Determination of tea polyphenols in green tea by homemade color sensitive sensor combined with multivariate analysis

Tea polyphenols content in green tea has an indirect relationship with the aroma quality of tea. This study innovatively proposed a method for quantitative determination of tea polyphenols in green tea based on the self-developed color sensitive sensor. Firstly, the color sensitive sensor was prepared to acquire the aroma information of green tea. Secondly, color components were extracted and then optimized using ant colony optimization (ACO) algorithm. Finally, extreme learning machine (ELM) model was built using the optimized color feature components for quantitative determination of tea polyphenols content in green tea. Results showed that the correlation coefficient (RP) of the best ELM model is 0.8035, and the root mean square error prediction (RMSEP) is 1.6003% in the validation set. The overall results sufficiently demonstrate that it is feasible to quantitative detect tea polyphenols content in green tea by the homemade color sensitive sensor combined with appropriate chemometrics methods.