schliessen

Filtern

 

Bibliotheken

Belief Function Based Decision Fusion for Decentralized Target Classification in Wireless Sensor Networks

Decision fusion in sensor networks enables sensors to improve classification accuracy while reducing the energy consumption and bandwidth demand for data transmission. In this paper, we focus on the decentralized multi-class classification fusion problem in wireless sensor networks (WSNs) and a new... Full description

Journal Title: Sensors 01 August 2015, Vol.15(8), pp.20524-20540
Main Author: Wenyu Zhang
Other Authors: Zhenjiang Zhang
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: E-ISSN: 1424-8220 ; DOI: 10.3390/s150820524
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: doaj_soai_doaj_org_article_788c704c7b8948c19de9a05f7825a0e1
title: Belief Function Based Decision Fusion for Decentralized Target Classification in Wireless Sensor Networks
format: Article
creator:
  • Wenyu Zhang
  • Zhenjiang Zhang
subjects:
  • Decision Fusion
  • Distributed Classification Fusion
  • Belief Function
  • Evidence Theory
  • Wireless Sensor Networks
  • Engineering
ispartof: Sensors, 01 August 2015, Vol.15(8), pp.20524-20540
description: Decision fusion in sensor networks enables sensors to improve classification accuracy while reducing the energy consumption and bandwidth demand for data transmission. In this paper, we focus on the decentralized multi-class classification fusion problem in wireless sensor networks (WSNs) and a new simple but effective decision fusion rule based on belief function theory is proposed. Unlike existing belief function based decision fusion schemes, the proposed approach is compatible with any type of classifier because the basic belief assignments (BBAs) of each sensor are constructed on the basis of the classifier’s training output confusion matrix and real-time observations. We also derive explicit global BBA in the fusion center under Dempster’s combinational rule, making the decision making operation in the fusion center greatly simplified. Also, sending the whole BBA structure to the fusion center is avoided. Experimental results demonstrate that the proposed fusion rule has better performance in fusion accuracy compared with the naïve Bayes rule and weighted majority voting rule.
language: eng
source:
identifier: E-ISSN: 1424-8220 ; DOI: 10.3390/s150820524
fulltext: fulltext_linktorsrc
issn:
  • 1424-8220
  • 14248220
url: Link


@attributes
ID1258855425
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordidoai_doaj_org_article_788c704c7b8948c19de9a05f7825a0e1
sourceiddoaj_s
recordidTN_doaj_soai_doaj_org_article_788c704c7b8948c19de9a05f7825a0e1
sourcesystemOther
dbidDOA
pqid1706577863
display
typearticle
titleBelief Function Based Decision Fusion for Decentralized Target Classification in Wireless Sensor Networks
creatorWenyu Zhang ; Zhenjiang Zhang
ispartofSensors, 01 August 2015, Vol.15(8), pp.20524-20540
identifierE-ISSN: 1424-8220 ; DOI: 10.3390/s150820524
subjectDecision Fusion ; Distributed Classification Fusion ; Belief Function ; Evidence Theory ; Wireless Sensor Networks ; Engineering
descriptionDecision fusion in sensor networks enables sensors to improve classification accuracy while reducing the energy consumption and bandwidth demand for data transmission. In this paper, we focus on the decentralized multi-class classification fusion problem in wireless sensor networks (WSNs) and a new simple but effective decision fusion rule based on belief function theory is proposed. Unlike existing belief function based decision fusion schemes, the proposed approach is compatible with any type of classifier because the basic belief assignments (BBAs) of each sensor are constructed on the basis of the classifier’s training output confusion matrix and real-time observations. We also derive explicit global BBA in the fusion center under Dempster’s combinational rule, making the decision making operation in the fusion center greatly simplified. Also, sending the whole BBA structure to the fusion center is avoided. Experimental results demonstrate that the proposed fusion rule has better performance in fusion accuracy compared with the naïve Bayes rule and weighted majority voting rule.
languageeng
oafree_for_read
source
version4
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
linktorsrc$$Uhttps://doaj.org/article/788c704c7b8948c19de9a05f7825a0e1$$EView_full_text_in_DOAJ
search
creatorcontrib
0Wenyu Zhang
1Zhenjiang Zhang
titleBelief Function Based Decision Fusion for Decentralized Target Classification in Wireless Sensor Networks
description

Decision fusion in sensor networks enables sensors to improve classification accuracy while reducing the energy consumption and bandwidth demand for data transmission. In this paper, we focus on the decentralized multi-class classification fusion problem in wireless sensor networks (WSNs) and a new simple but effective decision fusion rule based on belief function theory is proposed. Unlike existing belief function based decision fusion schemes, the proposed approach is compatible with any type of classifier because the basic belief assignments (BBAs) of each sensor are constructed on the basis of the classifier’s training output confusion matrix and real-time observations. We also derive explicit global BBA in the fusion center under Dempster’s combinational rule, making the decision making operation in the fusion center greatly simplified. Also, sending the whole BBA structure to the fusion center is avoided. Experimental results demonstrate that the proposed fusion rule has better performance in fusion accuracy compared with the naïve Bayes rule and weighted majority voting rule.

subject
0Decision Fusion
1Distributed Classification Fusion
2Belief Function
3Evidence Theory
4Wireless Sensor Networks
5Engineering
general
0English
1MDPI AG
210.3390/s150820524
3Directory of Open Access Journals (DOAJ)
sourceiddoaj_s
recordiddoaj_soai_doaj_org_article_788c704c7b8948c19de9a05f7825a0e1
issn
01424-8220
114248220
rsrctypearticle
creationdate2015
addtitleSensors
searchscope
0doaj_full
1doaj1
scope
0doaj_full
1doaj1
lsr45$$EView_full_text_in_DOAJ
tmp01Directory of Open Access Journals (DOAJ)
tmp02DOA
startdate20150801
enddate20150801
lsr40Sensors, 01 August 2015, Vol.15 (8), pp.20524-20540
doi10.3390/s150820524
citationpf 20524 pt 20540 vol 15 issue 8
lsr30VSR-Enriched:[pqid]
sort
titleBelief Function Based Decision Fusion for Decentralized Target Classification in Wireless Sensor Networks
authorWenyu Zhang ; Zhenjiang Zhang
creationdate20150801
lso0120150801
facets
frbrgroupid7902421637838528962
frbrtype5
newrecords20190714
languageeng
topic
0Decision Fusion
1Distributed Classification Fusion
2Belief Function
3Evidence Theory
4Wireless Sensor Networks
5Engineering
collectionDirectory of Open Access Journals (DOAJ)
prefilterarticles
rsrctypearticles
creatorcontrib
0Wenyu Zhang
1Zhenjiang Zhang
jtitleSensors
creationdate2015
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext_linktorsrc
addata
au
0Wenyu Zhang
1Zhenjiang Zhang
atitleBelief Function Based Decision Fusion for Decentralized Target Classification in Wireless Sensor Networks
jtitleSensors
risdate20150801
volume15
issue8
spage20524
epage20540
pages20524-20540
eissn1424-8220
formatjournal
genrearticle
ristypeJOUR
abstract

Decision fusion in sensor networks enables sensors to improve classification accuracy while reducing the energy consumption and bandwidth demand for data transmission. In this paper, we focus on the decentralized multi-class classification fusion problem in wireless sensor networks (WSNs) and a new simple but effective decision fusion rule based on belief function theory is proposed. Unlike existing belief function based decision fusion schemes, the proposed approach is compatible with any type of classifier because the basic belief assignments (BBAs) of each sensor are constructed on the basis of the classifier’s training output confusion matrix and real-time observations. We also derive explicit global BBA in the fusion center under Dempster’s combinational rule, making the decision making operation in the fusion center greatly simplified. Also, sending the whole BBA structure to the fusion center is avoided. Experimental results demonstrate that the proposed fusion rule has better performance in fusion accuracy compared with the naïve Bayes rule and weighted majority voting rule.

pubMDPI AG
doi10.3390/s150820524
oafree_for_read
date2015-08-01