Neural identification of dynamic systems on FPGA with improved PSO learning

dc.authorid0000-0003-0569-098X
dc.contributor.authorCavuslu, Mehmet Ali
dc.contributor.authorKarakuzu, Cihan
dc.contributor.authorKarakaya, Fuat
dc.date.accessioned2019-08-01T13:38:39Z
dc.date.available2019-08-01T13:38:39Z
dc.date.issued2012
dc.departmentNiğde ÖHÜ
dc.description.abstractThis work introduces hardware implementation of artificial neural networks (ANNs) with learning ability on field programmable gate array (FPGA) for dynamic system identification. The learning phase is accomplished by using the improved particle swarm optimization (PSO). The improved PSO is obtained by modifying the velocity update function. Adding an extra term to the velocity update function reduced the possibility of stucking in a local minimum. The results indicates that ANN, trained using improved PSO algorithm, converges faster and produces more accurate results with a little extra hardware utilization cost. (C) 2012 Elsevier B.V. All rights reserved.
dc.identifier.doi10.1016/j.asoc.2012.03.022
dc.identifier.endpage2718
dc.identifier.issn1568-4946
dc.identifier.issn1872-9681
dc.identifier.issue9
dc.identifier.scopus2-s2.0-84863441795
dc.identifier.scopusqualityQ1
dc.identifier.startpage2707
dc.identifier.urihttps://dx.doi.org/10.1016/j.asoc.2012.03.022
dc.identifier.urihttps://hdl.handle.net/11480/4551
dc.identifier.volume12
dc.identifier.wosWOS:000306107900001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthor[0-Belirlenecek]
dc.language.isoen
dc.publisherELSEVIER SCIENCE BV
dc.relation.ispartofAPPLIED SOFT COMPUTING
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectArtificial neural networks (ANN)
dc.subjectParticle swarm optimization (PSO)
dc.subjectFPGA
dc.subjectSystem identification
dc.titleNeural identification of dynamic systems on FPGA with improved PSO learning
dc.typeArticle

Dosyalar