Rapid Identification of Chrysanthemum morifolium cv. Chuju Grades by Excitation-Emission Matrix Fluorescence Spectroscopy Combined with Chemometric Methods

Abstract

Chrysanthemum morifolium Ramat cv. “Chuju” (Chuju) requires precise quality grading to ensure effective quality control. This study developed a method for rapid and precise classification tof Chuju’s quality grades by combining excitation-emission matrix (EEM) fluorescence spectroscopy with chemometric analysis. First, EEM fluorescence spectra of Chuju samples were characterized analyzed using parallel factor analysis (PARAFAC) to extract key fluorescence features (such as flavonoids and amino acids). Next, we applied several classification algorithms to construct discriminant models, including k-nearest neighbors (kNN), N-way partial least squares discriminant analysis (N-PLS-DA), and unfolded partial least squares discriminant analysis (U-PLS-DA). Among these, U-PLS-DA demonstrated the most robust performance, achieving a 100% correct classification rate (CCR) for both training and test datasets. Additionally, the classification metrics, including accuracy (ACC), sensitivity (SEN), specificity (SPE), and precision (PRE), all reached 100%. These findings indicate that the proposed method effectively distinguishes between different quality grades of Chuju, providing a reliable and reproducible tool for quality evaluation.