Cutset-type Possibilistic C-means Clustering Algorithms Based on Semi-supervised Information

• DOI: 10.11999/jeit200757
• Publication Date: 2021-08-10
• Authors: Jiulun Fan; Mengfei Gao; Haiyan Yu; Binbin Chen
• Keywords: Data stream clustering

Cutset-type Possibilistic C-Means clustering (C-PCM) algorithm can significantly reduce the coincident phenomenon of (PCM) by introducing cut-set concept into PCM. The C-PCM also has strong robustness to noise and outliers. However, still suffers from center migration problem for datasets with small targets. In order solve this problem, a Semi-Supervised Possibility (SS-C-PCM) is proposed semi-supervised learning mechanism objective function utilizing some prior information guide process. Meanwhile, in improve segmentation efficiency accuracy color images, differential evolutionary superpixel-based (desSS-C-PCM) proposed. desSS-C-PCM, Differential Evolutionary Superpixel(DES) used obtain spatial neighborhood an image, which integrated quality. Simultaneously, histogram reconstruct new computational complexity algorithm. Several experiments artificial data image show that effectively effect targets execution compared several related algorithms.