Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK)

Qinhuangdao,China,7.9-7.13,2010

ISBN: 978-1-935068-15-0 Scientific Research Publishing, USA

E-Book 840pp Pub. Date: July 2010

Category: Computer Science & Communications

Price: $120

Title: Estimating Channel States by Density-Based Rival Penalized Competitive Learning
Source: Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK) (pp 221-224)
Author(s): Yao-Jen Chang, Department of Communication Engineering Central University, Chung-Li, 320
Chia-Lu Ho, Department of Communication Engineering Central University, Chung-Li, 320
Abstract: We propose a channel states estimation method named as the density-based RPCL (DERPCL) to prune the structure of a rival penalized competitive learning (RPCL) method by evaluating the data density of each unit. Although the RPCL has been shown to perform clustering methods without knowing the extract number of clusters, they may not solve the problems of local optima and slow learning speed for complicated circumstances. This newly proposed method is applied to estimating channel states, and its results are compared with the other RPCL methods. Our results show that the proposed DERPCL method outperforms the traditional ones in terms of convergence accuracy and speed.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top