Machine learning-based prediction of total phenolic and flavonoid in horticultural products

Abstract The purpose of this study was to predict the total phenolic content (TPC) and flavonoid (TFC) in several horticultural commodities using near-infrared spectroscopy (NIRS) combined with machine learning. Although models are typically developed for a single product, expanding coverage model can improve efficiency. In study, 700 samples were used, including varieties shallot, cayenne pepper, red chili. results showed that TPC yielded R 2 cal, root mean squares error calibration set, pred, prediction ratio performance deviation values 0.79, 123.33, 0.78, 124.20, 2.13, respectively. Meanwhile, TFC produced 0.71, 44.52, 0.72, 42.10, 1.87, wavelengths 912, 939, 942 nm closely related compounds flavonoids. accuracy satisfactory results. Therefore, application NIRS learning products has high potential replacing conventional laboratory analysis TFC.