Artificial-neural-network prediction of hexagonal lattice parameters for non-stoichiometric apatites

Basit Öğe Kaydı
dc.contributor.authorKockan, Umit
dc.contributor.authorOzturk, Fahrettin
dc.contributor.authorEvis, Zafer
dc.date.accessioned2024-11-07T10:40:01Z
dc.date.available2024-11-07T10:40:01Z
dc.date.issued2014
dc.departmentNiğde Ömer Halisdemir Üniversitesi
dc.description.abstractIn this study, hexagonal lattice parameters (a and c) and unit-cell volumes of non-stoichiometric apatites of M10(TO4)6X2 are predicted from their ionic radii with artificial neural networks. A multilayer-perceptron network is used for training. The results indicate that the Bayesian regularization method with four neurons in the hidden layer with a tansig activation function and one neuron in the output layer with a purelin function gives the best results. It is found that the errors for the predicted data of the lattice parameters of a and c are less than 1 % and 2 %, respectively. On the other hand, about 3 % errors were encountered for both lattice parameters of the non-stoichiometric apatites with exact formulas in the presence of the T-site ions that are not used for training the artificial neural network.
dc.identifier.endpage79
dc.identifier.issn1580-3414
dc.identifier.issue1
dc.identifier.scopus2-s2.0-84894083527
dc.identifier.scopusqualityQ3
dc.identifier.startpage73
dc.identifier.urihttps://hdl.handle.net/11480/11365
dc.identifier.volume48
dc.indekslendigikaynakScopus
dc.language.isoen
dc.relation.ispartofMateriali in Tehnologije
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241106
dc.subjectArtificial neural networks
dc.subjectCrystal structure
dc.subjectHydroxyapatite
dc.subjectMultilayer-perceptron network
dc.titleArtificial-neural-network prediction of hexagonal lattice parameters for non-stoichiometric apatites
dc.typeArticle

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu