Premium
Optimization of ultrasound‐assisted extraction of phenolic compounds from grapefruit ( Citrus paradisi Macf.) leaves via D‐optimal design and artificial neural network design with categorical and quantitative variables
Author(s) -
Ciğeroğlu Zeynep,
Aras Ömür,
Pinto Carlos A,
Bayramoglu Mahmut,
Kırbaşlar Ş İsmail,
Lorenzo José M,
Barba Francisco J,
Saraiva Jorge A,
Şahin Selin
Publication year - 2018
Publication title -
journal of the science of food and agriculture
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.782
H-Index - 142
eISSN - 1097-0010
pISSN - 0022-5142
DOI - 10.1002/jsfa.8987
Subject(s) - extraction (chemistry) , citrus paradisi , chromatography , response surface methodology , gallic acid , ultrasound energy , chemistry , artificial neural network , materials science , ultrasound , mathematics , analytical chemistry (journal) , botany , artificial intelligence , computer science , organic chemistry , antioxidant , physics , rutaceae , acoustics , biology
BACKGROUND The extraction of phenolic compounds from grapefruit leaves assisted by ultrasound‐assisted extraction (UAE) was optimized using response surface methodology (RSM) by means of D‐optimal experimental design and artificial neural network (ANN). For this purpose, five numerical factors were selected: ethanol concentration (0–50%), extraction time (15–60 min), extraction temperature (25–50 °C), solid:liquid ratio (50–100 g L −1 ) and calorimetric energy density of ultrasound (0.25–0.50 kW L −1 ), whereas ultrasound probe horn diameter (13 or 19 mm) was chosen as categorical factor. RESULTS The optimized experimental conditions yielded by RSM were: 10.80% for ethanol concentration; 58.52 min for extraction time; 30.37 °C for extraction temperature; 52.33 g L −1 for solid:liquid ratio; 0.457 kW L −1 for ultrasonic power density, with thick probe type. Under these conditions total phenolics content was found to be 19.04 mg gallic acid equivalents g −1 dried leaf. CONCLUSION The same dataset was used to train multilayer feed‐forward networks using different approaches via MATLAB, with ANN exhibiting superior performance to RSM (differences included categorical factor in one model and higher regression coefficients), while close values were obtained for the extraction variables under study, except for ethanol concentration and extraction time. © 2018 Society of Chemical Industry