摘要
针对经典C均值聚类算法和模糊C均值聚类算法所存在的对初始聚类中心过分依赖以及需要预先知道实际聚类数目的问题,基于模糊C均值聚类算法提出了一种新算法:自适应约束模糊C均值(ACFCM)聚类算法,它在模糊C均值聚类算法的基础上,给目标函数加入了一个惩罚项,使得上述问题得以解决。并通过仿真实验证实了新算法的可行性和有效性。
There are two issues in the application of FCM clustering algorithm： one is that the FCM algorithm is too sensitive to the initial cluster centers,and the other is that the number of the clusters C needs to be determined in advance as an input to the algorithm.Based on this,a novel algorithm of FCM is proposed in this paper：Adaptive Constrained FCM clustering algorithm,based on the FCM,a penalty term is added into the objective function and the above-mentioned issues can be resolved.The simulation demonstrates the feasibility and validity of the proposed method.
出处
《模糊系统与数学》
CSCD
北大核心
2010年第5期126-130,共5页
Fuzzy Systems and Mathematics
基金
国家自然科学基金资助项目(10371106
10471114
61070234
61071167)
江苏省高校自然科学基金资助项目(04KJB110097
08KJB520003)
南京邮电大学攀登计划项目(NY207064)
