Advanced search
1 file | 3.54 MB Add to list

Probabilistic topic modelling in food spoilage analysis : a case study with Atlantic salmon (Salmo salar)

Lotta Kuuliala (UGent) , Raul Perez Fernandez (UGent) , Mengzi Tang (UGent) , Mieke Vanderroost (UGent) , Bernard De Baets (UGent) and Frank Devlieghere (UGent)
Author
Organization
Project
Abstract
Probabilistic topic modelling is frequently used in machine learning and statistical analysis for extracting latent information from complex datasets. Despite being closely associated with natural language processing and text mining, these methods possess several properties that make them particularly attractive in metabolomics applications where the applicability of traditional multivariate statistics tends to be limited. The aim of the study was thus to introduce probabilistic topic modelling more specifically, Latent Dirichlet Allocation (LDA) in a novel experimental context: volatilome-based (sea) food spoilage characterization. This was realized as a case study, focusing on modelling the spoilage of Atlantic salmon (Salmo solar) at 4 degrees C under different gaseous atmospheres (% CO2/O-2/N-2): 0/0/100 (A), air (B), 60/0/40 (C) or 60/40/0 (D). First, an exploratory analysis was performed to optimize the model tunings and to consequently model salmon spoilage under 100% N-2 (A). Based on the obtained results, a systematic spoilage characterization protocol was established and used for identifying potential volatile spoilage indicators under all tested storage conditions. In conclusion, LDA could be used for extracting sets of underlying VOC profiles and identifying those signifying salmon spoilage, giving rise to an extensive discussion regarding the key points associated with model tuning and/or spoilage analysis. The identified compounds were well in accordance with a previously established approach based on partial least squares regression analysis (PLS). Overall, the outcomes of the study not only reflect the promising potential of LDA in spoilage characterization, but also provide several new insights into the development of data-driven methods for food quality analysis.
Keywords
Food Science, Microbiology, General Medicine, Latent Dirichlet Allocation, Food quality, Metabolomics, Potential spoilage indicator, Volatile organic compound, VOLATILE ORGANIC-COMPOUNDS, MASS-SPECTROMETRY, IDENTIFICATION, MODULES, STORAGE, LDA

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.54 MB

Citation

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

MLA
Kuuliala, Lotta, et al. “Probabilistic Topic Modelling in Food Spoilage Analysis : A Case Study with Atlantic Salmon (Salmo Salar).” INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY, vol. 337, 2021, doi:10.1016/j.ijfoodmicro.2020.108955.
APA
Kuuliala, L., Perez Fernandez, R., Tang, M., Vanderroost, M., De Baets, B., & Devlieghere, F. (2021). Probabilistic topic modelling in food spoilage analysis : a case study with Atlantic salmon (Salmo salar). INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY, 337. https://doi.org/10.1016/j.ijfoodmicro.2020.108955
Chicago author-date
Kuuliala, Lotta, Raul Perez Fernandez, Mengzi Tang, Mieke Vanderroost, Bernard De Baets, and Frank Devlieghere. 2021. “Probabilistic Topic Modelling in Food Spoilage Analysis : A Case Study with Atlantic Salmon (Salmo Salar).” INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY 337. https://doi.org/10.1016/j.ijfoodmicro.2020.108955.
Chicago author-date (all authors)
Kuuliala, Lotta, Raul Perez Fernandez, Mengzi Tang, Mieke Vanderroost, Bernard De Baets, and Frank Devlieghere. 2021. “Probabilistic Topic Modelling in Food Spoilage Analysis : A Case Study with Atlantic Salmon (Salmo Salar).” INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY 337. doi:10.1016/j.ijfoodmicro.2020.108955.
Vancouver
1.
Kuuliala L, Perez Fernandez R, Tang M, Vanderroost M, De Baets B, Devlieghere F. Probabilistic topic modelling in food spoilage analysis : a case study with Atlantic salmon (Salmo salar). INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY. 2021;337.
IEEE
[1]
L. Kuuliala, R. Perez Fernandez, M. Tang, M. Vanderroost, B. De Baets, and F. Devlieghere, “Probabilistic topic modelling in food spoilage analysis : a case study with Atlantic salmon (Salmo salar),” INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY, vol. 337, 2021.
@article{8685346,
  abstract     = {{Probabilistic topic modelling is frequently used in machine learning and statistical analysis for extracting latent information from complex datasets. Despite being closely associated with natural language processing and text mining, these methods possess several properties that make them particularly attractive in metabolomics applications where the applicability of traditional multivariate statistics tends to be limited. The aim of the study was thus to introduce probabilistic topic modelling more specifically, Latent Dirichlet Allocation (LDA) in a novel experimental context: volatilome-based (sea) food spoilage characterization. This was realized as a case study, focusing on modelling the spoilage of Atlantic salmon (Salmo solar) at 4 degrees C under different gaseous atmospheres (% CO2/O-2/N-2): 0/0/100 (A), air (B), 60/0/40 (C) or 60/40/0 (D). First, an exploratory analysis was performed to optimize the model tunings and to consequently model salmon spoilage under 100% N-2 (A). Based on the obtained results, a systematic spoilage characterization protocol was established and used for identifying potential volatile spoilage indicators under all tested storage conditions. In conclusion, LDA could be used for extracting sets of underlying VOC profiles and identifying those signifying salmon spoilage, giving rise to an extensive discussion regarding the key points associated with model tuning and/or spoilage analysis. The identified compounds were well in accordance with a previously established approach based on partial least squares regression analysis (PLS). Overall, the outcomes of the study not only reflect the promising potential of LDA in spoilage characterization, but also provide several new insights into the development of data-driven methods for food quality analysis.}},
  articleno    = {{108955}},
  author       = {{Kuuliala, Lotta and Perez Fernandez, Raul and Tang, Mengzi and Vanderroost, Mieke and De Baets, Bernard and Devlieghere, Frank}},
  issn         = {{0168-1605}},
  journal      = {{INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY}},
  keywords     = {{Food Science,Microbiology,General Medicine,Latent Dirichlet Allocation,Food quality,Metabolomics,Potential spoilage indicator,Volatile organic compound,VOLATILE ORGANIC-COMPOUNDS,MASS-SPECTROMETRY,IDENTIFICATION,MODULES,STORAGE,LDA}},
  language     = {{eng}},
  pages        = {{13}},
  title        = {{Probabilistic topic modelling in food spoilage analysis : a case study with Atlantic salmon (Salmo salar)}},
  url          = {{http://dx.doi.org/10.1016/j.ijfoodmicro.2020.108955}},
  volume       = {{337}},
  year         = {{2021}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: