Abstract
Determination of Chinese liquor from different geographic origins is benefit for controlling liquor quality and safeguarding the interests of consumers. In the study, 131 Chinese liquor samples were detected by the headspace (HS)-solid phase microextraction (SPME)-mass spectrometry (MS) technique, and then mass spectra data of samples were exported by the NIST 05 library. By combination of partial least squares discriminant analysis (PLS-DA) and stepwise linear discriminant analysis (SLDA) method, 32 characteristic ions were finally picked out and the prediction accuracy of SLDA was more than 97.7%. And then an artificial neural network (ANN) recognition model using the 32 ions as inputs and 8 groups different geographic origins as outputs was built, whose prediction accuracy was up to 100%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have