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

Date

2014-01-01

Author

Kockan, Umit
Ozturk, Fahrettin
Evis, Zafer

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

304
views

0
downloads

In this study, hexagonal lattice parameters (a and c) and unit-cell volumes of non-stoichiometric apatites of M-10(TO4)(6)X-2 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.

Subject Keywords

Artificial neural networks, Crystal structure, Hydroxyapatite, Multilayer-perceptron network

URI

https://hdl.handle.net/11511/54827

Journal

MATERIALI IN TEHNOLOGIJE

Collections

Department of Engineering Sciences, Article

Suggestions

OpenMETU
Core

Prediction of hexagonal lattice parameters of various apatites by artificial neural networks Kockan, Umit; Evis, Zafer (International Union of Crystallography (IUCr), 2010-08-01) In this study, the hexagonal lattice parameters of apatite compounds, M-10(TO4)(6)X-2, where M is Na+, Ca2+, Ba2+, Cd2+, Pb2+, Sr2+, Mn2+, Zn2+, Eu2+, Nd3+, La3+ or Y3+, T is As+5, Cr+5, P5+, V5+ or Si+4, and X is F-, Cl-, OH- or Br-, were predicted from their ionic radii by artificial neural networks. A multilayer perceptron network was used for training and the best results were obtained with a Bayesian regularization method. Four neurons were used in the hidden layer, utilizing a tangent sigmoid activati...
Theoretical investigation of quercetin and its radical isomers Erkoc, E; Erkoc, F; Keskin, N (Elsevier BV, 2003-08-01) The structural and electronic properties of quercetin and its five radical isomers have been investigated theoretically by performing semi-empirical molecular orbital theory calculations. The geometry of the systems have been optimized and the electronic properties of the systems considered have been calculated by semi-empirical self-consistend-field molecular orbital theory at the level AM1 within UHF formalism in their ground state. Conclusions have been drawn by comparing with experimental results.
Energy preserving integration of bi-Hamiltonian partial differential equations Karasözen, Bülent (2013-12-01) The energy preserving average vector field (AVF) integrator is applied to evolutionary partial differential equations (PDEs) in bi-Hamiltonian form with nonconstant Poisson structures. Numerical results for the Korteweg de Vries (KdV) equation and for the Ito type coupled KdV equation confirm the long term preservation of the Hamiltonians and Casimir integrals, which is essential in simulating waves and solitons. Dispersive properties of the AVF integrator are investigated for the linearized equations to ex...
Estimation of thermally stimulated current in as grown TlGaSeS layered single crystals by multilayered perceptron neural network Kucuk, Ilker; Yildirim, Tacettin; Hasanlı, Nızamı; Ozkan, Husnu (Elsevier BV, 2011-6) This paper presents an artificial neural network approach to compute thermally stimulated current (TSC) in as-grown T1GaSeS layered single crystals. The experimental data have been obtained from TSC measurements. The network has been trained by a genetic algorithm (GA). The results confirmed that the proposed model could provide an accurate computation of the TSC.
Estimation of protein secondary structure from FTIR spectra using neural networks Severcan, M; Severcan, Feride; Haris, PI (Elsevier BV, 2001-05-30) Secondary structure of proteins have been predicted using neural networks (NN) from their Fourier transform infrared spectra. Leave-one-out approach has been used to demonstrate the applicability of the method. A form of cross-validation is used to train NN to prevent the overfitting problem. Multiple neural network outputs are averaged to reduce the variance of predictions. The networks realized have been tested and rms errors of 7.7% for alpha -helix, 6.4% for beta -sheet and 4.8% for turns have been achi...

Citation Formats

U. Kockan, F. Ozturk, and Z. Evis, “Artificial-neural-network prediction of hexagonal lattice parameters for non-stoichiometric apatites,” MATERIALI IN TEHNOLOGIJE, pp. 73–79, 2014, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/54827.