Multivariate versus machine learning-based classification of rapid evaporative Ionisation mass spectrometry spectra towards industry based large-scale fish speciation.

M. De Graeve, Nicholas Birse, Y. Hong, C. Elliott, L. Hemeryck, L. Vanhaecke

2023 Food Chemistry Cited 27 times

Abstract

Detection and prevention of fish food fraud are of ever-increasing importance, prompting the need for rapid, high-throughput fish speciation techniques. Rapid Evaporative Ionisation Mass Spectrometry (REIMS) has quickly established itself as a powerful technique for the instant in situ analysis of foodstuffs. In the current study, a total of 1736 samples (2015-2021) - comprising 17 different commercially valuable fish species - were analysed using iKnife-REIMS, followed by classification with various multivariate and machine learning strategies. The results demonstrated that multivariate models, i.e. PCA-LDA and (O)PLS-DA, delivered accuracies from 92.5 to 100.0%, while RF and SVM-based classification generated accuracies from 88.7 to 96.3%. Real-time recognition on a separate test set of 432 samples (2022) generated correct speciation between 89.6 and 99.5% for the multivariate models, while the ML models underperformed (22.3-95.1%), in particular for the white fish species. As such, we propose a real-time validated modelling strategy using directly amenable PCA-LDA for rapid industry-proof large-scale fish speciation.

Cited in this thesis

Introduction Literature Survey Fish Species and Part Identification Oil Contamination and Cross-Species Adulteration Conclusions

Frequently Cited Together

One model to learn them allKaiser 20175 chapters
From Laboratory Exploration to Practice: Applications, Challenges, and DevelopmeXue 20255 chapters
Development of an intelligent surgical knife rapid evaporative ionization mass sShen 20205 chapters
Comparative evaluating laser ionization and iKnife coupled with rapid evaporativLu 20245 chapters
Detection of fish frauds (basa catfish and sole fish) via iKnife rapid evaporatiShen 20225 chapters
Attention is all you needVaswani 20175 chapters

BibTeX

@article{De2023,
  title = {Multivariate versus machine learning-based classification of rapid evaporative Ionisation mass spectrometry spectra towards industry based large-scale fish speciation},
  author = {De Graeve, Marilyn and Birse, Nicholas and Hong, Yunhe and Elliott, Christopher T and Hemeryck, Lieselot Y and Vanhaecke, Lynn},
  journal = {Food Chemistry},
  volume = {404},
  pages = {134632},
  year = {2023},
  publisher = {Elsevier},
  abstract = {Detection and prevention of fish food fraud are of ever-increasing importance, prompting the need for rapid, high-throughput fish speciation techniques. Rapid Evaporative Ionisation Mass Spectrometry (REIMS) has quickly established itself as a powerful technique for the instant in situ analysis of foodstuffs. In the current study, a total of 1736 samples (2015–2021) - comprising 17 different commercially valuable fish species - were analysed using iKnife-REIMS, followed by classification with various multivariate and machine learning strategies. The results demonstrated that multivariate models, i.e. PCA-LDA and (O)PLS-DA, delivered accuracies from 92.5 to 100.0%, while RF and SVM-based classification generated accuracies from 88.7 to 96.3%. Real-time recognition on a separate test set of 432 samples (2022) generated correct speciation between 89.6 and 99.5% for the multivariate models, while the ML models underperformed (22.3–95.1%), in particular for the white fish species. As such, we propose a real-time validated modelling strategy using directly amenable PCA-LDA for rapid industry-proof large-scale fish speciation.},
}