The Influence of Different Ultrasonication Parameters on Physicochemical Properties and Secoiridoid Compositions of Olive Extracts: A Mathematical Approach Using Artificial Neural Network (ANN) and Response Surface Methodology (RSM)

The effects of different ultrasound parameters on some physicochemical properties and secoiridoid compositions of olive extracts were investigated. For this purpose, pH, acidity, photometric color index (PCI), total phenolic content, and secoiridoid phenolic compound composition analyses were carried out in olive extracts obtained by ultrasonic extraction at different operating parameters such as temperature, ultrasonic power, and extraction time. The data obtained were modeled and optimized by using the Box–Behnken design of RSM. Then, the comparison of experimental data versus mathematical estimations was performed by using both ANN and RSM. The results revealed that the pH values of the samples ranged between 4.94 and 5.23, and the average acidity value was 0.551 (% oleic acid). PCI values varied between 20.46 and 83.70. Total phenolic content ranged between 0.13 and 0.42 mg GAE (gallic acid equivalent)/g extract. Regarding secoiridoid phenolics, the ranges for oleuropein, oleacein, and oleocanthal were 5.33–34.39 ng/μL, 0.76–6.03 ng/μL, and 3.77–14.16 ng/μL, respectively. The optimized temperature, time, and ultrasonic power were 43.13 °C, 15 min, and 100% (of the maximum ultrasonic power of 90 W), respectively. The overall desirability of the process was obtained as 95.51%. RSM and ANN were both favorable in the estimation of experimental data with slight differences.