论文部分内容阅读
在模糊C均值(Fuzzy C-Means,FCM)聚类应用过程中,针对目前模糊加权指数的确定缺乏理论依据和有效评价方法这一问题,提出了一种基于子集测度的模糊加权指数计算方法。首先根据子集测度理论定义了一个聚类有效性函数,然后依据该函数在聚类过程中通过循环进化迭代来计算聚类结果的有效性,并将其值反馈到模糊加权指数m的变化中,而使m收敛到一个稳定解,即得到最佳模糊加权指数。理论分析和实验表明,该算法是有效的,为模糊加权指数m的探讨研究提供了一种新的思路和途径。
In the application of fuzzy C-Means (FCM) clustering, in view of the lack of theoretical basis and effective evaluation method for the determination of the current fuzzy weighted index, a fuzzy weighted index calculation method based on subset measure is proposed . Firstly, a clustering validity function is defined according to the sub-measure theory, and then the validity of the clustering result is calculated through iterative evolution iteration in the clustering process according to the function, and its value is fed back to the change of the fuzzy weighting index m , And make m converge to a stable solution, that is, get the best fuzzy weighted index. Theoretical analysis and experiments show that this algorithm is effective and provides a new way of thinking for the study of fuzzy weighted index m.