Artificial intelligence prediction the desirable moisture content of dried oyster mushroom (Pleurotus sajor-caju) for enhancing the cellulase-assisted extraction efficiency

Abstract

Oyster mushroom (Pleurotus sajor-caju) presents high nutritional values and substantial potential as a raw material widely utilized in food production, especially its extract form. This study was aimed at investigating the effect of different drying methods (conventional dryer, sun drying, and solar drying) and moisture content of dried mushrooms on the cellulase-assisted extraction efficiency. The change in moisture content (MC) was predicted by an artificial neural network (ANN) as an intelligent model. The ANN model with 10 nodes successfully and accurately forecasted the change in MC during drying using different techniques. It was easily predicted the time for achieving the desirable MC (10–20 %) for the extraction experiment by applying this model. The obtained results also indicated that the highest nutrient content in the extracted solution from dried mushrooms was achieved when the material had an MC of 15 % and was dried using a solar drying system. Under these conditions, the extract's total soluble solid, protein, saccharose, phenolic, flavonoid, and β-glucan contents were 2.20 %, 21.78 %, 8.16 %, 5.74 g TAE/100 g, 0.73 g QE/100 g, and 2.25 %, respectively. High protein content, as well as the antioxidant compounds in the extract, could be a promising source for developing nutraceuticals and healthy food.

Keywords

• Drying
• Artificial intelligence
• Cellulase-assisted extraction
• Pleurotus sajor-Caju