聚类——GAKFCM

聚类——GAKFCM

作者：凯鲁嘎吉 - 博客园 http://www.cnblogs.com/kailugaji/

参考文献：黄白梅. 基于GA优化的核模糊C均值聚类算法的研究[D]. 武汉科技大学, 2013.

一、遗传算法

二、算法具体细节

1.Real Coding Mode

Each individual is represented by C×D real numbers, where C is the number of clusters and D is the dimension of the data.

2.Nonlinear Ranking Select Measurement

where q is the parameter, j is the sorting number and n is the number of individuals.

3.Adaptive Crossover Strategy

where pc0 is the initial crossover rate, t is the current evolution time of individuals and T is the maximum number of iterations.

4.Adaptive Mutation Strategy

where pm0 is the initial mutation rate, t is the current evolution time of individuals and T is the maximum number of iterations.

5.Fitness Function

其中JKFCM见聚类——KFCM。

三、算法流程

四、理解

GAKFCM是指用GA进行初始化KFCM的参数（聚类中心）。每个个体的大小与聚类中心的大小一致。