TY - JOUR
T1 - On rival penalization controlled competitive learning for clustering with automatic cluster number selection
AU - CHEUNG, Yiu Ming
N1 - Funding Information:
The author would like to sincerely thank the editor and three anonymous reviewers for their valuable comments and insightful suggestions. Also, thanks go to Mr. Lap-tak Law for helping to carry out the experiments on color image segmentation. This work was supported by a grant from the Research Grant Council of the Hong Kong SAR (Project No: HKBU 2156/04E), and by a Faculty Research Grant of Hong Kong Baptist University (Project Code: FRG/02-03/II-40).
PY - 2005/11
Y1 - 2005/11
N2 - The existing Rival Penalized Competitive Learning (RPCL) algorithm and its variants have provided an attractive way to perform data clustering without knowing the exact number of clusters. However, their performance is sensitive to the preselection of the rival delearning rate. In this paper, we further investigate the RPCL and present a mechanism to control the strength of rival penalization dynamically. Consequently, we propose the Rival Penalization Controlled Competitive Learning (RPCCL) algorithm and its stochastic version. In each of these algorithms, the selection of the delearning rate is circumvented using a novel technique. We compare the performance of RPCCL to RPCL in Gaussian mixture clustering and color image segmentation, respectively. The experiments have produced the promising results.
AB - The existing Rival Penalized Competitive Learning (RPCL) algorithm and its variants have provided an attractive way to perform data clustering without knowing the exact number of clusters. However, their performance is sensitive to the preselection of the rival delearning rate. In this paper, we further investigate the RPCL and present a mechanism to control the strength of rival penalization dynamically. Consequently, we propose the Rival Penalization Controlled Competitive Learning (RPCCL) algorithm and its stochastic version. In each of these algorithms, the selection of the delearning rate is circumvented using a novel technique. We compare the performance of RPCCL to RPCL in Gaussian mixture clustering and color image segmentation, respectively. The experiments have produced the promising results.
KW - Cluster number
KW - Clustering
KW - Rival Penalization Controlled Competitive Learning
KW - Stochastic RPCL
UR - http://www.scopus.com/inward/record.url?scp=28244471987&partnerID=8YFLogxK
U2 - 10.1109/TKDE.2005.184
DO - 10.1109/TKDE.2005.184
M3 - Journal article
AN - SCOPUS:28244471987
SN - 1041-4347
VL - 17
SP - 1583
EP - 1588
JO - IEEE Transactions on Knowledge and Data Engineering
JF - IEEE Transactions on Knowledge and Data Engineering
IS - 11
ER -