基于聚类中心分离的模糊聚类模型

在模糊C-均值聚类（FCM）目标函数的基础上按聚类中心分离原则增加一个聚类中心分离项来扩展FCM算法，提出基于聚类中心分离的模糊聚类模型(FCM_CCS)。该模型可使聚类过程中的聚类中心之间距离扩大，从而得到更好的聚类效果。由于该模型和FCM一样对噪声敏感我们提出它的可能性聚类模型(PCM_CCS)，最后进一步扩展成它的可能性模糊聚类模型(PFCM_CCS)。基于聚类中心分离的可能性模糊聚类模型在处理噪声数据和克服一致性聚类问题方面表现出良好的性能。对数据集的测试实验结果表明了提出的PFCM_CCS能同时产生模糊隶属度和典型值，使聚类中心间距扩大，同时具有更好的聚类准确率。

Fuzzy Clustering Models Based on Cluster Centers Separation

A cluster centers separation item is added in the objective function of fuzzy C-means (FCM) algorithm to extend FCM algorithm based on the principle of cluster centers separation. In this method we propose fuzzy clustering model based on cluster centers separation (FCM_CCS). FCM_CCS enlarges the distances between cluster centers during clustering and obtain better clustering effect. FCM_CCS is sensitive to noises the same as FCM so we propose its possibilistic clustering model (PCM_CCS). Finally, we extend PCM_CCS to its possibilistic fuzzy clustering model. Possibilistic fuzzy clustering model based on cluster centers separation (PFCM_CCS) shows good performance in dealing with noisy data and overcoming the problem of coincident clusters. The experimental results with data sets show that our proposed PFCM_CCS can produce both fuzzy membership values and typicality values simultaneously, large distances between cluster centers and better clustering accuracy.