Fusing one-class and two-class classification – A case study on the detection of pepper fraud

Martin Alewijn*, Vasiliki Akridopoulou, Tjerk Venderink, Judith Müller-Maatsch, Erika Silletti

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Black pepper is a commercially important commodity, which is susceptible for fraudulent additions. Analytical tools are capable of detection of specific additions, but in most published cases these tools and associated mathematical models are suitable for only one or a few predetermined adulterants. There is a need for methodology that can detect any addition without having to know the type of adulterant a priori. We analysed a dataset of 200 authentic black pepper samples and a total of 210 adulterated samples consisting of mixtures of black pepper and oil-dress pepper, spent pepper, coffee husk, coffee skin and papaya seeds, respectively. A small, non-destructive spectral tool, a visible-near infrared spectrophotometer, (VIS/NIR) and a slower and more expensive mass spectrometric tool, direct analysis in real time-mass spectrometer (DART-MS), were evaluated according to their performances in terms of adulteration detection for a number of machine learning modes. The often-used approach where an ‘optimal’ model is selected and employed yielded for VIS/NIR very reasonable results for most of the adulterants used, but no single model performed well for all adulterants in the dataset. However, high-level fusion modelling of both one- and two-class models developed for different adulterant types using a penalized excess scoring system led to a performance of typically >75% correct classification, regardless of the nature of the adulterant. DART-MS outperformed VIS/NIR but also led to no single model that was able to detect all adulterants present. From the small number of tested fusion strategies, again the penalized excess score outperformed the other fusion options and yielded perfect classification scores for all but one of the adulterants tested. This shows that this type of modelling for cases where the nature of a target is unknown is a promising approach. It is even speculated that this modelling approach is likely to be suitable for types of adulterant that were not used in the model development phase.

Original languageEnglish
Article number109502
JournalFood Control
Volume145
DOIs
Publication statusPublished - Mar 2023

Keywords

  • Classification
  • Direct analysis in real time-mass spectrometry
  • Fraud
  • High-level data fusion
  • Visible-near infrared spectrophotometry

Fingerprint

Dive into the research topics of 'Fusing one-class and two-class classification – A case study on the detection of pepper fraud'. Together they form a unique fingerprint.

Cite this