Traceability of honey origin based on volatiles pattern processing by artificial neural networks

J Chromatogr A. 2009 Feb 27;1216(9):1458-62. doi: 10.1016/j.chroma.2008.12.066. Epub 2008 Dec 27.

Abstract

Head-space solid-phase microextraction (HS-SPME)-based procedure, coupled to comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry (GCxGC-TOF-MS), was employed for fast characterisation of honey volatiles. In total, 374 samples were collected over two production seasons in Corsica (n=219) and other European countries (n=155) with the emphasis to confirm the authenticity of the honeys labelled as "Corsica" (protected denomination of origin region). For the chemometric analysis, artificial neural networks with multilayer perceptrons (ANN-MLP) were tested. The best prediction (94.5%) and classification (96.5%) abilities of the ANN-MLP model were obtained when the data from two honey harvests were aggregated in order to improve the model performance compared to separate year harvests.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Food Analysis / methods*
  • Gas Chromatography-Mass Spectrometry / methods
  • Honey / analysis*
  • Neural Networks, Computer*
  • Principal Component Analysis / methods
  • Reproducibility of Results
  • Solid Phase Microextraction / methods
  • Volatile Organic Compounds / analysis

Substances

  • Volatile Organic Compounds