Determination of Total Polysaccharides and Total Flavonoids in Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging and Multivariate Analysis

Abstract

The rapid and nondestructive determination of active compositions in Chrysanthemum morifolium (Hangbaiju) is of great value for producers and consumers. Hyperspectral imaging as a rapid and nondestructive technique was used to determine total polysaccharides and total flavonoids content in Chrysanthemum morifolium. Hyperspectral images of different sizes of Chrysanthemum morifolium flowers were acquired. Pixel-wise spectra within all samples were preprocessed by wavelet transform (WT) followed by standard normal variate (SNV). Partial least squares (PLS) and least squares-support vector machine (LS-SVM) were used to build prediction models using sample average spectra calculated by preprocessed pixel-wise spectra. The LS-SVM model performed better than the PLS models, with the determination of the coefficient of calibration (R2c) and prediction (R2p) being over 0.90 and the residual predictive deviation (RPD) being over 3 for total polysaccharides and total flavonoids content prediction. Prediction maps of total polysaccharides and total flavonoids content in Chrysanthemum morifolium flowers were successfully obtained by LS-SVM models, which exhibited the best performances. The overall results showed that hyperspectral imaging was a promising technique for the rapid and accurate determination of active ingredients in Chrysanthemum morifolium, indicating the great potential to develop an online system for the quality determination of Chrysanthemum morifolium.

Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis

“…The closer R 2 of the model is to 1, the closer RMSE is to 0, the higher the value of RPD, indicating that the variables are more capable to explain the response value, which also means that the performance of the model is better. According to the reference [34], the value of R 2 between 0.61 and 0.8 demonstrates that the model is capable for prediction. An R 2 of 0.81-0.9 indicates that the model shows good performance, and its value above 0.9 manifests the prediction ability of the model is excellent.…”

“…RPD is the ratio of standard deviation (SD) of the prediction set to RMSEP. Its value below 2.0 indicates the model is incapable to perform quantitative prediction, a value of 2.0-2.5 means that the model can be applied to prediction and a value above 2.5 proves the prediction ability of the model is good [34]. R 2 , RMSE, and RPD of the calibration, validation, and prediction set were calculated using the following equations.…”

Nondestructive Determination and Visualization of Quality Attributes in Fresh and Dry Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging

“…Hyperspectral image acquisition of fresh and dry flowers was conducted using the hyperspectral imaging system in our previous study [14]. Each single fresh or dry flower was placed separately in a black plate for hyperspectral image acquisition.…”

“…After image acquisition and calibration [14], spectral information was extracted from the hyperspectral images. Pixelwise spectra within each flower were extracted.…”

“…Knowing quality attributes will help to optimize the harvest time and procedure of Chrysanthemum morifolium, and the quality sorting can be conducted during harvest. Our previous study has proven the feasibility of using hyperspectral imaging to determine total polysaccharides and total flavonoids in dry Chrysanthemum morifolium [14]. The feasibility of using hyperspectral imaging to determine more chemical compositions for quality sorting and monitoring of Chrysanthemum morifolium should be further studied.…”