Multi-objective optimization of process parameters of a hybrid IR-vibro fluidized bed dryer using RSM-DF and RSM-GA for recovery of bioactive compounds from pumpkin seeds

Pumpkin seeds are generally discarded as a waste but they comprise an excellent source of proteins, oil, and bioactive compounds. For valorization of pumpin seeds, the selection of drying technique and statistical tools is important as bioactive compound alters with drying method. Therefore, the current study investigated the effect of drying parameters of infrared-assisted vibro-fluidized bed dryer on bioactive compounds and oil yield of pumpkin seeds. Central composite rotatable design (CCRD) was used with 4 drying parameters viz; temperature (35–65 °C), air velocity (0.5–2.5 m/s), vibration intensity (0.5–4.5), and infrared power (80–160 W). The effect of drying parameters on total phenol content (TPC), total flavonoid content (TFC), 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity, and total oil yield was determined. Analysis of variance of RSM proposed mathematical models to investigate the significance of factors and their interactions on the responses. Predictive modeling was performed by response surface methodology (RSM) and artificial neural network (ANN). The statistical indicators analysis showed the ANN model predicted results closer to experimental results than RSM proposed mathematical models. Optimization was carried out using RSM with desirability function (RSM-DF) and RSM with genetic algorithm (RSM-GA) approaches. The optimal condition predicted by RSM-DF was as follows: 64.99 °C of temperature, 1.60 m/s of air velocity, 1.97 of vibration intensity, and 159.99 W of infrared power were obtained for maximum recovery of TPC (9.46 mg GAE/g dw), TFC (5.63 mg QE/ g dw), DPPH scavenging activity (96.78%), and oil yield (49.02%). RSM-DF optimization predicted results closer to the experimental results than the RSM-GA approach. Graphical abstract