Reliable Identification of Oolong Tea Species: Nondestructive Testing Classification Based on Fluorescence Hyperspectral Technology and Machine Learning

A rapid and nondestructive tea classification method is of great significance in today’s research. This study uses fluorescence hyperspectral technology machine learning to distinguish Oolong by analyzing the spectral features wavelength ranging from 475 1100 nm. The data are preprocessed multivariate scattering correction (MSC) standard normal variable (SNV), which can effectively reduce impact baseline drift tilt. Then principal component analysis (PCA) t-distribution random neighborhood embedding (t-SNE) adopted for feature dimensionality reduction visual display. Random Forest-Recursive Feature Elimination (RF-RFE) used selection. Decision Tree (DT), Forest Classification (RFC), K-Nearest Neighbor (KNN) Support Vector Machine (SVM) establish model. results show that MSC-RF-RFE-SVM best model accuracy training set test 100% 98.73%, respectively. It be concluded feasible classify tea.