An initial independent and highly noise-resistant fuzzy possibilistic clustering algorithm
Xinhua Zhuang, Yunxin Zhao, Yan Huang, Tong Huang · 2002
The possibilistic C-means (PCM) clustering algorithm is shown to be superior to the conventional fuzzy C-means (FCM) clustering algorithms. We attack several unsolved issues in applying the possibilistic approach to fuzzy clustering. An initial independent and highly noise resistant possibilistic clustering algorithm, named the novel possibilistic C-means (NPCM) clustering algorithm, is developed.>