Application of Artificial Neural Network (ANN) in Ultrasound-Assisted Extraction of Bioactive Compounds

Abstract

Artificial neural network (ANN) is regarded as a promising tool among the recent trends of modeling methodologies for the nonlinear mapping of multiple variables. In the case of the ultrasound-assisted extraction (UAE) process, the majority of the response-based predictive models are administered with nonlinear modeling approaches. Numerical models provide restricted extension and abilities to show such nonlinear prescient conditions. Due to this, ANN modeling gets considerable scope for effectively mapping the variables. In addition, the essential of no prior specific, in the event that there ought to emerge an event of fitting the data or information, make ANN the most popular and compelling one for modeling the extraction process. This paper provides the basics of principles and applications of ANNs in process modeling and optimization of different UAE-based extraction perspectives. In addition, the prevalence of the UAE process in diverging from other extraction methods is highlighted. Further, the impact of various process factors like ultrasound intensity, exposure time, and temperature during the UAE interaction and their prescient modeling approaches for efficient controlling of the responses are detailed. Hence, this review would be useful for modeling and optimization of thermal and non-thermal-based extraction processes, which would assist the food processing industries to improve food quality.