A rapid dynamic headspace method for authentication of whiskies using artificial neural networks

Abstract

A rapid headspace analysis method for the authenticity testing of whiskies of different brands and years was developed for a low cost, deployable atmospheric pressure ionisation mass spectrometer, which required minimal sample preparation. Principal component analysis was applied to the time-averaged mass spectra, the classification results for which were compared against artificial neural network methods. The artificial neural network was found to outperform PCA, achieving ≥95% accuracy for all sampling conditions, with only two misclassifications under the ideal conditions, while requiring less development time.

Keywords

• Food authentication
• Atmospheric pressure chemical ionisation
• Artificial neural networks
• Whisky
• Headspace
• Transportable equipment