Show simple item record

dc.contributor.authorMilovanović, Miroslav
dc.contributor.authorAntić, Dragan
dc.contributor.authorMilojković, Marko
dc.contributor.authorNikolić, Saša S.
dc.contributor.authorSpasić, Miodrag
dc.contributor.authorPerić, Staniša
dc.date.accessioned2017-11-25T07:20:43Z
dc.date.available2017-11-25T07:20:43Z
dc.date.copyright2017/7/2
dc.date.issued2017
dc.identifier.issn0022-0434
dc.identifier.otherds_139_04_041006.pdf
dc.identifier.urihttp://138.201.223.254:8080/yetl1/handle/yetl/4236612
dc.description.abstractThis paper presents a new type of endocrine neural network (ENN). ENN utilizes artificial glands which enable the network to be adaptive to external disturbances. Sensitivity is controlled by the hormone decay rate and the value of the sensitivity parameter. The network presented in this paper is improved by making the sensitivity parameter self-tuning and implementing orthogonal activation functions inside the network structure. Automatic tuning is performed on the basis of the biological principle of postsynaptic potentials by implementing inhibitory and excitatory glands inside the standard backpropagation learning algorithm of developed orthogonal ENN. These additional network functionalities enable extra sensitivity to external conditions and an additional network feature of activation sharpening. The network was tested on real-time series of experimental data with a purpose to forecast exchange rate of the three widely used international currencies.
dc.publisherThe American Society of Mechanical Engineers (ASME)
dc.titleTime Series Forecasting With Orthogonal Endocrine Neural Network Based on Postsynaptic Potentials
dc.typeJournal Paper
dc.journal.volume139
dc.journal.issue4
dc.journal.titleJournal of Dynamic Systems, Measurement, and Control
dc.identifier.doi10.1115/1.4035090
dc.journal.fristpage41006
dc.journal.lastpage041006-9
dc.treeJournal of Dynamic Systems, Measurement, and Control:;2017:;volume( 139 ):;issue: 004
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record