Application of Neural Networks and Meta-Learners to Recognize Beef from OTM Cattle by Using Volatile Organic Compounds
- 126 Downloads
Cattle with age under 30 months (UTM) are usually slaughtered for human consumption to be not associated of the disease called mad cow. Though the age of the animal can generally be estimated by dentition, this method cannot be applied to a piece of meat from which the teeth have been removed. Since volatile organic compounds have been used to analyze food samples, this technique was used to recognize meat obtained from cattle aged over 30 months (OTM).
The monitoring of the volatile organic compounds (VOCs) released by UTM and OTM beef were done by using gas chromatography. A dataset with more than 500 chromatograms (each one with 17 VOCs fully identified) from fresh meat, refrigerated meat and vacuum-packaged meat was used to develop a classifier by using neural networks. Neural networks were trained with backpropagation, and then further optimized by using meta-learners.
Optimal configuration of the neural networks allowed discriminating between beef obtained from OTM or UTM cattle with accuracy close to 90 %. Results contrast favorably with more traditional statistical methods such as linear discriminant analysis (LDA), soft independent modeling of class analogies (SIMCA), partial least square discriminate analysis (PLS-DA), and support vector machines (SVM).
In conclusion, VOCs can be used as a fingerprint to recognize OTM beef from a pool of meat obtained indistinctly from fresh meat, refrigerated, or vacuum-packaged meat.
KeywordsBeef Meta learner Neural network Over 30 months Volatile organic compounds
The authors wish to thank DGIP -UTFSM by Grant 23.13.56 and CONICYT from Chile by FONDEF Grant D08i1102.
- Arredondo, T., & Ormazabal, W. (2013). Meta-learning framework applied in bioinformatics inference system design. International Journal of Data Mining and Bioinformatics, (In Press).Google Scholar
- Boser, B.E., Guyon, I.M., & Vapnik, V.N. (1992). A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning theory (Pittsburgh, PA, United States, July 27–29,1992). COLT’92. New York, NY: ACMGoogle Scholar
- Brereton, R. (2003). Chemometrics data analysis for the laboratory and chemical plant. Chichester: Wiley.Google Scholar
- Elmore, J. S., Warren, H. E., Mottram, D. S., Scollan, N. D., Enser, M., Richardson, R. I., & Wood, J. D. (2004). A comparison of the aroma volatiles and fatty acid compositions of grilled beef muscle from Aberdeen Angus and Holstein–Friesian steers fed diets based on silage or concentrates. Meat Science, 68, 27–33.CrossRefGoogle Scholar
- European Commission (2009). Commission Regulation (EC) No 620/ 2009 of 13 July 2009 providing for the administration of an import tariff quota for high-quality beef.Google Scholar
- Eriksson, L., Johansson, E., Kettaneh-Wold, N., Trygg, J., Wikstrom, C., & Wold, S. (2006). Multi and megavariate data analysis: Part I. Basic principles and applications (3rd ed.). Umea: Umetrics Academy.Google Scholar
- Haykin, S. (1998). Neural networks: a comprehensive foundation (2nd ed.). Upper Saddle River: Prentice Hall.Google Scholar
- Leiva, M., Arredondo, T.V., Candel, D., Dombrovskaia, L., Agulló, L., Seeger, M., & Vásquez, F. (2009). Feed-forward artificial neural network based inference system applied in bioinformatics data-mining. In: International Joint Conference on Neural Networks, Atlanta, pp. 1744–1749.Google Scholar
- Mitchell, T. (1997). Machine learning (1st ed.). New York: McGraw-Hill.Google Scholar
- Neelakanta, P. S. (1999). Information theoretic aspects of neural networks. Florida: CRC Press.Google Scholar
- Simon, H. (1983). Why should machines learn? In R. Michalski, J. Carbonell, & T. Mitchell (Eds.), Machine learning: an artificial intelligence approach (pp. 25–37). Palo Alto: Morgan Kaufmann.Google Scholar
- Toker, O. S., Yilmaz, M. T., Karaman, S., Dogan, M., & Kayacier, A. (2012). Adaptive neuro-fuzzy inference system and artificial neural network estimation of apparent viscosity of ice-cream mixes stabilized with different concentrations of xanthan gum. Applied Rheology, 22, 63918.Google Scholar
- Werbos, P. (1974) Beyond regression: new tools for prediction and analysis in the behavioral sciences. PhD dissertation, Harvard University.Google Scholar