基于免疫粒子群优化的模糊C均值聚类算法

Fuzzy C-means clustering algorithm based on immune particle swarm optimization

把免疫系统的免疫信息处理机制引入到粒子群优化(PSO)算法中,并与模糊C均值(FCM)算法相结合提出一种新的模糊聚类算法.新算法用免疫粒子群优化算法代替FCM算法的基于梯度下降的迭代过程,使算法具有较强的全局搜索能力,很大程度上避免了FCM算法易陷入局部极小的缺陷,同时也降低了FCM算法对初始值的敏感度.采用对当基思想初始化种群,获得更优的初始候选解,提高算法聚类过程中的收敛速度.以UCI机器学习数据库中的两组数据集为研究对象,实验结果表明,该算法优于基于PSO的模糊C均值聚类算法和FCM算法.

By combining the properties of both Particle Swarm Optimization （PSO） algorithm in which the immune information processing mechanism of immune system is involved and Fuzzy C-Means （FCM） method, a novel fuzzy clustering algorithm is proposed. The iteration process is replaced by the PSO algorithm with immunity based on the gradient descent of FCM, which makes the algorithm have a strong global searching capacity and avoids the local minimum problems of FCM. At the same time, FCM is no longer a large degree dependent on the initialization values. Moreover, it employs opposition-based learning for population initialization to obtain fitter starting candidate solutions and improve the conver- gence speed. A real application in classifying two data sets in UCI machine learning database is provided. Numerical experiments show that the proposed algorithm is better than fuzzy c-means clustering based on PSO and FCM.