Tea Quality Prediction by Autoregressive Modeling of Electronic Tongue Signals

In this paper, a novel method to model the responses of electronic tongue (ET) sensors using autoregressive (AR) and AR moving average techniques is presented. The transient response of each electrode present in the sensor array of an ET is characterized with tea samples of different qualities. Models coefficients are used as the characteristics features of the ET response corresponding to the tea samples. Three different classifiers, namely, artificial neural network, vector valued regularized kernel function approximation, and one-versus-one support vector machine, are employed to evaluate the performance of these features to discriminate the quality of black tea. Experimental results on three types of voltammetric measurement data show that the proposed method may be very useful for prediction of tea quality. The present model-based classification method is very straightforward and provides better or similar performance compared with some other methods proposed in the literature for ET signal classification.