Identification of Red Wine Storage Years based on Electronic Tongue and EEMD-WOA-LSSVM Model

In order to achieve identification of different storage years of red wine, an electronic tongue identification method based on ensemble empirical modal decomposition(EEMD), whale optimization algorithm (WOA) and least square support vector machine (LSSVM) was proposed. The voltammetry electronic tongue was used to collect the "fingerprint" information of the aged red wine with four storage years, and then the ensemble empirical modal decomposition was used to carry out the original signal of the electronic tongue. The scale decomposition obtained a set of intrinsic mode functions, and finally obtained its singular spectral entropy and Hilbert marginal spectrum as feature data. Finally, the whale optimization algorithm was used to optimize the parameters of the least square support vector machine, and the analysis model of red wine storage age was established. The experimental results showed that the accuracy, precision, recall, F1-score and Kappa coefficient of EEMD-WOA-LSSVM model were 97.5%, 97.75%, 97.5%, 0.98 and 0.97, respectively, which had discrimination better performance for storage year of red wine compared with SVM, GA-LSSVM and PSO-LSSVM. This research can provide a technical reference and research approach of red wine storage year.