National Changhua University of Education Institutional Repository : Item 987654321/11820
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 6507/11669
造访人次 : 30058559      在线人数 : 598
RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 进阶搜寻

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.ncue.edu.tw/ir/handle/987654321/11820

题名: Employing CHNN to develop a data refining algorithm for wireless sensor networks
作者: Chen, Joy Iong-Zong;Yu, Chieh-Chung;Hsieh, M.-T.;Chung, Yi-Nung
贡献者: 電機工程學系
关键词: CHNN (competitive Hopfield neural network);DFA (data fusion algorithm);Mobile sensors;WSN (wireless sensor network)
日期: 2009-04
上传时间: 2012-07-02T02:11:05Z
出版者: IEEE
摘要: 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.
關聯: 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, Los Angeles, CA, 31 March 31-April 2, 2009: 24-31
显示于类别:[電機工程學系] 會議論文

文件中的档案:

档案 大小格式浏览次数
index.html0KbHTML543检视/开启


在NCUEIR中所有的数据项都受到原著作权保护.

 

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