Metric-Based Semi-Supervised Fuzzy C-Means Clustering

Abstract:

Article Preview

This paper presents a metric-based semi-supervised fuzzy c-means algorithm called MSFCM. Through using side information and unlabeled data together, MSFCM can be applied to both clustering and classification tasks. The resulting algorithm has the following advantages compared with semi-supervised clustering: firstly, membership degree as side information is used to guide the clustering of the data; secondly, through the metric learned, clustering accuracy can be greatly improved. Experimental results on a collection of real-world data sets demonstrated the effectiveness of the proposed algorithm.

Info:

Periodical:

Advanced Materials Research (Volumes 268-270)

Edited by:

Feng Xiong

Pages:

166-171

DOI:

10.4028/www.scientific.net/AMR.268-270.166

Citation:

X. S. Yin et al., "Metric-Based Semi-Supervised Fuzzy C-Means Clustering", Advanced Materials Research, Vols. 268-270, pp. 166-171, 2011

Online since:

July 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.