EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Learning algorithms for identification of whisky using portable Raman spectroscopy

Kwang Jun Lee, Alexander C Trowbridge, Graham D Bruce, George O Dwapanyin, Kylie R Dunning, Kishan Dholakia, Erik P Schartner

Current Research in Food Science · 2024 · 8 · 100729

DOI: 10.1016/j.crfs.2024.100729 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Current Research in Food Science, 2024. Verfasst von Kwang Jun Lee und 6 weiteren Autor:innen. Beteiligte Einrichtung: Centre of Light for Life (CLL) and Institute for Photonics and Advanced Sensing (IPAS), The University of Adelaide, Adelaide, 5005, SA, Australia. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Health and Medical Research Council, Australian Research Council, Horizon 2020.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable identification of high-value products such as whisky is vital due to rising issues of brand substitution and quality control in the industry. We have developed a novel framework that can perform whisky analysis directly from raw spectral data with no human intervention by integrating machine learning models with a portable Raman device. We demonstrate that machine learning models can achieve over 99% accuracy in brand or product identification across twenty-eight commercial samples. To demonstrate the flexibility of this approach, we utilized the same algorithms to quantify ethanol concentrations, as well as measuring methanol levels in spiked whisky samples. To demonstrate the potential use of these algorithms in a real-world environment we tested our algorithms on spectral measurements performed through the original whisky bottle. Through the bottle measurements are facilitated by a beam geometry hitherto not applied to whisky brand identification in conjunction with machine learning. Removing the need for decanting greatly enhances the practicality and commercial potential of this technique, enabling its use in detecting counterfeit or adulterated spirits and other high-value liquids. The techniques established in this paper aim to function as a rapid and non-destructive initial screening mechanism for detecting falsified and tampered spirits, complementing more comprehensive and stringent analytical methods.

Schlagwörter

Stichwörter der Autor:innen

Brand identificationMachine learningRaman spectroscopyWhisky

Autor:innen und Institutionen

  • Centre of Light for Life (CLL) and Institute for Photonics and Advanced Sensing (IPAS), The University of Adelaide, Adelaide, 5005, SA, Australia.
  • School of Physics, Chemistry and Earth Sciences, The University of Adelaide, Adelaide, 5005, SA, Australia.
  • School of Biological Sciences, The University of Adelaide, Adelaide, 5005, SA, Australia.
  • SUPA School of Physics and Astronomy, University of St Andrews, St Andrews, KY16 9SS, Fife, United Kingdom.
  • Robinson Research Institute, School of Biomedicine, The University of Adelaide, Adelaide, 5005, SA, Australia.

Förderung

  • National Health and Medical Research Council
  • Australian Research Council
  • Horizon 2020

Zitieren

APA

Lee, K. J., Trowbridge, A. C., Bruce, G. D., Dwapanyin, G. O., Dunning, K. R., Dholakia, K., & Schartner, E. P. (2024). Learning algorithms for identification of whisky using portable Raman spectroscopy. Current Research in Food Science, 8, 100729. https://doi.org/10.1016/j.crfs.2024.100729

Vancouver

Lee KJ, Trowbridge AC, Bruce GD, Dwapanyin GO, Dunning KR, Dholakia K, et al. Learning algorithms for identification of whisky using portable Raman spectroscopy. Current Research in Food Science. 2024;8:100729. doi:10.1016/j.crfs.2024.100729

BibTeX
@article{Lee2024,
  author = {Lee, Kwang Jun and Trowbridge, Alexander C and Bruce, Graham D and Dwapanyin, George O and Dunning, Kylie R and Dholakia, Kishan and Schartner, Erik P},
  title = {Learning algorithms for identification of whisky using portable Raman spectroscopy},
  journal = {Current Research in Food Science},
  year = {2024},
  volume = {8},
  pages = {100729},
  doi = {10.1016/j.crfs.2024.100729}
}
Kostenlos starten →