English  |  正體中文  |  简体中文  |  Items with full text/Total items : 6491/11663
Visitors : 24735347      Online Users : 49
RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ir.ncue.edu.tw/ir/handle/987654321/11820

Title: Employing CHNN to develop a data refining algorithm for wireless sensor networks
Authors: Chen, Joy Iong-Zong;Yu, Chieh-Chung;Hsieh, M.-T.;Chung, Yi-Nung
Contributors: 電機工程學系
Keywords: CHNN (competitive Hopfield neural network);DFA (data fusion algorithm);Mobile sensors;WSN (wireless sensor network)
Date: 2009-04
Issue Date: 2012-07-02T02:11:05Z
Publisher: IEEE
Abstract: In this report a data fusion algorithm (DFA) for obtaining the relationships between wireless sensor measurements and existing tracks is proposed. It is known that a DFA plays an important role in wireless sensors for target tracking over WSN (wireless sensor network) deployments. However, a new approach to data fusion based on the CHNN (competitive Hopfield neural network) is here investigated, wherein the matching between mobile sensor measurements and existing target tracks can achieve global consideration. Embedded within the CHNN is also a competitive learning mechanism which creatively removes the dilemma of occasional irrational solutions in traditional HNN (Hopfield neural networks). In this research, it is also established that with the proposed approach, the network is guaranteed to converge into a stable state when performing a data association. The CHNN-based DFA is combined with mobile sensors in a WSN system to demonstrate the target tracking capabilities. Finally, computer simulation results indicate that this approach successfully solves the data association problems addressed over WSN environments.
Relation: 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, Los Angeles, CA, 31 March 31-April 2, 2009: 24-31
Appears in Collections:[電機工程學系] 會議論文

Files in This Item:

File SizeFormat

All items in NCUEIR are protected by copyright, with all rights reserved.


DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback