Artificial intelligence proficient systems with neural network machine learning algorithms in nanoparticle size prediction application

Abstract

Artificial Intelligence (AI) indicates the usage of a computer to model intellectual performance with least human
intercession. Modern progress in nanoparticle technology has facilitated the preparation of nanoparticle with a distinct size
which in turn has expedited significant improvements in the field of nanomedicine. Predicting this characteristic would
leap numerous preceding studies customarily needed to optimize formulations. This paper intends to develop Artificial
Neural Network (ANN) for predicting the size of the silver nanoparticle (AgNP) with four input variables. Different
algorithms were applied to train ANNs with several numbers of hidden layers, nodes and transfer functions by arbitrary
selection. The estimation performance of the different model was evaluated, on training, validation and testing data sets in
terms of Regression (R) and Mean Square Error (MSE). The optimized prediction model was proficient in predicting
nanoparticle size for a broad range of conditions with better R and MSE values. The relative impact of each input variables
on AgNP size was also determined. Results from this study contribute to design an effective green approach for obtaining
nanoparticles, while the limited received materials are employed, and the merest size of nanoparticles will be achieved.