Summary
International Symposium on Nonlinear Theory and its Applications
2010
Session Number:C3L-C
Session:
Number:C3L-C2
Kernelized Fuzzy c-Means Clustering for Uncertain Data with L1-Regularization Term of Penalty Vectors Using Explicit Mapping
ENDO Yasunori, TAKAYAMA Isao, HAMASUNA Yukihiro, MIYAMOTO Sadaaki,
pp.607-610
Publication Date:2010/9/5
Online ISSN:2188-5079
Summary:
Recently, fuzzy c-means clustering with kernel functions is remarkable in the reason that these algorithms can handle datasets which consist of some clusters with nonlinear boundary. However the algorithms have the following problems: (1) the cluster centers can not be calculated explicitly, (2) it takes long time to calculate clustering results. By the way, we have proposed the clustering algorithms with regularization terms of penalty vectors to handle uncertain data. In this paper, we propose new clustering algorithms with L1-regularization term by introducing explicit mapping of kernel functions to solve the following problems.