Artificial neural network in optimization of bioactive compound extraction: recent trends and performance comparison...

Area of Science:

• Agricultural Chemistry
• Biotechnology
• Food Science

Background:

• Plant-derived bioactive compounds possess significant health benefits.
• Extraction of these compounds is complex, time-consuming, and sensitive to experimental conditions.
• Predictive modeling can streamline extraction processes, reducing labor and environmental impact.

Purpose of the Study:

• To review current trends in applying Artificial Neural Networks (ANN) for optimizing bioactive compound extraction.
• To compare the performance of ANN against Response Surface Methodology (RSM) in modeling and optimizing extraction processes.
• To highlight the potential of ANN for industrial-scale applications in natural product chemistry.

Main Methods:

• Literature review focusing on ANN and RSM applications in bioactive compound extraction.
• Comparative analysis of ANN and RSM performance metrics from existing studies.
• Evaluation of prediction accuracy and efficiency of both methodologies.

Main Results:

• Artificial Neural Networks (ANN) demonstrate superior efficiency and accuracy over Response Surface Methodology (RSM) in optimizing and modeling bioactive compound extraction.
• ANN facilitates extensive predictions with high precision, outperforming traditional methods.
• Studies indicate ANN's effectiveness across various plant matrices, including herbs, fruits, and vegetables.

Conclusions:

• ANN presents a more advanced and effective tool for optimizing bioactive compound extraction compared to RSM.
• The findings support the broader adoption of ANN in natural product research and development.
• Future research should explore ANN's application in industrial-scale extraction optimization.