Optimization of ultrasound‐assisted extraction of ascorbic acid, protein and total antioxidants from cashew apple bagasse using artificial neural network‐genetic algorithm and response surface methodology

The study explored the effect of ultrasonication to extract ascorbic acid, protein, and total antioxidants from cashew apple bagasse. The process was designed and optimized using three independent variables and the response values were predicted individually using both response surface methodology (RSM) and artificial neural network-genetic algorithm (ANN-GA). The ascorbic acid, antioxidant activity and protein content extracted using RSM were 6.61 mg/g, 90.98% and 338.48 mg/g respectively whereas using ANN-GA were 8.81 mg/g, 94.97% and 369.10 mg/g respectively at individual optimized conditions. These yields were comparatively higher in ANN-GA than RSM. Also, the ascorbic acid, antioxidant activity and protein content were predicted using ANN-GA around 8, 2 and 8 times higher than those of conventional solvent extraction. Further, the coefficient of determination (R2) for every response was higher and other statistical parameters were lower in ANN-GA. Thus, the ANN-GA is superior to the RSM in optimizing the extraction. Practical applications The cashew apple byproducts are being underutilized by food process industries discarding as waste. Due to this, these industries are facing environmental pollution problems. Besides, the byproducts are nutritious as it has a significant amount of protein, vitamins as well as antioxidants. The ultrasound process provides the extraction of those bioactive compounds in the least usage of solvent, time and temperature. Hence, this research represents the optimum conditions of extraction of bioactive compounds from cashew apple bagasse using this green technology; it will be favorable for industries to develop value-added products by dissipating waste disposal.