Related Experiment Video
Updated: Jun 26, 2026
13:55
Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
Published on: July 21, 2014
Traceability of honey origin based on volatiles pattern processing by artificial neural networks
Tomas Cajka1, Jana Hajslova, Frantisek Pudil
1Institute of Chemical Technology, Prague, Faculty of Food and Biochemical Technology, Department of Food Chemistry and Analysis, Technicka 5, 16628 Prague 6, Czech Republic.
Journal of Chromatography. A
|January 20, 2009
Summary
This study used advanced chromatography and AI to analyze honey volatiles for authenticity. Aggregating data from two harvests improved the artificial neural network model
Area of Science:
- Food chemistry
- Analytical chemistry
- Chemometrics
Background:
- Honey authentication is crucial for consumer trust and regulatory compliance.
- Geographical origin and production season significantly impact honey's volatile profile.
- Advanced analytical techniques are needed for rapid and reliable honey characterization.
Purpose of the Study:
- To develop a fast method for characterizing honey volatiles.
- To confirm the authenticity of honeys labeled as "Corsica" (PDO).
- To evaluate the performance of artificial neural networks for honey classification.
Main Methods:
- Head-space solid-phase microextraction (HS-SPME) for sample preparation.
- Comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry (GCxGC-TOF-MS) for volatile analysis.
- Artificial neural networks with multilayer perceptrons (ANN-MLP) for chemometric analysis.
Main Results:
- Successfully characterized honey volatiles using HS-SPME-GCxGC-TOF-MS.
- Collected 374 honey samples from Corsica and other European countries over two seasons.
- Achieved high prediction (94.5%) and classification (96.5%) accuracy with ANN-MLP by aggregating data from two harvests.
Conclusions:
- The developed HS-SPME-GCxGC-TOF-MS method provides fast characterization of honey volatiles.
- Aggregating data from multiple harvests enhances the performance of ANN-MLP models for honey authentication.
- The approach is effective for confirming the authenticity of geographically labeled honeys.
