schliessen

Filtern

 

Bibliotheken

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decrea... Full description

Journal Title: PLoS ONE 2016, Vol.11(6)
Main Author: Cao, Jianfang
Other Authors: Cui, Hongyan , Shi, Hao , Jiao, Lijuan
Format: Electronic Article Electronic Article
Language:
Subjects:
ID: E-ISSN: 1932-6203 ; DOI: 10.1371/journal.pone.0157551 ; PMCID: 4909218 ; PMID: 27304987
Link: pone.0157551.pdf
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: pubmed_central4909218
title: Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce
format: Article
creator:
  • Cao, Jianfang
  • Cui, Hongyan
  • Shi, Hao
  • Jiao, Lijuan
subjects:
  • Research Article
  • Computer And Information Sciences
  • Biology And Life Sciences
  • Physical Sciences
  • Research And Analysis Methods
  • Computer And Information Sciences
  • Physical Sciences
  • Research And Analysis Methods
  • Biology And Life Sciences
  • Computer And Information Sciences
  • Physical Sciences
  • Research And Analysis Methods
  • Physical Sciences
  • Biology And Life Sciences
  • Computer And Information Sciences
  • Biology And Life Sciences
  • Biology And Life Sciences
  • Computer And Information Sciences
ispartof: PLoS ONE, 2016, Vol.11(6)
description: A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
language:
source:
identifier: E-ISSN: 1932-6203 ; DOI: 10.1371/journal.pone.0157551 ; PMCID: 4909218 ; PMID: 27304987
fulltext: fulltext
issn:
  • 1932-6203
  • 19326203
url: Link


@attributes
ID463313756
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid4909218
sourceidpubmed_central
recordidTN_pubmed_central4909218
sourceformatXML
sourcesystemPC
pqid1797874217
display
typearticle
titleBig Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce
creatorCao, Jianfang ; Cui, Hongyan ; Shi, Hao ; Jiao, Lijuan
contributorZou, Quan (editor)
ispartofPLoS ONE, 2016, Vol.11(6)
identifier
subjectResearch Article ; Computer And Information Sciences ; Biology And Life Sciences ; Physical Sciences ; Research And Analysis Methods ; Computer And Information Sciences ; Physical Sciences ; Research And Analysis Methods ; Biology And Life Sciences ; Computer And Information Sciences ; Physical Sciences ; Research And Analysis Methods ; Physical Sciences ; Biology And Life Sciences ; Computer And Information Sciences ; Biology And Life Sciences ; Biology And Life Sciences ; Computer And Information Sciences
descriptionA back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
source
version7
lds50peer_reviewed
links
openurl$$Topenurl_article
backlink$$Upone.0157551.pdf$$EView_source_record
openurlfulltext$$Topenurlfull_article
search
creatorcontrib
0Cao, Jianfang
1Cui, Hongyan
2Shi, Hao
3Jiao, Lijuan
4Zou, Quan
titleBig Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce
descriptionA back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
subject
0Research Article
1Computer and Information Sciences
2Biology and Life Sciences
3Physical Sciences
4Research and Analysis Methods
general
027304987
14909218
210.1371/journal.pone.0157551
3PMC (PubMed Central)
sourceidpubmed_central
recordidpubmed_central4909218
issn
01932-6203
119326203
rsrctypearticle
creationdate2016
addtitlePLoS ONE
searchscopepubmed_central
scopepubmed_central
lsr30VSR-Enriched:[pages, pqid]
sort
titleBig Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce
authorCao, Jianfang ; Cui, Hongyan ; Shi, Hao ; Jiao, Lijuan
creationdate20160615
facets
frbrgroupid7248290398667803074
frbrtype5
creationdate2016
topic
0Research Article
1Computer And Information Sciences
2Biology And Life Sciences
3Physical Sciences
4Research And Analysis Methods
collectionPMC (PubMed Central)
prefilterarticles
rsrctypearticles
creatorcontrib
0Cao, Jianfang
1Cui, Hongyan
2Shi, Hao
3Jiao, Lijuan
4Zou, Quan
jtitlePlos One
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Cao
1Cui
2Shi
3Jiao
4Zou
aufirst
0Jianfang
1Hongyan
2Hao
3Lijuan
4Quan
au
0Cao, Jianfang
1Cui, Hongyan
2Shi, Hao
3Jiao, Lijuan
4Zou, Quan
atitleBig Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce
jtitlePLoS ONE
risdate20160615
volume11
issue6
eissn1932-6203
formatjournal
genrearticle
ristypeJOUR
abstractA back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
pubPublic Library of Science
doi10.1371/journal.pone.0157551
pmid27304987
pagese0157551
oafree_for_read
date2016-06-15