Elements like minerals and heavy metals play important roles in nutrients and safety of agricultural products. It is necessary to develop rapid, online, real time and in-situ methods for monitoring...
The economic value and consumer acceptance of Pu-erh tea heavily depend on the production year. The present study aims to evaluate the potential of utilizing laser-induced breakdown spectroscopy (LIBS) in conjunction with chemometric models to identify Pu-erh raw tea from various production years. The research utilizes tea leaves from a common source in 2008, 2013, and 2018 as the analytical samples. One hundred spectral datasets were collected for each type of tea, and these datasets are randomly partitioned into cross-validation and test sets in a 3:2 ratio. Subsequently, by utilizing threshold peak finding to extract features from the baseline-corrected LIBS spectrum, 21 spectral datasets are identified and input into LDA, SVM, EML, and KNN classification models for analysis. Results demonstrate that the LDA model achieves superior performance in identifying tea leaf years, attaining a recognition rate of 98.75%. Additionally, the average recognition rate of the other three algorithms in three-classification tasks exceeds 90%. Overall, this study confirms the feasibility and effectiveness of utilizing LIBS in conjunction with machine learning algorithms for discriminating Pu-erh raw tea originating from different production years.
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.