Validation of two discriminant strategies applied to NIRS data spectra for detection of animal meals in feedstuffs

  • A. Soldado Regional Institute for Research and Agro-Food Development (SERIDA). Villaviciosa (Asturias).
  • J. R. Quevedo Artificial Intelligent Centre. University of Oviedo. Campus de Viesques. Gijón (Asturias).
  • A. Bahamonde Artificial Intelligent Centre. University of Oviedo. Campus de Viesques. Gijón (Asturias).
  • S. Modroño Regional Institute for Research and Agro-Food Development (SERIDA). Villaviciosa (Asturias).
  • A. Martinez-Fernandez Regional Institute for Research and Agro-Food Development (SERIDA). Villaviciosa (Asturias).
  • F. Vicente Regional Institute for Research and Agro-Food Development (SERIDA). Villaviciosa (Asturias).
  • D. Perez-Marin Faculty of Agriculture and Forestry Engineering. ETSIAM. Campus de Rabanales. University of Cordoba.
  • A. Garrido-Varo Faculty of Agriculture and Forestry Engineering. ETSIAM. Campus de Rabanales. University of Cordoba.
  • J. E. Guerrero Faculty of Agriculture and Forestry Engineering. ETSIAM. Campus de Rabanales. University of Cordoba.
  • B. de la Roza-Delgado Regional Institute for Research and Agro-Food Development (SERIDA). Villaviciosa (Asturias).
Keywords: animal nutrition, compoundfeeds, discriminant models, NIR spectroscopy, partial least square, support vector machine

Abstract

For developing qualitative or quantitative applications with spectroscopic data, such as near infrared spectroscopy (NIRS), different methodologies have been proposed in the mathematical statistical and computer science literature. Useful chemometrical alternatives have emerged, such as support vector machines (SVM), widely used for modeling multivariate and non-linear systems. These methods are usually compared using the classification performance and the success of results. The aim of the present work was to develop and validate a robust, accurate and fast discriminant methodology based on NIRS data to detect presence of animal meals in feedstuffs. A linear method, modified partial least square (PLS) analysis and one non-linear method (SVM) were studied. Results showed that modified PLS model allows obtaining coefficients of determination for cross validation around 0.97. Applying SVM strategy no false negatives were detected during training step. With both strategies the lowest percentage of misclassified samples on external validation was achieved with SVM, 0% with certified standard samples containing from 0.05% to 4% of animal meals. These results show SVM strategy as a robust method of classification for detecting animal meals in feedstuffs using NIRS methodology.

Downloads

Download data is not yet available.

References

BARNES R.J., DHANOA M.S., LISTER S.J., 1993. Correction of the description of standard normal variate (SNV) and De-Trend transformation in practical spectroscopy with applications in food and beverage analysis. J Near Infrared Spec 1(3), 185-186.

CHIH-CHUNG CH., CHIH-JEN L., 2001. LIBSVM : a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm

COGDILL R.P., DARDENNE P., 2004. Least-squares support vector machines for chemometrics: an introduction and evaluation. J Near Infrared Spec 12, 93-100.

DE LA ROZA-DELGADO B., 2005. Near Infrared Spectroscopy for enforcement of European Legislation concerning the use of animal by-products in animal feeds. Termes. Biotechnol Agron Soc Environ 9(1), 3-9.

DE LA ROZA-DELGADO B., SOLDADO A., MODROÑO S., MARTÍNEZ A., VICENTE F., PÉREZ-MARÍN D.C., GARRIDO-VARO A., GUERRERO J.E., BAYÓN G.F., QUEVEDO J.R., 2007a. NIRS data and support vector machine (SVM) as tool to minimise the risk of false negatives to detect animal meals in feedstuffs. In: Near in action-making a difference. Proceedings of the 12th International Conference on Near infrared Spectroscopy-2005 (Burling-Claridge G.R., Holroyd S.E. and Summer R.M.W., eds). Auckland, New Zealand. pp. 133-139.

DE LA ROZA-DELGADO B., SOLDADO A., MARTÍNEZ-FERNÁNDEZ A., VICENTE, F., GARRIDO-VARO A., PÉREZ–MARÍN D., DE LA HABA M.J., GUERRERO-GINEL J.E., 2007b. Application of near infrared microscopy (NIRM) for the detection of meat and bone meals in animal feeds. A tool for food and feed safety. Food Chem 105, 1164-1170. http://dx.doi.org/10.1016/j.foodchem.2007.02.041

EC, 2000. Commission Decision 2000/766/EC of 4 December 2000 concerning certain protection measures with regard to transmissible spongiform encephalopaties and the feeding of animal protein. European Commission, Official Journal L 306, 07/12/2000. pp. 32-33.

EC, 2003. Commission Directive 2003/126/EC of 23 December 2003 on the analytical method for the determination of constituents of animal origin for the official control of feedingstuffs. European Commission, Official Journal L 339/78, 24/12/2003. pp. 78-84.

EC, 2008. Commission Regulation No 956/2008 of 29 September 2008. European Commission, Official Journal L 260/8, 30/9/2008.

Fernández-Ahumada E., Fearn T., Gómez A., Vallesquino P., Guerrero J. E., Pérez-Marín D., Garrido-Varo A., 2008. Reducing NIR prediction errors with nonlinear methods and large population of intact compound feedstuffs. Meas Sci Technol 19, 085601. http://dx.doi.org/10.1088/0957-0233/19/8/085601

Fernández-Ibáñez V, Fearn T., Montañés E., Quevedo J.R., Soldado A., De La Roza-Delgado B., 2010. Improving the discriminatory power of a near infrared microscopy spectral library with a support vector machine classifier. Appl Spectrosc 64(1), 46-52. http://dx.doi.org/10.1366/000370210790572124

Fernández-Pierna J.A., Baeten V., Michoette R., Cogdill R.P., Dardenne P., 2004. Combination of support vector machines (SVM) and near-infrared (NIR) imaging spectroscopy for the detection of meat and bone meal (MBM) in compound feeds. J Chemometr 18, 341-349. http://dx.doi.org/10.1002/cem.877

Garrido-Varo A., Pérez–Marín D., Guerrero J. E., Gómez-Cabrera A., De La Haba M. J., Bautista J., Soldado A., Vicente F., Martínez A., De La Roza-Delgado B., 2005. Near Infrared spectroscopy for enforcement of European Legislation concerning the use of animal by-products in animal feeds. Termes Biotechnol Agron Soc Environ 9 (1), 3-9.

Joachims T., 1998. Making large-scale support vector machine learning practical Advances in Kernel Methods: Support Vector Machines (Scholkopf B., Burges C., Smola A., eds.) MIT Press, Cambridge, MA, USA.

Murray I., Aucott L.S, Pie I.H., 2001. Use of discriminant analysis on visible and near infrared reflectance spectra to detect adulteration of fishmeal with meat and bone meal. J Near Infrared Spec 9, 297-311. http://dx.doi.org/10.1255/jnirs.315

Naes T., Isaksson T., Fearn T., Davies T., 2002. A user-friendly guide to multivariate calibration and classification. NIR Publ, Chichester, West Sussex, UK. pp. 221-259.

Perez-Marín D., Garrido A., Guerrero J., Murray I., Puigdomenech A., Dardenne P., Baeten V., Zegers J., 2004. Detection and quantification of mammalian meat and bone meal in compound feedingstuffs using NIR. In: Near infrared spectroscopy: Proc. 11th International Conference (Davies A.M.C., Garrido-Varo A., eds.), Norfolk, UK. pp. 667-671.

Pérez-Marín D., Garrido-Varo A., Guerrero J. E., Fearn T., Davies A.M. C., 2008a. Advanced nonlinear approaches for predicting the ingredient composition in compound feedingstuffs by near-infrared reflection spectroscopy. Appl Spectrosc 62 (5), 536-541. http://dx.doi.org/10.1366/000370208784344389

Pérez–Marín D., Garrido-Varo A., Guerrero J.E., Gómez A., Soldado A., De La Roza-Delgado B., 2008b. External validation and transferability of NIRS models developed for detecting and quantifying MBM in compound feeding stuffs. J Food Quality 31, 96–107. http://dx.doi.org/10.1111/j.1745-4557.2007.00186.x

Prince M.J., Bailey J.A., Barrowman P.R., Bishop K.J., Campbell G.R., Wood J.M., 2003. Bovine spongiform encephalopathy. Rev Sci Tech Off Int Epiz 22(1), 37-60. http://dx.doi.org/10.20506/rst.22.1.1389

Sellier P., 2003. Protein nutrition for ruminants in European countries, in the light of animal feedings regulations, linked to bovine spongiform encephalopathy. Rev Sci Tech Off Int Epiz 22(1), 259-269. http://dx.doi.org/10.20506/rst.22.1.1395

Shenk J.S., Westerhaus M.O., 1991. New standardization and calibration procedure for NIRS analytical systems. Crop Sci 31, 1548-1555. http://dx.doi.org/10.2135/cropsci1991.0011183X003100060034x

Shenk J.S., Westerhaus M.O., 1993. Analysis of agriculture and food products by near infrared reflectance spectroscopy. Monograph, Infrasoft International, Port Matilda, PA, USA. 118 pp.

Vanciuc O., 2007. Applications of support vector machines in chemistry Rev Comput Chem 23, 291-400.

Van Raamsdonk L.W.D., Von Holst C., Baeten V., Berben G., Boix A., De Jong J., 2007. New developments in the detection and identification of processed animal proteins in feeds. Anim Feed SciTech 133, 63-83. http://dx.doi.org/10.1016/j.anifeedsci.2006.08.004

Vapnik V., 1998. Statistical learning theory. Wiley Intersci, NY, USA.

Von Holst C., Baeten V., Boix A., Slowikowski B., Fernández Pierna J.A., Tirendi S., Dardenne P., 2008. Transferability study of a near-infrared microscopic method for the detection of banned meat and bone meal in feedingstuffs. Anal Bioanal Chem 392, 313-317. http://dx.doi.org/10.1007/s00216-008-2232-4

WESTON J., ELISSEEFF A., BAKIR G., SINZ F., 2006. Library of objects in Matlab. Available in http://www.kyb.tuebingen.mpg.de/bs/people/spider

Winisi II, 2000. The complete software solution using a single screen for routine analysis, robust calibrations, and networking manual, version 1.5. Foss-Tecator-Infrasoft International, Port Matilda, PA, USA.

How to Cite
Soldado, A., Quevedo, J. R., Bahamonde, A., Modroño, S., Martinez-Fernandez, A., Vicente, F., Perez-Marin, D., Garrido-Varo, A., Guerrero, J. E., & de la Roza-Delgado, B. (1). Validation of two discriminant strategies applied to NIRS data spectra for detection of animal meals in feedstuffs. Spanish Journal of Agricultural Research, 9(1), 41-49. https://doi.org/10.5424/sjar/20110901-138-10
Section
Agricultural engineering