering number and the corresponding samples in each cluster‚a new cluster-ing method is introduced in this paper．The new method can be used to construct an object evaluation function‚which takes into consideration not only the scattering degree among clusters but also the compactness in the same cluster．To obtain the center and memberships values of each cluster by iteration‚the FCM（Fuzzy c-mean） algorithm is adopted．The genetic algorithm is then used to search for the global optimal point．The proposed algorithm is applied to the fuzzy clustering of the ful- l factored productivity of China．

Key words: fuzzy clustering, fuzzy c-mean, genetic algorithm