一种基于核的混合c-均值聚类模型

A Kernel-based Hybrid c-means Clustering Model

FCM和PCM的混合模型可以克服它们单独聚类时的缺点,在聚类效果上有很大改进,但是对于特征不明显的样本而言,这种混合模型的聚类效果并不太好,为了克服这一缺点,本文引入Mercer核,提出了一种新的基于核的混合c-均值聚类模型(KIPCM),运用核函数使得在原始空间不可分的数据点在核空间变得可分。通过数值实验,得到了较为合理的中心值以及较高的正确分类率,证实了本文算法的可行性和有效性。

The hybrid model of FCM and PCM can overcome the shortcomings when they cluster separately. It has great improvement in the clustering effect. But the effect is not so well for the samples without obvious characteristics. In order to overcome this disadvantage, this paper introduces the Mercer kernel and proposes a new model called Kernel-based hybrid c-means clustering （KIPCM）. This model makes it possible to cluster the data which are linearly non-separable in the original space into homogeneous groups in the kernel space by using kernel function. We get the better center values and the higher correct classification rate through numerical experiment. This confirms the feasibility and effectiveness of the algorithm in this paper, i