Identification of the green tea grade level using electronic tongue and pattern recognition

Electronic tongue as an analytical tool was attempted to identify tea grade level coupled with pattern recognition in this work. Four grades of green tea were attempted in the experiment. Electronic tongue system was developed for data acquisition. K-nearest neighbors (KNN) and artificial neural network (ANN) were applied to build identification models, respectively. Some parameters of the model were optimized by cross-validation in building models. The performance of the KNN model and the ANN model on electronic tongue data was compared. Experimental results showed that the ANN model is better than the KNN model. The optimal ANN model was achieved when principal component factors are equal to five, and identification rates of the ANN model are 100% in both the training set and the prediction set. This work demonstrated that electronic tongue technology with ANN pattern recognition method can be successfully applied to the identification tea grade level.