Modeling and Optimization of Artificial Neural Network and Response Surface Methodology in Ultra-high-Pressure Extraction of Artemisia argyi Levl. et Vant and its antifungal activity

Artificial neural network (ANN) and response surface methodology (RSM) are the two preferred methods for optimization of extracting bio-active components from traditional Chinese medicine. In this work, four flavonoids and polyphenols extraction of Artemisia argyi by using ultra-high-pressure extraction (UHPE) has been investigated. Studies were conducted to obtain suitable extraction conditions for quercetin, luteolin, apigenin, and kaempferol, which were identified and quantified by high-performance liquid chromatography (HPLC). Moreover, process optimization were carried out by using both ANN and RSM methods to predict the best operating conditions, which resulted in the maximum extraction yield. The antifungal activity of plants extracts against several dermatophytes was also studied using diameters of inhibition zones and minimum inhibitory concentration procedures. The results revealed that, among all the tested methods, UHPE exhibited good extraction effectiveness in terms of higher extraction yields and also with higher antifungal activities. In addition, root-mean-square error and relative error methods were utilized to compare the predicted values of the extraction yield obtained from both models with the experimental data. The results of the comparison reveal the superiority of ANN model compared with RSM model.