Artificial neural network for modeling the size of silver nanoparticles’ prepared in montmorillonite/starch bionanocomposites

Abstract

In this study, artificial neural network (ANN) was employed to develop an approach for the evaluation of size of silver nanoparticles (Ag-NPs) in montmorillonite/starch bionanocomposites (MMT/Stc-BNCs). A multi-layer feed forward ANN was applied to correlate the output as size of Ag-NPs, with the four inputs include of AgNO3 concentration, temperature of reaction, weight percentage of starch, and gram of MMT. The results of proposed methodology were compared for its predictive capabilities in terms of the coefficient of determination (R2) and mean square error (MSE) based on the validation data set. The model finding revealed that AgNO3 concentration content has significant effect on size of Ag-NPs (about 37.90 %). Also other linear model, multiple linear regression models verified this result. The results demonstrated that the ANN model prediction and experimental data are quite match and the model can be employed with confidence for prediction of size of Ag-NPs in the composites and bionanocomposites compounds.