Artificial neural network (ANN) model for prediction and optimization of bacoside A content in Bacopa monnieri: a statistical approach and experimental validation

Abstract

The current research aims to elucidate the drug environment Interactions and predict a suitable growing condition for Bacopa monnieri (L.) Wettst with maximum bacoside A content using an artificial neural network (ANN) model. An experimental dataset was generated by collecting B. monnieri wild accessions from 81 locations across different geographical regions of eastern Indian (Odisha and West Bengal). The obtained ANN results specified that a single hidden layer containing 11 neurons namely 13-11-1 structure of multilayer perceptron (MLP) neural network showed the highest prediction accuracy for bacoside A content. The developed ANN model exhibited a better predictive potential for the training dataset with a coefficient of determination (R2), a root mean square error (RMSE), and a mean absolute percentage error (MAPE) of 0.90, 0.16, and 7.76%, respectively. Further, the results on sensitivity analysis showed nitrogen levels and altitude to have the highest impact on bacoside A content. Additionally, the ANN model exhibited a prediction accuracy of 93.60% for bacoside A content when tested at a new geographical location. The results of this study thus indicates that ANN model can be used for predicting and optimizing bacoside A content in B. monnieri (L.) at a specific location.