Colorimetric Sensor Array for White Wine Tasting

Abstract

A colorimetric sensor array was developed to characterize and quantify the taste of white wines. A charge-coupled device (CCD) camera captured images of the sensor array from 23 different white wine samples, and the change in the R, G, B color components from the control were analyzed by principal component analysis. Additionally, high performance liquid chromatography (HPLC) was used to analyze the chemical components of each wine sample responsible for its taste. A two-dimensional score plot was created with 23 data points. It revealed clusters created from the same type of grape, and trends of sweetness, sourness, and astringency were mapped. An artificial neural network model was developed to predict the degree of sweetness, sourness, and astringency of the white wines. The coefficients of determination (R2) for the HPLC results and the sweetness, sourness, and astringency were 0.96, 0.95, and 0.83, respectively. This research could provide a simple and low-cost but sensitive taste prediction system, and, by helping consumer selection, will be able to have a positive effect on the wine industry.

Keywords: artificial neural network; colorimetric; principle component analysis; taste sensor.

Figure 1

Image acquisition system for the colorimetric sensor array. Images of the taste sensor were taken before and after 100 µL of the white wine sample was placed on the taste sensor.

Figure 2

Coefficient of determination between the average absorbance of each dye-bead conjugate and the concentration of each taste-related chemical in terms of the red (620–780 nm), green (500–580 nm), and blue (450–500 nm) color values.

Figure 3

The sweetness (A); sourness (B); and astringency (C) of the white wine samples based on HPLC analysis and weighted. The left and right charts are for the sweet and less sweet wine samples, respectively.

Figure 4

Images of eight dye-bead conjugates in the array before and after incubation with wine samples.

Figure 5

Score plot of PCA grouping wines with grape varieties and characterizing the taste on the plane of PC1 and PC2 (A); and PC1 and PC3 (B).

Figure 6

ANN model evaluation of measured and predicted sweetness (A); sourness (B); and astringency (C).