作者: Rohan Bhargava , Balakrushna Tripathy
DOI: 10.1007/978-3-642-45062-4_20
关键词:
摘要: Data clustering has found its usefulness in various fields. Algorithms are mostly developed using euclidean distance. But it several drawbacks which maybe rectified by kernel distance formula. In this paper, we propose a based rough-fuzzy C-Means (KRFCM) algorithm and use modified version of the performance indexes (DB D) obtained replacing function with function. We provide comparative analysis RFCM KRFCM computing their DB D index values. The is upon both numerical as well image datasets. results establish that proposed algotihtm outperforms existing one.