摘要
提出一种新的结合了模糊c-均值聚类(FCM)算法和可能性c-均值聚类(PCM)算法优点的联合模糊c-均值聚类(AFCM)算法。它克服了PCM对初始值敏感、易产生一致性聚类的缺点,是PCM的扩展算法。试验表明AFCM能同时产生隶属度和典型值,从而更好地处理噪声,避免了一致性聚类,同时提高了聚类准确性。
A novel model of fuzzy clustering, i.e. an allied fuzzy c means （AFCM） model is proposed based on the combination of advantages of fuzzy c means （FCM） and possibilistic c means （PCM） clustering. PCM is sensitive to initializations and often generates coincident clusters. AFCM overcomes this shortcoming and it is an ex tension of PCM. Membership and typicality values can be simultaneously produced in AFCM. Experimental re- suits show that noise data can be well processed, coincident clusters are avoided and clustering accuracy is better.
