In this study, near-infrared (NIR) spectroscopy was applied to efficiently and non-destructively identify Shandong green tea origins coupled with three different regression tools. Analysis results indicated that partial least squares… Click to show full abstract
In this study, near-infrared (NIR) spectroscopy was applied to efficiently and non-destructively identify Shandong green tea origins coupled with three different regression tools. Analysis results indicated that partial least squares (PLS) had better performance than back propagation artificial neural network (BP-ANN) and support vector machine (SVM). For PLS, the accuracies of identification were up to 100% for both training and testing. The results sufficiently demonstrate that NIR spectroscopy can be efficiently utilized for the non-destructive identification of green tea origins.
               
Click one of the above tabs to view related content.