Advanced search
2 files | 27.19 MB Add to list

Rapid and non-destructive microbial quality prediction of fresh pork stored under modified atmospheres by using selected-ion flow-tube mass spectrometry and machine learning

(2024) MEAT SCIENCE. 213.
Author
Organization
Project
Abstract
Volatile organic compounds (VOCs) indicative of pork microbial spoilage can be quantified rapidly at trace levels using selected-ion flow-tube mass spectrometry (SIFT-MS). Packaging atmosphere is one of the factors influencing VOC production patterns during storage. On this basis, machine learning would help to process complex volatolomic data and predict pork microbial quality efficiently. This study focused on (1) investigating model generalizability based on different nested cross-validation settings, and (2) comparing the predictive power and feature importance of nine algorithms, including Artificial Neural Network (ANN), k-Nearest Neighbors, Support Vector Regression, Decision Tree, Partial Least Squares Regression, and four ensemble learning models. The datasets used contain 37 VOCs’ concentrations (input) and total plate counts (TPC, output) of 350 pork samples with different storage times, including 225 pork loin samples stored under three high-O2 and three low-O2 conditions, and 125 commercially packaged products. An appropriate choice of cross-validation strategies resulted in trustworthy and relevant predictions. When trained on all possible selections of two high-O2 and two low-O2 conditions, ANNs produced satisfactory TPC predictions of unseen test scenarios (one high-O2 condition, one low-O2 condition, and the commercial products). ANN-based bagging outperformed other employed models, when TPC exceeded ca. 6 log CFU/g. VOCs including benzaldehyde, 3-methyl-1-butanol, ethanol and methyl mercaptan were identified with high feature importance. This elaborated case study illustrates great prospects of real-time detection techniques and machine learning in meat quality prediction. Further investigations on handling low VOC levels would enhance the model performance and decision making in commercial meat quality control.
Keywords
Pork storage, Volatile organic compounds, Nested cross-validation, Ensemble learning, Permutation feature importance

Downloads

  • (...).pdf
    • full text (Accepted manuscript)
    • |
    • UGent only (changes to open access on 2024-10-05)
    • |
    • PDF
    • |
    • 21.60 MB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 5.59 MB

Citation

Please use this url to cite or link to this publication:

MLA
Chen, Linyun, et al. “Rapid and Non-Destructive Microbial Quality Prediction of Fresh Pork Stored under Modified Atmospheres by Using Selected-Ion Flow-Tube Mass Spectrometry and Machine Learning.” MEAT SCIENCE, vol. 213, 2024, doi:10.1016/j.meatsci.2024.109505.
APA
Chen, L., Kuuliala, L., Somrani Achouri, M., Walgraeve, C., Demeestere, K., De Baets, B., & Devlieghere, F. (2024). Rapid and non-destructive microbial quality prediction of fresh pork stored under modified atmospheres by using selected-ion flow-tube mass spectrometry and machine learning. MEAT SCIENCE, 213. https://doi.org/10.1016/j.meatsci.2024.109505
Chicago author-date
Chen, Linyun, Lotta Kuuliala, Mariem Somrani Achouri, Christophe Walgraeve, Kristof Demeestere, Bernard De Baets, and Frank Devlieghere. 2024. “Rapid and Non-Destructive Microbial Quality Prediction of Fresh Pork Stored under Modified Atmospheres by Using Selected-Ion Flow-Tube Mass Spectrometry and Machine Learning.” MEAT SCIENCE 213. https://doi.org/10.1016/j.meatsci.2024.109505.
Chicago author-date (all authors)
Chen, Linyun, Lotta Kuuliala, Mariem Somrani Achouri, Christophe Walgraeve, Kristof Demeestere, Bernard De Baets, and Frank Devlieghere. 2024. “Rapid and Non-Destructive Microbial Quality Prediction of Fresh Pork Stored under Modified Atmospheres by Using Selected-Ion Flow-Tube Mass Spectrometry and Machine Learning.” MEAT SCIENCE 213. doi:10.1016/j.meatsci.2024.109505.
Vancouver
1.
Chen L, Kuuliala L, Somrani Achouri M, Walgraeve C, Demeestere K, De Baets B, et al. Rapid and non-destructive microbial quality prediction of fresh pork stored under modified atmospheres by using selected-ion flow-tube mass spectrometry and machine learning. MEAT SCIENCE. 2024;213.
IEEE
[1]
L. Chen et al., “Rapid and non-destructive microbial quality prediction of fresh pork stored under modified atmospheres by using selected-ion flow-tube mass spectrometry and machine learning,” MEAT SCIENCE, vol. 213, 2024.
@article{01J070B81WBKCG5SBBFBEJ5TNN,
  abstract     = {{Volatile organic compounds (VOCs) indicative of pork microbial spoilage can be quantified rapidly at trace levels using selected-ion flow-tube mass spectrometry (SIFT-MS). Packaging atmosphere is one of the factors influencing VOC production patterns during storage. On this basis, machine learning would help to process complex volatolomic data and predict pork microbial quality efficiently. This study focused on (1) investigating model generalizability based on different nested cross-validation settings, and (2) comparing the predictive power and feature importance of nine algorithms, including Artificial Neural Network (ANN), k-Nearest Neighbors, Support Vector Regression, Decision Tree, Partial Least Squares Regression, and four ensemble learning models. The datasets used contain 37 VOCs’ concentrations (input) and total plate counts (TPC, output) of 350 pork samples with different storage times, including 225 pork loin samples stored under three high-O2 and three low-O2 conditions, and 125 commercially packaged products. An appropriate choice of cross-validation strategies resulted in trustworthy and relevant predictions. When trained on all possible selections of two high-O2 and two low-O2 conditions, ANNs produced satisfactory TPC predictions of unseen test scenarios (one high-O2 condition, one low-O2 condition, and the commercial products). ANN-based bagging outperformed other employed models, when TPC exceeded ca. 6 log CFU/g. VOCs including benzaldehyde, 3-methyl-1-butanol, ethanol and methyl mercaptan were identified with high feature importance. This elaborated case study illustrates great prospects of real-time detection techniques and machine learning in meat quality prediction. Further investigations on handling low VOC levels would enhance the model performance and decision making in commercial meat quality control.}},
  articleno    = {{109505}},
  author       = {{Chen, Linyun and Kuuliala, Lotta and Somrani Achouri, Mariem and Walgraeve, Christophe and Demeestere, Kristof and De Baets, Bernard and Devlieghere, Frank}},
  issn         = {{0309-1740}},
  journal      = {{MEAT SCIENCE}},
  keywords     = {{Pork storage,Volatile organic compounds,Nested cross-validation,Ensemble learning,Permutation feature importance}},
  language     = {{eng}},
  pages        = {{14}},
  title        = {{Rapid and non-destructive microbial quality prediction of fresh pork stored under modified atmospheres by using selected-ion flow-tube mass spectrometry and machine learning}},
  url          = {{http://doi.org/10.1016/j.meatsci.2024.109505}},
  volume       = {{213}},
  year         = {{2024}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: