结合蚁群聚类算法的模糊C均值聚类

模糊C均值（FCM）聚类算法采取随机选取聚类中心的方法，这种方法使得FCM算法在局部范围内容易获得最优解，但在全局范围内效果较差，且FCM算法中聚类簇的个数一般需要人为设定。面对上述种种问题，文中将蚁群聚类算法和FCM聚类算法进行结合，获得了一种改进的FCM聚类算法。该算法在初步聚类中利用蚁群聚类产生聚类中心和簇的个数，将产生的聚类中心提供给FCM算法进行再次聚类。利用蚁群聚类的全局搜索和并行运算的优点避免了聚类易陷入局部最优解的缺陷。经过实验验证，该算法较一般FCM算法具有更好的性能。

Fuzzy C Mean Clustering Combined Ant Colony Clustering Algorithm

Fuzzy C-means （FCM ） clustering algorithm gets the initial clustering center by random selecting, which makes the FCM algo- rithm is easy to fall into local optimal solution of the dilemma,and the FCM clustering algorithm needs to set the number of clustering center by human constructing. It addresses the above problems with ant colony clustering to propose an advanced FCM clustering algo- rithm. The ant colony clustering creates the initial clustering center and the number of the center,tbe data uses to be the input for Fuzzy C -means clustering algorithm. Global search and parallel computing benefits avoid the clustering which is easy to fall into local optimal so- lution of the defects. After experimental verification,the simulation result shows the effectiveness of the method.