基于人工蜂群的模糊聚类算法

Fuzzy clustering algorithm based on artificial bee colony

针对模糊C-均值(FCM)聚类算法存在容易陷入局部极小值、对初始值和噪声数据敏感的缺点,提出一种基于人工蜂群(ABC)的模糊聚类算法(ABFM).该算法引入全局寻优能力强的人工蜂群算法来求得最优解作为FCM算法的初始聚类中心,然后利用FCM算法优化初始聚类中心,最后求得全局最优解,从而有效克服了FCM算法的缺点.实验结果表明,新算法与FCM聚类算法相比,提高了算法的寻优能力,并且迭代次数更少,收敛速度更快,聚类效果更好.

Aimed at the problems such as the ready occurrence of local minimum with the fuzzy C-means（FCM）clustering algorithm and its sensitivity to initial value and noise data,an artificial bee colony（ABC）-based fuzzy algorithm（ABFM） was put forward.In this algorithm,the optimal solution obtained with ABC algorithm with strong global searching ability was taken as initial clustering-centers of FCM algorithm to optimize initial clustering-centers,so as to get the global optimum and overcome the shortcoming of the FCM algorithm.It was shown by experimental result that compared with the FCM clustering algorithm,the new algorithm could improve the optimum searching ability of the algorithm,the number of iterations would be less,the convergence speed faster,and the clustering efficiency better.