In order to explore the drying characteristics of Panax notoginseng taproot (PNT) and realize the dynamic monitoring of moisture content in the segmented drying process of microwave vacuum combined with hot air, the PNT was conducted the experimental study under different convert moisture contents of wet basis (20, 30, 40 g•g À1 ), upper-temperature limits (45, 50, 55 C), power densities (0.50, 0.75, 1.00, 1.50 W•g À1 ) and chamber pressures (1, 3, 5, 10 kPa). The dynamic changes in moisture ratio and drying rate under different drying conditions were studied, and a snake optimizer-support vector regression (SO-SVR) model was proposed to predict mois-

Panax notoginseng slices (PNS) are prepared from the taproot of a rare Chinese herbal plant, Panax notoginseng. The price and efficacy of PNS change depending on its grade, but substandard PNS are more prevalent in the Asian market. In this study, a portable near‐infrared spectrometer was used to collect the spectra of 240 PNS samples divided into four grades. The spectral data were preprocessed by the Savitzky–Golay (SG) filter to eliminate noise interference. Principal component analysis (PCA), competitive adaptive reweighted sampling, and variable combination population analysis were used to extract the feature variables of the spectral data. The selected feature variables were used to establish least squares support vector machine (LSSVM), support vector machine (SVM), and extreme learning machine (ELM) classification models. To further improve the classification accuracy of the most effective of these models, a grey wolf optimizer (GWO) was introduced, and particle swarm optimization (PSO) as well as genetic algorithm (GA) were used to conduct comparative analyses. The results showed that PCA provided accurate identification information of different PNS grades and that the classification effect of the LSSVM model was better than that of the ELM and SVM models. During the optimization process, the optimization accuracy of the GWO was better than that of the PSO and GA systems. Therefore, the optimal classification model was established as GWO–PCA–LSSVM, and the classification accuracy of the test set was 91.67%. Therefore, portable near‐infrared spectroscopy technology can be used to identify the grade of PNS effectively.

Microwave vacuum drying (MVD) is a rapid drying method, which can achieve a good balance between drying rate and quality. In the present work, the effects of MVD processes on the quality, drying kinetics, and moisture diffusion of yam (Dioscorea opposita L.) were investigated. Results indicated that the loss of moisture in the MVD of yam slices mainly occurred in the stage with a constant and decreasing speed. When the moisture content of the dry base was decreased to about 1.3 g/g (dry basis, D.B.), it began to enter the deceleration phase. The effective moisture diffusivity (Deff) and mass transfer coefficient (km) increased following the power, loading amount at one time, and vacuum (pressure drop). The established equation of these parameters described well this variation law. Furthermore, a neural network model was established to predict the change in moisture content in the drying process, and the law of moisture diffusion was described. In terms of quality, the contribution ranked from high to low was loading, power, and pressure. Increasing the microwave power, loading, and maintaining a high vacuum degree could reduce energy consumption and ensure quality, thus improving the economic feasibility of microwave vacuum in the drying process.