Antioxidant increase by response surface optimization and Bayesian neural network modelling of pumpkin (Cucurbita moschata Duch) freezing

Abstract

Pumpkin antioxidants have been found to benefit diabetics. This current study was attempted to optimize slow freezing treatment for a pumpkin to obtain maximum antioxidant gain using response surface methodology (RSM) and Bayesian regularized neural network (BRANN) approaches. A central composite design was used to generate the freezing experiment and to examine response change as a function of temperature and freezing time. Feedforward neural networks with a 2-15-1 structure were developed and trained using the Bayesian regularization algorithm. The results showed that the freezing data were well fitted to quadratic models generating R2 for total phenolic compounds (TPC), flavonoid of 0.850 and 0.857 respectively. The RSM optimized freezing of -20oC for 9 hrs were well confirmed to produce an increase in TPC and flavonoid by 54.44% and 60.4% respectively. The BRANN performances were found to be similar to that of RSM. While overfitting was mitigated during the supervised training, the BRANN model served excellent predictive and confirmatory tool for the optimization. In conclusion, slow freezing at -20oC for 9 hrs significantly increases TPC and flavonoid of pumpkin. This novel process may be adopted to provide healthier pumpkins food products for targeted consumers.