Predicting methionine and lysine contents in soybean meal and fish meal using a group method of data handling-type neural network

  1. Mottaghitalab, Majid 1
  2. Nikkhah, Mohsen 1
  3. Darmani-Kuhi, Hassan 1
  4. López, Secundino 2
  5. France, James 3
  1. 1 University of Guilan, Faculty of Agricultural Science, Dept. Animal Science. PO Box 41635-1314, Rasht
  2. 2 Universidad de León, Instituto de Ganadería de Montaña (CSIC-ULE), Dept. Producción Animal. 24071 León
  3. 3 University of Guelph Centre for Nutrition Modelling, Department of Animal and Poultry Science, Guelph ON, N1G 2W1
Show affiliations +
Journal:
Spanish journal of agricultural research

ISSN: 1695-971X,  2171-9292

Year of publication: 2015

Volume: 13

Issue: 1

Type: Article

DOI: 10.5424/SJAR/2015131-5877 DIALNET GOOGLE SCHOLAR lock_openDialnet editor

More publications in: Spanish journal of agricultural research

Abstract

Artificial neural network models offer an alternative to linear regression analysis for predicting the amino acid content of feeds from their chemical composition. A group method of data handling-type neural network (GMDH-type NN), with an evolutionary method of genetic algorithm, was used to predict methionine (Met) and lysine (Lys) contents of soybean meal (SBM) and fish meal (FM) from their proximate analyses (i.e. crude protein, crude fat, crude fibre, ash and moisture). A data set with 119 data lines for Met and 116 lines for Lys was used to develop GMDH-type NN models with two hidden layers. The data lines were divided into two groups to produce training and validation sets. The data sets were imported into the GEvoM software for training the networks. The predictive capability of the constructed models was evaluated by their abilities to estimate the validation data sets accurately. A quantitative examination of goodness of fit for the predictive models was made using a number of precision, concordance and bias statistics. The statistical performance of the models developed revealed close agreement between observed and predicted Met and Lys contents for SBM and FM. The results of this study clearly illustrate the validity of GMDH-type NN models to estimate accurately the amino acid content of poultry feed ingredients from their chemical composition.

Bibliographic References

  • References
  • Ahmadi H, Golian A, Mottaghitalab M, Nariman-Zadeh N, 2008. Prediction model for true metabolizable energy of feather meal and poultry offal meal using group method of data handling-type neural network. Poultry Sci 87: 1909-1912. http://dx.doi.org/10.3382/ps.2007-00507
  • AOAC, 1990. Official Methods of Analysis, 15th ed. Association of Official Analytical Chemists, Arlington, VA, USA.
  • Baker DH, Han Y, 1994. Ideal amino acid profile for chicks during the first weeks post-hatching. Poultry Sci 73: 1441-1447. http://dx.doi.org/10.3382/ps.0731441
  • Bibby J, Toutenburg H, 1977. Prediction and improved estimation in linear models. John Wiley and Sons, London, UK.
  • Bimbo AP, Crowther JB, 1992. Fish meal and oil: current uses. J Am Oil Chem Soc 69: 221-227. http://dx.doi.org/10.1007/BF02635890
  • Cravener TL, Roush WB, 1999. Improving neural network prediction of amino acid levels in feed ingredients: advanced optimization. Poultry Sci 78: 983-991. http://dx.doi.org/10.1093/ps/78.7.983
  • Cravener TL, Roush WB, 2001. Prediction of amino acid profiles in feed ingredients: genetic algorithm calibration of artificial neural networks. Anim Feed Sci Technol 90: 131-141. http://dx.doi.org/10.1016/S0377-8401(01)00219-X
  • Dayhoff JE, De Leo JM, 2001. Artificial neural networks: opening the black box. Cancer 91 (Suppl 8): 1615-1635.
  • Degussa Corporation, 1990. The amino acid composition of feedstuffs. Degussa Corporation, Allendale, NJ, USA.
  • Faridi A, Mottaghitalab M, Darmani Kuhi H, France J, Ahamadi H, 2011. Predicting carcass energy content and composition in broilers using the group method of data handling-type neural networks. J Agric Sci 149: 249-254. http://dx.doi.org/10.1017/S002185961000105X
  • Faridi A, Golian A, France J, 2012. Evaluating the egg production of broiler breeder hens in response to dietary nutrient intake from 31 to 60 weeks of age through neural network models. Can J Anim Sci 92: 473-481. http://dx.doi.org/10.4141/cjas2012-020
  • Faridi A, France J, Golian A, 2013a. Neural network models for predicting early egg weight in broiler breeder hens. J App Poultry Res 22: 1-8. http://dx.doi.org/10.3382/japr.2011-00446
  • Faridi A, Golian A, France J, Heravi Mousavi A, 2013b. Study of broiler chicken responses to dietary protein and lysine using neural network and response surface models. Br Poultry Sci 54: 524-530. http://dx.doi.org/10.1080/00071668.2013.803517
  • Farrow SJ, 1984. The GMDH algorithm. In: Self-organizing methods in modeling: GMDH type algorithms (Farrow SJ, ed.). Marcel Dekker, NY, USA. pp: 1-24.
  • Fickler J, 1995. The amino acid composition of feedstuffs. Degussa Corporation, Ridgefield Park, NJ, USA.
  • Fontaine J, Horr J, Schirmer B, 2001. Near-infrared reflectance spectroscopy enables the fast and accurate prediction of the essential amino acid contents in soy, rapeseed meal, sunflower meal, peas, fishmeal, meat meal products, and poultry meal. J Agric Food Chem 49: 57-66. http://dx.doi.org/10.1021/jf000946s
  • GEvoM, 2014. GMDH-type neural network designed by an evolutionary method of modelling. Available at: http://research.guilan.ac.ir/gevom/.
  • Heaton J, 2008. Introduction to neural networks for Java, second edition. Heaton Res. Inc., St. Louis, MO, USA.
  • Ivakhnenko AG, 1971. Polynomial theory of complex systems. IEEE T Syst Man Cyb SMC-1(4): 364-378. http://dx.doi.org/10.1109/TSMC.1971.4308320
  • Kovalenko, IV, Rippke GR, Hurburgh CR, 2006, Determination of amino acid composition of soybeans (Glycine max) by near-infrared spectroscopy. J Agric Food Chem 54: 3485−3491. http://dx.doi.org/10.1021/jf052570u
  • Lemke F, Müller JA, 2003. Medical data analysis using self-organizing data mining technologies. Syst Anal Model Sim 43: 1399-1408. http://dx.doi.org/10.1080/02329290290027337
  • Lin LIK, 1989. A concordance correlation coefficient to evaluate reproducibility. Biometrics 45: 255−268. http://dx.doi.org/10.2307/2532051
  • Mendes AA, Watkins SE, England JA, Saleh EA, Waldroup AL, Waldroup PW, 1997. Influence of dietary lysine levels and arginine:lysine ratios on performance of broilers exposed to heat or cold stress during the period of three to six weeks of age. Poultry Sci 76: 472-481.http://dx.doi.org/10.1093/ps/76.3.472
  • Monsanto, 1986a. Amino acids in feed ingredients and their predictability, part I. Monsanto Nutrition Update, Vol. 4:2. Monsanto, St. Louis, MO, USA.
  • Monsanto, 1986b. Amino acids in feed ingredients and their predictability, part II: animal by-products. Monsanto Nutrition Update, Vol. 4:3. Monsanto, St. Louis, MO, USA.
  • Monsanto, 1986c. Amino acids in feed ingredients and their predictability, part III: grain-based ingredients. Monsanto Nutrition Update, Vol. 4:4. Monsanto, St. Louis, MO, USA.
  • Mottaghitalab M, Faridi A, Darmani-Kuhi H., France J, Ahmadi H, 2010. Predicting caloric and feed efficiency in turkeys using the group method of data handling-type neural networks. Poultry Sci 89: 1325-1331. http://dx.doi.org/10.3382/ps.2009-00490
  • Müller JA, Lemke F, 2000. Self-organising data mining: an intelligent approach to extract knowledge from data. Libri Publ., Hamburg, Germany.
  • Nariman-Zadeh N, Darvizeh A, Jamali A, Moieni A, 2005. Evolutionary design of generalized polynomial neural networks for modeling and prediction of explosive forming process. J Mater Process Tech 164-165: 1561-1571. http://dx.doi.org/10.1016/j.jmatprotec.2005.02.020
  • NRC, 1994. Nutrient requirements of poultry, 9th rev. ed. National Research Council, National Academy Press, Washington DC, USA.
  • Oberstone J, 1990. Management science - Concepts, insights and applications. West Publ. Co., NY, USA.
  • Pérez-Marín DC, Garrido-Varo A, Guerrero-Ginel JE, Gómez-Cabrera A, 2004. Near-infrared reflectance spectroscopy (NIRS) for the mandatory labelling of compound feedingstuffs: chemical composition and open-declaration. Anim Feed Sci Technol 116: 333-349. http://dx.doi.org/10.1016/j.anifeedsci.2004.05.002
  • Roush WB, Kochera-Kirby Y, Cravener TL, Wideman Jr RF, 1996. Artificial neural network prediction of ascites in broilers. Poultry Sci 75: 1479-1487. http://dx.doi.org/10.3382/ps.0751479
  • Roush WB, Cravener TL, 1997. Artificial neural network prediction of amino acid levels in feed ingredients. Poultry Sci 76:721-727. http://dx.doi.org/10.1093/ps/76.5.721
  • Seginer I, Boulard T, Bailey BJ, 1994. Neural network models of the greenhouse climate. J Agric Eng Res 59: 203-216. http://dx.doi.org/10.1006/jaer.1994.1078
  • Steel, RGD, Torrie, JH, 1981. Principles and procedures of statistics, A biometrical approach, 2nd ed. McGraw-Hill, Singapore.
  • Vallejo-Cordoba B, Arteaga GE, Nakai S, 1995. Predicting milk shelf-life based on artificial neural networks and headspace gas chromatographic data. J Food Sci 60: 885-888. http://dx.doi.org/10.1111/j.1365-2621.1995.tb06253.x
  • Van Kempen T, Bodin JC, 1998. Near-infrared reflectance spectroscopy (NIRS) appears to be superior to nitrogen-based regression as a rapid tool in predicting the poultry digestible amino acid content of commonly used feedstuffs. Anim Feed Sci Technol 76: 139-147. http://dx.doi.org/10.1016/S0377-8401(98)00207-7
  • Ward Systems Group, 1993. Neuroshell 2 user's manual. Ward Systems Group, Inc., Frederick, MD, USA.
Data source: Dialnet