Journal ID : AMA-01-08-2022-11578
[This article belongs to Volume - 53, Issue - 08]
Total View : 354

Title : Prediction of Artificial Neural Network (ANN) in the optimization of quality attributes in heat pump-assisted dehumidified air-dried (HPD) Moringa oleifera by Principal Component Analysis (PCA)

Abstract :

Moringa oleifera (M. Oleifera) is a storehouse of essential nutrients like protein, fibre, vitamins, minerals, and phytochemicals. The moringa leaves can be consumed in cooked form or supplemented as a fine powder in processed food products. The conventional drying process takes more time and energy and that will affect the organoleptic property, product quality and safety. Hence, the study aims to apply advanced techniques like heat pump-assisted dehumidified air drying (HPD), running effectively and efficiently to achieve higher retention of nutritional properties. To develop a predictive model Artificial Neural Network (ANN) was chosen as a tool for drying at temperature and drying time varied at three levels. For this, The output variables of crude protein (%), crude fibre (%), and colour values (L*, a* and b*) as an input of drying temperature (45 to 65 °C) and drying time (45 to 75 minutes). Physicochemical and drying characteristics of moringa leaf were highly found at 55⁰C with special reference to maximum powder recovery, excellent flowability and better retention of nutrients like crude protein (29.64 %) and crude fibre (16.37 %). The values of coefficient of determination (R2 - 0.969 to 0.998), Root mean square error (RMSE - 0.02685 to 0.13541), Mean Absolute Error (MAE - 0.00912 to 0.0946) and Mean Absolute Percentage Error (MAPE - 0.04768 to 0.34129) were used to determine the potential and sensitivity analysis of training function and hidden layer for each response variable for their prediction with the highest accuracy.

Full article