Ultrasonic–enzymatic pretreatments enhance germination of brown rice. However, structural–metabolic interactions and process optimization require further investigation. This study systematically assessed the effects of ultrasonic time (UT), cellulase concentration (CC), and liquid-to-solid ratio (LS) on γ-aminobutyric acid (GABA), total phenolic content (TPC), total flavonoid content (TFC), antioxidant activity (2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging and ferric reducing antioxidant power (FRAP) assays), and optimal cooking time (OCT) using a Box–Behnken design. Response surface methodology (RSM) and artificial neural network (ANN) models predicted outcomes. Genetic algorithm (GA) and particle swarm optimization (PSO) facilitated multiobjective optimization. The ANN model demonstrated higher predictive accuracy, with greater coefficients of determination and lower prediction errors than RSM. The optimized process increased GABA content, enhanced antioxidant properties, and shortened cooking time. Scanning electron microscopy (SEM) showed that the optimized samples exhibited greater particle breakage, layer separation, and pores, suggesting cavitation-assisted enzymatic hydrolysis. These changes facilitate the movement of substances and the release of beneficial compounds. In summary, ultrasonic-enzymatic pretreatment with ANN-based optimization is an effective and scalable method for producing functional germinated brown rice (GBR) with improved nutritional and technological properties.
Chamsai et al. (Mon,) studied this question.