A rice classification method for the fast and non-destructive differentiation of different varieties is significant in research at present. In this study, fluorescence hyperspectral technology combined with machine learning techniques was used to distinguish five rice varieties by analyzing the fluorescence hyperspectral features of Thai jasmine rice and four rice varieties with a similar appearance to Thai jasmine rice in the wavelength range of 475–1000 nm. The fluorescence hyperspectral data were preprocessed by a first-order derivative (FD) to reduce the background and baseline drift effects of the rice samples. Then, a principal component analysis (PCA) and t-distributed stochastic neighborhood embedding (t-SNE) were used for feature reduction and 3D visualization display. A partial least squares discriminant analysis (PLS-DA), BP neural network (BP), and random forest (RF) were used to build the rice classification models. The RF classification model parameters were optimized using the gray wolf algorithm (GWO). The results show that FD-t-SNE-GWO-RF is the best model for rice classification, with accuracy values of 99.8% and 95.3% for the training and test sets, respectively. The fluorescence hyperspectral technique combined with machine learning is feasible for classifying rice varieties.

The dry matter test of mango has important practical significance for the quality classification of mango. Most of the common fruit and vegetable quality nondestructive testing methods based on fluorescence hyperspectral imaging technology use a single algorithm in algorithms such as Uninformative Variable Elimination (UVE), Random Frog (RF), Competitive Adaptive Reweighted Sampling (CARS) and Continuous Projection Algorithm (SPA) to extract feature spectral variables, and the use of these algorithms alone can easily lead to the insufficient stability of prediction results. In this regard, a nondestructive detection method for the dry matter of mango based on hyperspectral fluorescence imaging technology was carried out. Taking the ‘Keitt’ mango as the research object, the mango samples were numbered in sequence, and their fluorescence hyperspectral images in the wavelength range of 350–1100 nm were collected, and the average spectrum of the region of interest was used as the effective spectral information of the sample. Select SPXY algorithm to divide samples into a calibration set and prediction set, and select Orthogonal Signal Correction (OSC) as preprocessing method. For the preprocessed spectra, the primary dimensionality reduction (UVE, SPA, RF, CARS), the primary combined dimensionality reduction (UVE + RF, CARS + RF, CARS + SPA), and the secondary combined dimensionality reduction algorithm ((CARS + SPA)-SPA, (UVE + RF)-SPA) and other 12 algorithms were used to extract feature variables. Separately constructed predictive models for predicting the dry matter of mangoes, namely, Support Vector Regression (SVR), Extreme Learning Machine (ELM), and Back Propagation Neural Network (BPNN) model, were used; The results show that (CARS + RF)-SPA-BPNN has the best prediction performance for mango dry matter, its correlation coefficients were R_C² = 0.9710, R_P² = 0.9658, RMSEC = 0.1418, RMSEP = 0.1526, this method provides a reliable theoretical basis and technical support for the non-destructive detection, and precise and intelligent development of mango dry matter detection.

Black tea has a long history in China, but in export trade, pesticide residues often exceed the standard. To obtain a rapid, accurate, and non-destructive identification method of pesticide residues on black tea, the fluorescence hyperspectral data of dry black tea sprayed with distilled water and six pesticides were collected in this study. The spectra were preprocessed by multiplicative scatter correction (MSC) and standard normal variate (SNV). Then the uninformative variable elimination (UVE), successive projections algorithm (SPA), competitive adaptive re-weighted sampling (CARS), UVE-SPA, and CARS-SPA were used to feature extraction. This study proposes a machine learning model composed of a one-dimensional convolutional neural network backbone (1D CNN backbone) and a random forest classifier (RF classifier) to identify pesticide residues on black tea, and the 1D CNN-RF model was compared with three other machine learning models (support vector machine, RF, and 1D CNN). The results show that MSC-CARS-SPA-1D CNN-RF is the best model for identifying pesticide residues on black tea in which the accuracy of the test set is 99.05%. Combined with fluorescence hyperspectral technology, the proposed 1D CNN-RF model has great potential in the non-destructive identification of pesticide residues on black tea.

Oolong tea is a semi-fermented tea that is popular among people. This study aims to establish a classification method for oolong tea based on fluorescence hyperspectral technology(FHSI) combined with chemometrics. First, the spectral data of Tieguanyin, Benshan, Maoxie and Huangjingui were obtained. Then, standard normal variation (SNV) and multiple scatter correction (MSC) were used for preprocessing. Principal component analysis (PCA) was used for data visualization, and with tolerance ellipses that were drawn according to Hotelling, outliers in the spectra were removed. Variable importance for the projection (VIP) > 1 in partial least squares discriminant analysis (PLS–DA) was used for feature selection. Finally, the processed spectral data was entered into the support vector machine (SVM) and PLS–DA. MSC_VIP_PLS–DA was the best model for the classification of oolong tea. The results showed that the use of FHSI could accurately distinguish these four types of oolong tea and was able to identify the key wavelengths affecting the tea classification, which were 650.11, 660.29, 665.39, 675.6, 701.17, 706.31, 742.34 and 747.5 nm. In these wavelengths, different kinds of tea have significant differences (p < 0.05). This study could provide a non-destructive and rapid method for future tea identification.

China ranks first in apple production worldwide, making the assessment of apple quality a critical factor in agriculture. Sucrose concentration (SC) is a key factor influencing the flavor and ripeness of apples, serving as an important quality indicator. Nondestructive SC detection has significant practical value. Currently, SC is mainly measured using handheld refractometers, hydrometers, electronic tongues, and saccharimeter analyses, which are not only time-consuming and labor-intensive but also destructive to the sample. Therefore, a rapid nondestructive method is essential. The fluorescence hyperspectral imaging system (FHIS) is a tool for nondestructive detection. Upon excitation by the fluorescent light source, apples displayed distinct fluorescence characteristics within the 440–530 nm and 680–780 nm wavelength ranges, enabling the FHIS to detect SC. This study used FHIS combined with machine learning (ML) to predict SC at the apple’s equatorial position. Primary features were extracted using variable importance projection (VIP), the successive projection algorithm (SPA), and extreme gradient boosting (XGBoost). Secondary feature extraction was also conducted. Models like gradient boosting decision tree (GBDT), random forest (RF), and LightGBM were used to predict SC. VN-SPA + VIP-LightGBM achieved the highest accuracy, with $R_p^2$, $RMS{E}_p$, and $RPD$ reaching 0.9074, 0.4656, and 3.2877, respectively. These results underscore the efficacy of FHIS in predicting apple SC, highlighting its potential for application in nondestructive quality assessment within the agricultural sector.