Evaluation of Taste Quality in Green Tea Infusion Using Electronic Tongue Combined with LS-SVM

Abstract

This study discussed the feasibility of taste quality evaluation for green tea infusion using electronic tongue. Chemistry evaluation was regarded as the reference measurement, and used to measure total taste scores of green tea infusion. LS-SVM was used to build the correlativity between the sensor signals of green tea infusion and total taste scores by the reference measurement, and compared the influence of different principal components on the performance of LS-SVM model. Experimental results showed that the optimal model was obtained when 4 PCs were included with Rc=0.951 and RMSECV=3.242 in calibration set, Rp=0.904 and RMSEP=4.134 in the prediction set. This study showed that the electronic tongue had a great potential in the evaluation of taste quality for green tea and LS-SVM was an efficient method to build the evaluation model based on electronic tongue.

An Optimum Tea Fermentation Detection Model Based on Deep Convolutional Neural Networks

“…Some studies exist on the application of an electronic tongue to monitor tea fermentation. They include References [33][34][35][36]. In Reference [33], an optimal fermentation model with the use of electronic nose and machine learning techniques is proposed.…”

“…They include References [33][34][35][36]. In Reference [33], an optimal fermentation model with the use of electronic nose and machine learning techniques is proposed. In Reference [34], the authors applied CNN in the development of an electronic tongue.…”