Please use this identifier to cite or link to this item: http://buratest.brunel.ac.uk/handle/2438/13465
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLiu, Y-
dc.contributor.authorXu, L-
dc.contributor.authorLi, M-
dc.date.accessioned2016-11-09T13:53:13Z-
dc.date.available2016-02-24-
dc.date.available2016-11-09T13:53:13Z-
dc.date.issued2016-
dc.identifier.citationInternational Journal of Parallel Programming, pp. 1 - 20, (2016)en_US
dc.identifier.issn0885-7458-
dc.identifier.urihttp://bura.brunel.ac.uk/handle/2438/13465-
dc.description.abstractArtificial neural network is proved to be an effective algorithm for dealing with recognition, regression and classification tasks. At present a number of neural network implementations have been developed, for example Hamming network, Grossberg network, Hopfield network and so on. Among these implementations, back propagation neural network (BPNN) has become the most popular one due to its sensational function approximation and generalization abilities. However, in the current big data researches, BPNN, as a both data intensive and computational intensive algorithm, its efficiency has been significantly impacted. Therefore, this paper presents a parallel BPNN algorithm based on data separation in three distributed computing environments including Hadoop, HaLoop and Spark. Moreover to improve the algorithm performance in terms of accuracy, ensemble techniques have been employed. The algorithm is firstly evaluated in a small-scale cluster. And then it is further evaluated in a commercial cloud computing environment. The experimental results indicate that the proposed algorithm can improve the efficiency of BPNN with guaranteeing its accuracy.en_US
dc.description.sponsorshipThe authors would like to appreciate the support from the National Natural Science Foundation of China (No. 51437003) and the National Basic Research Program (973) of China under Grant 2014CB340404.en_US
dc.format.extent1 - 20-
dc.language.isoenen_US
dc.publisherSpringer Verlagen_US
dc.subjectNeural networken_US
dc.subjectMapReduceen_US
dc.subjectHadoopen_US
dc.subjectHaLoopen_US
dc.subjectSparken_US
dc.subjectEnsemble techniqueen_US
dc.titleThe Parallelization of Back Propagation Neural Network in MapReduce and Sparken_US
dc.typeArticleen_US
dc.identifier.doihttp://dx.doi.org/10.1007/s10766-016-0401-1-
dc.relation.isPartOfInternational Journal of Parallel Programming-
pubs.publication-statusAccepted-
Appears in Collections:Dept of Electronic and Computer Engineering Research Papers

Files in This Item:
File Description SizeFormat 
Fulltext.docx3.22 MBUnknownView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.