A Novel Fuzzy Weighted C-Means Method for Classification

• Main Authors: Wen-Chun Huang, 黃文俊
• Other Authors: Bor-chen Kuo
• Format: Others
• Language: zh-TW
• Published: 2009
• Online Access: http://ndltd.ncl.edu.tw/handle/93482846165969876602

碩士 === 國立臺中教育大學 === 教育測驗統計研究所 === 97 === Many researches show the fuzzy c-means clustering is a powerful tool for partitioning samples into different categories. However, the cost function of the classical fuzzy c-means (FCM) is defined by the distances from data to the cluster centers with their fuzzy memberships. In this study, a new fuzzy clustering algorithm, namely the fuzzy weighted c-means (FWCM), is proposed. In this proposed FWCM, the concept of weighted means used in nonparametric weighted feature extraction (NWFE) is employed for replacing the cluster centers in the FCM. The experiments on both synthetic and real data show that the proposed clustering algorithm can generate better clustering results than FCM and tradition the fuzzy clustering algorithms.