Classification of black tea liquor using cyclic voltammetry

Tea quality evaluation is a complex task and is carried out qualitatively in the industry by experienced tea tasters. But, the unpredictable and inconsistent nature of human panel tasting demands instrumental methods to assess the quality of black tea in an objective manner. For discrimination between different black tea samples and instrumental evaluation of their quality, a new method employing the principle of cyclic voltammetry is proposed in this paper. The technique has been investigated using platinum and glassy carbon as working electrodes and the resultant current from the potentiostat has been considered for data analysis. First, principal component analysis (PCA) and linear discriminant analysis (LDA) has been performed for visualization of underlying clusters and finally, a neural network model has been used to classify the data. The performance of the classifier has been established using 10-fold cross-validation method.