Predicting the Removal Amount of SCN- by TiO2 NPs Using ANN Methods

Using Novel Artificial Neural Network Methods in Removing Aqueous Thiocyanate Anions by Titanium Dioxide Nanoparticles
Autor: Rashin Andayesh
CHF 54.40
ISBN: 978-620-2-51407-1
Einband: Kartonierter Einband (Kt)
Verfügbarkeit: Folgt in ca. 10 Arbeitstagen
+ -

In this work, the adsorbent method is performed using arti¿cial neural network (ANN) modeling. The adsorbent is applied for removal of Thiocyanate in water samples using Titanium Dioxide (TiO2) nanoparticles as effective sorbent. Prediction amount of Thiocyanate removal was investigated with novel algorithms of neural network. For this purpose, six parameters were chosen as training input data of neural network functions including pH, time of stirring, the mass of adsorbent, volume of TiO2, volume of Fe (III), and volume of buffer. Performances of the suggested methods were examined using statistical parameters and found that it is an ef¿cient, effective modeling satisfactory outputs. The radial basis function (RBF) and Levenberg-Marquardt (LM) algorithm could accurately predict the experimental data with correlation coefficient of 0.997939 and 0.99931, respectively. The Pearson's Chi¿square measure was found to be 29.00 for most variables, indicating that these variables are likely to be dependent in some way.

In this work, the adsorbent method is performed using arti¿cial neural network (ANN) modeling. The adsorbent is applied for removal of Thiocyanate in water samples using Titanium Dioxide (TiO2) nanoparticles as effective sorbent. Prediction amount of Thiocyanate removal was investigated with novel algorithms of neural network. For this purpose, six parameters were chosen as training input data of neural network functions including pH, time of stirring, the mass of adsorbent, volume of TiO2, volume of Fe (III), and volume of buffer. Performances of the suggested methods were examined using statistical parameters and found that it is an ef¿cient, effective modeling satisfactory outputs. The radial basis function (RBF) and Levenberg-Marquardt (LM) algorithm could accurately predict the experimental data with correlation coefficient of 0.997939 and 0.99931, respectively. The Pearson's Chi¿square measure was found to be 29.00 for most variables, indicating that these variables are likely to be dependent in some way.

Autor Rashin Andayesh
Verlag LAP Lambert Academic Publishing
Einband Kartonierter Einband (Kt)
Erscheinungsjahr 2020
Seitenangabe 52 S.
Ausgabekennzeichen Englisch
Abbildungen Paperback
Masse H22.0 cm x B15.0 cm x D0.4 cm 96 g

Weitere Titel von Rashin Andayesh