Generalized entropy based possibilistic fuzzy C-Means for clustering noisy data and its convergence proof

详细信息    查看全文

• 作者：S. Askari^aAuthor Vitae ; N. Montazerin^a ; ^{mntzrn@aut.ac.ir} ; ^{mntzrn@hotmail.com}Author Vitae ; M.H. Fazel Zarandi^bAuthor Vitae ; E. Hakimi^cAuthor Vitae
• 关键词：Fuzzy C-Means ; Possibilistic C-Means ; Entropy C-Means ; Noise ; Noisy data ; Fuzzy clustering ; Convergence proof
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：5 January 2017
• 年：2017
• 卷：219
• 期：Complete
• 页码：186-202
• 全文大小：1818 K
• 卷排序：219

文摘

An efficient fuzzy clustering algorithm is presented for noisy data. It works with covariance norm in contrast to PFCM. Its error is about 80% less than error of PFCM. It uses a function of distance instead of the distance itself.