A New Clustering Algorithm Based on Token Ring

Authors:
Yongquan Liang;Jiancong Fan;Zhongying Zhao
Affiliations:
Shandong University of Science and Technology, China;Shandong University of Science and Technology, China;Shandong University of Science and Technology, China
Venue:
SNPD '07 Proceedings of the Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing - Volume 01
Year:
2007

Citing 0
Cited 1

EDA-USL: unsupervised clustering algorithm based on estimation of distribution algorithm

International Journal of Wireless and Mobile Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Token is a kind of symbol. It has some controlling powers. A special token-ring structure is designed according to the characteristics of the token. The token-ring structure consists of a controlling token and a sub-token. The controlling token includes some controlling information such as clustering center. The sub-token is designed to search for data and mark the qualified data. Based on the token-ring structure, a new clustering algorithm is designed. The algorithm can modify class structure dynamically in the process of clustering. The theoretical and practical analysis showed that the algorithm had good performances in some indexes, such as scalability, accuracy and velocity.