A novel semi-supervised fuzzy c-means clustering method
Kunlun Li, Zheng Cao, Liping Cao, Rui Zhao · 2009
In this paper we propose a novel semi-supervised fuzzy c-means algorithm. We introduce a seed set which contains a small amount of labeled data. First, generating an initial partition in the seed set, we use the center of each partition as the cluster center and optimize the objective function of FCM using EM algorithm. Experiments results show that, our method can avoid the defect of fuzzy c-means that is sensitive to the initial centers partly and give much better partition accuracy.