Hyperspectral imaging (HSI) method was applied to rapidly and nondestructively predict total phenolic content in Flos Lonicerae. The least squares support vector machine (LS‐SVM) and partial least squares regression (PLSR) models were developed on the basis of full wavelengths data and characteristic wavelengths data chosen by six wavelengths selection ways. The results clarified that standard normal variable (SNV) was the optimal pretreatment method, and the nonlinear LS‐SVM model based on the characteristic wavelengths chosen by the combination (CARS‐SPA) of competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) yielded the best prediction performance for the total phenolic content. The overall results demonstrated that the proposed CARS‐SPA was a good method for selecting characteristic wavelengths to enhance prediction performance of HSI, and nonlinear LS‐SVM was more appropriate than linear PLSR for the prediction of total phenolic content in Flos Lonicerae.
Practical applications
Flos Lonicerae is a well‐known traditional Chinese medicinal herb, and also the raw material of various medicines and herbal tea. The demand for Flos Lonicerae is increasing. Therefore, monitoring the quality of Flos Lonicerae is very important to consumers and industry of Flos Lonicerae. The phenolic compounds content in Flos Lonicerae is one of the key internal quality factors. The traditional methods (such as spectrophotometric techniques or high‐performance liquid chromatography) for detecting total phenolic content are time‐consuming, labor‐consuming, and destructive. Hyperspectral imaging (HSI) is a nondestructive and reliable method for quality inspection. The results showed that SNV was determined as the best method for pretreatment, and the nonlinear CARS‐SPA‐LS‐SVM model was developed for total phenolic content detection with high precision. It could be verified that HSI technology is effective and promising for rapid determination of total phenolic content and quality control of Flos Lonicerae as well as other agricultural products.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.