Classification of Chinese Vinegars Using Optimized Artificial Neural Networks by Genetic Algorithm and Other Discriminant Techniques

The aims of this study were to explore the most important volatile aroma compounds of Chinese vinegars and to apply the artificial neural networks (ANN) to classify Chinese vinegars. A total of 101 volatile aroma components, which include 21 esters, 16 aldehydes, 15 acids, 19 alcohols, 10 ketones, 9 phenols, 5 pyrazines, 3 furans, and 3 miscellaneous compounds, were identified by gas chromatography mass spectrometry. On the basis of sensitivity analysis, 6 and 11 volatile aroma compounds were selected and proved to be useful for classifying Chinese vinegars by fermentation method and geographic region, respectively. The variables with the greatest contribution in the classification of Chinese vinegars by geographic region were 2-methoxy-4-methylphenol and acetic acid, whereas 3-methylbutanoic acid and furfural played the most important roles in fermentation method classification. ANN could classify Chinese vinegars based on fermentation method and geographic region with a prediction success rate of 100%. This level was higher than the accuracy of cluster analysis, linear discriminant analysis, and K-nearest neighbor. Results showed that ANN was a useful model for classifying Chinese vinegars.