Application of Electronic Nose for Detection of Wine-Aging Methods

Application progress of intelligent flavor sensing system in the production process of fermented foods based on the flavor properties

Fermented foods are sensitive to the production conditions because of microbial and enzymatic activities, which requires intelligent flavor sensing system (IFSS) to monitor and optimize the production process based on the flavor properties. As the simulation system of human olfaction and gustation, IFSS has been widely used in the field of food with the characteristics of nondestructive, pollution-free, and real-time detection. This paper reviews the application of IFSS in the control of fermentation, ripening, and shelf life, and the potential in the identification of quality differences and flavor-producing microbes in fermented foods. The survey found that electronic nose (tongue) is suitable to monitor fermentation process and identify food authenticity in real time based on the changes of flavor profile. Gas chromatography-ion mobility spectrometry and nuclear magnetic resonance technology can be used to analyze the flavor metabolism of fermented foods at various production stages and explore the correlation between flavor substances and microorganisms.

Assessment of Smoke Contamination in Grapevine Berries and Taint in Wines Due to Bushfires Using a Low-Cost E-Nose and an Artificial Intelligence Approach

Bushfires are increasing in number and intensity due to climate change. A newly developed low-cost electronic nose (e-nose) was tested on wines made from grapevines exposed to smoke in field trials. E-nose readings were obtained from wines from five experimental treatments: (i) low-density smoke exposure (LS), (ii) high-density smoke exposure (HS), (iii) high-density smoke exposure with in-canopy misting (HSM), and two controls: (iv) control (C; no smoke treatment) and (v) control with in-canopy misting (CM; no smoke treatment). These e-nose readings were used as inputs for machine learning algorithms to obtain a classification model, with treatments as targets and seven neurons, with 97% accuracy in the classification of 300 samples into treatments as targets (Model 1). Models 2 to 4 used 10 neurons, with 20 glycoconjugates and 10 volatile phenols as targets, measured: in berries one hour after smoke (Model 2; R = 0.98; R² = 0.95; b = 0.97); in berries at harvest (Model 3; R = 0.99; R² = 0.97; b = 0.96); in wines (Model 4; R = 0.99; R² = 0.98; b = 0.98). Model 5 was based on the intensity of 12 wine descriptors determined via a consumer sensory test (Model 5; R = 0.98; R² = 0.96; b = 0.97). These models could be used by winemakers to assess near real-time smoke contamination levels and to implement amelioration strategies to minimize smoke taint in wines following bushfires.

Using an electronic nose and volatilome analysis to differentiate sparkling wines obtained under different conditions of temperature, ageing time and yeast formats

Effect of yeast inoculation format (F), temperature (T), and "on lees" ageing time (t) factors were evaluated on the composition of sparkling wines by a quantitative fingerprint obtained from volatile metabolites and the response of an electronic nose (E-nose). Wines elaborated according the traditional method at 10 and 14 °C, free cells and yeast biocapsules formats were monitored at 15 and 24 months of ageing time. Sixty-six volatiles identified and quantified in the eight sampling lots were subjected to a pattern recognition technique. A dual criterion based on univariate (ANOVA) and multivariate analysis (PLS-DA) through the variable importance projection (VIP) values, allowed to identify ten volatiles as potential markers for T factor, eleven for t and twelve for F factors. The discriminant models based on E-nose dataset enable a 100% correct classification of samples, in relation with t and F factors and the 83% for T factor.

Bionic Electronic Nose Based on MOS Sensors Array and Machine Learning Algorithms Used for Wine Properties Detection

In this study, a portable electronic nose (E-nose) prototype is developed using metal oxide semiconductor (MOS) sensors to detect odors of different wines. Odor detection facilitates the distinction of wines with different properties, including areas of production, vintage years, fermentation processes, and varietals. Four popular machine learning algorithms—extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and backpropagation neural network (BPNN)—were used to build identification models for different classification tasks. Experimental results show that BPNN achieved the best performance, with accuracies of 94% and 92.5% in identifying production areas and varietals, respectively; and SVM achieved the best performance in identifying vintages and fermentation processes, with accuracies of 67.3% and 60.5%, respectively. Results demonstrate the effectiveness of the developed E-nose, which could be used to distinguish different wines based on their properties following selection of an optimal algorithm.

Quantification of Wine Mixtures with an Electronic Nose and a Human Panel

In this work, an electronic nose and a human panel were used for the quantification of wines formed by binary mixtures of four white grape varieties and two varieties of red wines at different percentages (from 0 to 100% in 10% steps for the electronic nose and from 0 to 100% in 25% steps for the human panel). The wines were prepared using the traditional method with commercial yeasts. Both techniques were able to quantify the mixtures tested, but it is important to note that the technology of the electronic nose is faster, simpler, and more objective than the human panel. In addition, better results of quantification were also obtained using the electronic nose.

Electronic Noses and Tongues in Wine Industry

The quality of wines is usually evaluated by a sensory panel formed of trained experts or traditional chemical analysis. Over the last few decades, electronic noses (e-noses) and electronic tongues have been developed to determine the quality of foods and beverages. They consist of arrays of sensors with cross-sensitivity, combined with pattern recognition software, which provide a fingerprint of the samples that can be used to discriminate or classify the samples. This holistic approach is inspired by the method used in mammals to recognize food through their senses. They have been widely applied to the analysis of wines, including quality control, aging control, or the detection of fraudulence, among others. In this paper, the current status of research and development in the field of e-noses and tongues applied to the analysis of wines is reviewed. Their potential applications in the wine industry are described. The review ends with a final comment about expected future developments.