A machine learning workflow for raw food spectroscopic classification in a future industry.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
08 07 2020
08 07 2020
Historique:
received:
30
10
2019
accepted:
07
06
2020
entrez:
10
7
2020
pubmed:
10
7
2020
medline:
22
12
2020
Statut:
epublish
Résumé
Over the years, technology has changed the way we produce and have access to our food through the development of applications, robotics, data analysis, and processing techniques. The implementation of these approaches by the food industry ensure quality and affordability, reducing at the same time the costs of keeping the food fresh and increase productivity. A system, as the one presented herein, for raw food categorization is needed in future food industries to automate food classification according to type, the process of algorithm approaches that will be applied to every different food origin and also for serving disabled people. The purpose of this work was to develop a machine learning workflow based on supervised PLS regression and SVM classification, towards automated raw food categorization from FTIR. The system exhibited high efficiency in multi-class classification of 7 different types of raw food. The selected food samples, were diverse in terms of storage conditions (temperature, storage time and packaging), while the variability within each food was also taken into account by several different batches; leading in a classifier able to embed this variation towards increased robustness and efficiency, ready for real life applications targeting to the digital transformation of the food industry.
Identifiants
pubmed: 32641761
doi: 10.1038/s41598-020-68156-2
pii: 10.1038/s41598-020-68156-2
pmc: PMC7343812
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
11212Références
White Paper on Food SafetyChapter 2 (2000) COM (1999) 719 final).
Vecchio, R. & Borrello, M. Measuring food preferences through experimental auctions: a review. Food Res. Int. 116, 1113–1120 (2019).
doi: 10.1016/j.foodres.2018.09.055
Mylona, K. et al. (Publications Office of the European Union, 2016).
FoodForLife https://etp.fooddrinkeurope.eu/news-and-publications/news/8-implementation-action-plan-2018.html . (January 10, 2020).
Nychas, G.-J.E., Panagou, E. Z. & Mohareb, F. Novel approaches for food safety management and communication. Curr. Opinion Food Sci. 12, 13–20 (2016).
doi: 10.1016/j.cofs.2016.06.005
He, H.-J. & Sun, D.-W. Microbial evaluation of raw and processed food products by visible/infrared, Raman and fluorescence spectroscopy. Trends Food Sci. Technol. 46, 199–210 (2015).
doi: 10.1016/j.tifs.2015.10.004
Tahir, H. E. et al. Recent progress in rapid analyses of vitamins, phenolic, and volatile compounds in foods using vibrational spectroscopy combined with chemometrics: a review. Food Anal. Methods 12, 2361–2382 (2019).
doi: 10.1007/s12161-019-01573-w
Pathmanaban, P., Gnanavel, B. K. & Anandan, S. S. Recent application of imaging techniques for fruit quality assessment. Trends Food Sci. Technol. 94, 32–42 (2019).
doi: 10.1016/j.tifs.2019.10.004
Pu, H., Lin, L. & Sun, D.-W. Principles of hyperspectral microscope imaging techniques and their applications in food quality and safety detection: a review. Compr. Rev. Food Sci. Food Saf. 18, 853–866 (2019).
doi: 10.1111/1541-4337.12432
Nychas, G.-J.E., Skandamis, P. N., Tassou, C. C. & Koutsoumanis, K. P. Meat spoilage during distribution. Meat Sci. 78, 77–89 (2008).
doi: 10.1016/j.meatsci.2007.06.020
Ropodi, A. I., Panagou, E. Z. & Nychas, G. J. E. Data mining derived from food analyses using non-invasive/non-destructive analytical techniques; determination of food authenticity, quality & safety in tandem with computer science disciplines. Trends Food Sci. Technol. 50, 11–25 (2016).
doi: 10.1016/j.tifs.2016.01.011
Estelles-Lopez, L. et al. An automated ranking platform for machine learning regression models for meat spoilage prediction using multi-spectral imaging and metabolic profiling. Food Res. Int. (Ottawa Ont.) 99, 206–215 (2017).
doi: 10.1016/j.foodres.2017.05.013
PhasmaFOOD https://phasmafood.eu/ . (January 10, 2020).
Food, T.S. https://www.tomra.com/en/sorting/food . (January 10, 2020).
Kutsanedzie, F. Y. H., Guo, Z. & Chen, Q. Advances in nondestructive methods for meat quality and safety monitoring. Food Rev. Int. 35, 536–562 (2019).
doi: 10.1080/87559129.2019.1584814
Kumar, Y. & Chandrakant Karne, S. Spectral analysis: a rapid tool for species detection in meat products. Trends Food Sci. Technol. 62, 59–67 (2017).
doi: 10.1016/j.tifs.2017.02.008
Barnes, R. J., Dhanoa, M. S. & Lister, S. J. Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Appl. Spectrosc. 43, 772–777 (1989).
doi: 10.1366/0003702894202201
Guo, Q., Wu, W. & Massart, D. L. The robust normal variate transform for pattern recognition with near-infrared data. Anal. Chim. Acta 382, 87–103 (1999).
doi: 10.1016/S0003-2670(98)00737-5
Wold, S., Sjöström, M. & Eriksson, L. PLS-regression: a basic tool of chemometrics. Chemomet. Intell. Lab. Syst. 58, 109–130 (2001).
doi: 10.1016/S0169-7439(01)00155-1
Hearst, M. A. Support vector machines. IEEE Intell. Syst. 13, 18–28 (1998).
doi: 10.1109/5254.708428
Doulgeraki, A. I., Ercolini, D., Villani, F. & Nychas, G.-J.E. Spoilage microbiota associated to the storage of raw meat in different conditions. Int. J. Food Microbiol. 157, 130–141 (2012).
doi: 10.1016/j.ijfoodmicro.2012.05.020
Koutsoumanis, K., Stamatiou, A., Skandamis, P. & Nychas, G. J. E. Development of a microbial model for the combined effect of temperature and pH on spoilage of ground meat, and validation of the model under dynamic temperature conditions. Appl. Environ. Microbiol. 72, 124–134 (2006).
doi: 10.1128/AEM.72.1.124-134.2006
Bruckner, S., Albrecht, A., Petersen, B. & Kreyenschmidt, J. Influence of cold chain interruptions on the shelf life of fresh pork and poultry. Int. J. Food Sci. Technol. 47, 1639–1646 (2012).
doi: 10.1111/j.1365-2621.2012.03014.x
Brock, T. D. & Rose, A. H. In Methods in Microbiology, 3 (eds Norris, J. R. & Ribbons, D. W.) 161–168 (Academic Press, Cambridge, 1969).
Joubert, W. A. & Britz, T. J. Characterization of aerobic, facultative anaerobic, and anaerobic bacteria in an acidogenic phase reactor and their metabolite formation. Microb. Ecol. 13, 159–168 (1987).
doi: 10.1007/BF02011251
Argyri, A. A. et al. A comparison of Raman and FT-IR spectroscopy for the prediction of meat spoilage. Food Control 29, 461–470 (2013).
doi: 10.1016/j.foodcont.2012.05.040
Papadopoulou, O., Panagou, E. Z., Tassou, C. C. & Nychas, G. J. E. Contribution of Fourier transform infrared (FTIR) spectroscopy data on the quantitative determination of minced pork meat spoilage. Food Res. Int. 44, 3264–3271 (2011).
doi: 10.1016/j.foodres.2011.09.012
Rahman, U. U., Sahar, A., Pasha, I., Rahman, S. U. & Ishaq, A. Assessing the capability of Fourier transform infrared spectroscopy in tandem with chemometric analysis for predicting poultry meat spoilage. PeerJ 6, e5376 (2018).
doi: 10.7717/peerj.5376
Wu, T.-F., Lin, C.-J. & Weng, R.C. Probability Estimates for Multi-class Classification by Pairwise Coupling, Vol 5. (JMLR.org, 2004).
Ha, J. et al. Identification of pork adulteration in processed meat products using the developed mitochondrial dna-based primers. Korean J. Food Sci. Anim. Resour. 37, 464–468 (2017).
doi: 10.5851/kosfa.2017.37.3.464
Tian, X., Wang, J., Shen, R., Ma, Z. & Li, M. Discrimination of pork/chicken adulteration in minced mutton by electronic taste system. Int. J. Food Sci. Technol. 54, 670–678 (2019).
doi: 10.1111/ijfs.13977
Yacoub, H. A. & Sadek, M. A. Identification of fraud (with pig stuffs) in chicken-processed meat through information of mitochondrial cytochrome b. Mitochondrial DNA A 28, 855–859 (2017).
doi: 10.1080/24701394.2016.1197220
Hoaglin, D. C., Mosteller, F. & Tukey, J. W. Understanding Robust and Exploratory Data Analysis (Wiley, Hoboken, 2000).
Tsakanikas, P. et al. A unified spectra analysis workflow for the assessment of microbial contamination of ready-to-eat green salads: comparative study and application of non-invasive sensors. Comput. Electron. Agric. 155, 212–219 (2018).
doi: 10.1016/j.compag.2018.10.025
Jolliffe, I. T. Principal Component Analysis 2nd edn. (Springer, New York, 2002).
Ellies-Oury, M. P. et al. Statistical model choice including variable selection based on variable importance: a relevant way for biomarkers selection to predict meat tenderness. Sci. Rep. 9, 10014 (2019).
doi: 10.1038/s41598-019-46202-y
Theodoridis, S. & Koutroumbas, K. Pattern Recognition 4th edn. (Academic Press, Cambridge, 2009).
https://scikit-learn.org/stable/modules/multiclass.html (January 10, 2020).
Pedregosa, F. et al. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Pavlidis, D. E., Mallouchos, A., Ercolini, D., Panagou, E. Z. & Nychas, G.-J.E. A volatilomics approach for off-line discrimination of minced beef and pork meat and their admixture using HS-SPME GC/MS in tandem with multivariate data analysis. Meat Sci. 151, 43–53 (2019).
doi: 10.1016/j.meatsci.2019.01.003
Tsakanikas, P., Pavlidis, D., Panagou, E. & Nychas, G.-J. Exploiting multispectral imaging for non-invasive contamination assessment and mapping of meat samples. Talanta 161, 606–614 (2016).
doi: 10.1016/j.talanta.2016.09.019
Tsakanikas, P., Pavlidis, D. & Nychas, G.-J. High throughput multispectral image processing with applications in food science. PLoS ONE 10, e0140122 (2015).
doi: 10.1371/journal.pone.0140122
Fengou, L.-C. et al. Estimation of minced pork microbiological spoilage through fourier transform infrared and visible spectroscopy and multispectral vision technology. Foods 8, 238 (2019).
doi: 10.3390/foods8070238
Lytou, A. E., Panagou, E. Z. & Nychas, G.-J.E. Effect of different marinating conditions on the evolution of spoilage microbiota and metabolomic profile of chicken breast fillets. Food Microbiol. 66, 141–149 (2017).
doi: 10.1016/j.fm.2017.04.013
Fengou, L.-C. et al. Evaluation of Fourier transform infrared spectroscopy and multispectral imaging as means of estimating the microbiological spoilage of farmed sea bream. Food Microbiol. 79, 27–34 (2019).
doi: 10.1016/j.fm.2018.10.020
Panagou, E. Z., Papadopoulou, O., Carstensen, J. M. & Nychas, G.-J.E. Potential of multispectral imaging technology for rapid and non-destructive determination of the microbiological quality of beef filets during aerobic storage. Int. J. Food Microbiol. 174, 1–11 (2014).
doi: 10.1016/j.ijfoodmicro.2013.12.026