基于网格和密度权值的模糊c均值聚类算法

Fuzzy c-means algorithm based on grid and density weight

改进了基于网格和密度的模糊c均值聚类初始化方法,提出了基于网格和密度权值的模糊c均值算法。该算法在参数初始化时用网格代表点代替原算法的网格凝聚点,同时考虑到在样本空间中处于不同位置的样本点对聚类的影响不同,把密度权值作为系数加入到模糊c均值聚类算法中。实验结果表明,提出的算法对提高算法的效率是有效的。

An initialization method for fuzzy c-means clustering algorithm based on grid and density is improved,a new algorithm is presented.This algorithm is fuzzy c-means algorithm based on the grid and density weight（shorted for GDWFCM）.GDWFCM uses the representative point in stead of the condensation point of grid;at the same time,taking into the account the fact that the sample point in different place will have different influence on the clustering results,we add the density weight as a coefficient to the fuzzy c-means clustering algorithm.The experimental results show that the new algorithm is valid in improving the efficiency of the algorithm.