Grasas y Aceites, Vol 63, No 3 (2012)

Neural networks to formulate special fats


https://doi.org/10.3989/gya.119011

R. K. Garcia
Laboratório de Óleos e Gorduras/FEA/UNICAMP, Brazil

K. Moreira Gandra
Laboratório de Óleos e Gorduras/FEA/UNICAMP, Brazil

J. M. Block
Departamento de Ciência e Tecnologia de Alimentos, CCA/UFSC, Brazil

D. Barrera-Arellano
Laboratório de Óleos e Gorduras/FEA/UNICAMP, Brazil

Abstract


Neural networks are a branch of artificial intelligence based on the structure and development of biological systems, having as its main characteristic the ability to learn and generalize knowledge. They are used for solving complex problems for which traditional computing systems have a low efficiency. To date, applications have been proposed for different sectors and activities. In the area of fats and oils, the use of neural networks has focused mainly on two issues: the detection of adulteration and the development of fatty products. The formulation of fats for specific uses is the classic case of a complex problem where an expert or group of experts defines the proportions of each base, which, when mixed, provide the specifications for the desired product. Some conventional computer systems are currently available to assist the experts; however, these systems have some shortcomings. This article describes in detail a system for formulating fatty products, shortenings or special fats, from three or more components by using neural networks (MIX). All stages of development, including design, construction, training, evaluation, and operation of the network will be outlined.

Keywords


Blending; Interesterified fats; Neural networks; Shortenings; Special fats

Full Text:


PDF

References


Anklam E, Bassani MR, Eiberger T. 1997. Characterization of cocoa butters and other vegetable fats by pyrolysis mass spectrometry. Fresen. J. Anal. Chem. 357, 981-984. http://dx.doi.org/10.1007/s002160050286

Arteaga GE, NakaiI S. 1993. Predicting protein functionality with artificial neural networks: foaming and emulsifying properties. J. Food Sci. 58, 1152-1156. http://dx.doi.org/10.1111/j.1365-2621.1993.tb06136.x

Barrera-Arellano D, Akamine EA, Garcia RKA, Gandra KM. 2011. Zero trans fats formulation through a neural network operated with five components: two soybean-soybean interesterified fats, palm, soybean and palm kernel oils. In: 9th Euro Fed Lipid Congress, Rotterdam, The Netherlands, Abstract.

Barrera-Arellano D, Block JM, Grimaldi R, Figueiredo MF, Gomide FAC, Almeida RR. 2005. Programa MIX— Software for the formulation of fats with neural networks. Register INPI 98003155, Campinas, Brazil.

Barbosa AH, Freitas MSR, Neves FA. 2005. Confiabilidade estrutural utilizando o método de Monte Carlo e redes neurais. Rev. Esc. de Minas 58, 247-255.

Barile D, Coisson JD, Arlorio M, Rinaldi M. 2006. Identification of production area of Ossolano Italian cheese with chemometric complex approach. Food Control 17, 197-206. http://dx.doi.org/10.1016/j.foodcont.2004.10.016

Berg EP, Engel BA, Forrest JC. 1998. Pork carcass composition derived from a neural network model of electromagnetic scans. J. Anim. Sci. 76, 18-22. PMid :9464879

Block JM, Barrera-Arellano D, Figueiredo MF, Gomide FC. 1997. Blending process optimization into special fat formulation by neural networks. J. Am. Oil Chem. Soc. 74, 1537-1541. http://dx.doi.org/10.1007/s11746-997-0073-5

Block JM, Barrera-Arellano D, Figueiredo MF, Gomide FC, Sauer L. 1999. Formulation of special fats by neural networks: A statistical approach. J. Am. Oil Chem. Soc. 76, 1357-1361. http://dx.doi.org/10.1007/s11746-999-0150-z

Block JM, Barrera-Arellano D, Almeida R, Gomide FC, Moretti RB. 2003. Formulación de grasas a través de redes neuronales: productos comerciales y producción en planta piloto. Grasas Aceites 54, 240-244.

Borggaard C, Madsen NT, Thodberg HH. 1996. In-line image analysis in the slaughter industry, illustrated by Beef Carcass Classification. Meat Sci. 43, 151-163. http://dx.doi.org/10.1016/0309-1740(96)00062-9

Brito LAL. 1994. Importancia de la instrumentación y computarización en programas de calidad total. Aceites y Grasas 15, 99-102.

Carrapiso A, Ventanas J, Jurado A, García C. 2001. An electronic nose to classify Iberian pig fats with different fatty acid composition. J. Am. Oil Chem. Soc. 78, 415-418. http://dx.doi.org/10.1007/s11746-001-0277-0

Cebula DJ, Smith KW. 1991. Differential scanning calorimetry of confectionery fats. Pure triglycerides: Effects of cooling and heating rate variation. J. Am. Oil Chem. Soc. 68, 591-595. http://dx.doi.org/10.1007/BF02660159

Cerqueira EO, Andrade JC, Poppi RJ, Mello C. 2001. Redes Neurais e suas aplicações em calibração multivariada. Quim. Nova 24, 864-873. http://dx.doi.org/10.1590/S0100-40422001000600025

Chiu MC, Gioielli LA, Grimaldi R. 2008. Lipídios estruturados obtidos a partir da mistura de gordura de frango, sua estearina e triacilgliceróis de cadeia média, II - pontos de amolecimento e fusão. Quim. Nova 31, 238-243. http://dx.doi.org/10.1590/S0100-40422008000200009

Cimpoiu C, Cristea V, Hosu A, Sandru M, Seserman L. 2011. Antioxidant activity prediction and classification of some teas using artificial neural networks. Food Chem. 127, 1323-1328. http://dx.doi.org/10.1016/j.foodchem.2011.01.091

Cheroutre-Vialette M, Lebert A. 2002. Application of recurrent neural network to predict bacterial growth in dynamic conditions. Int. J. Food Microbiol. 73, 107-118. http://dx.doi.org/10.1016/S0168-1605(01)00642-0

Da Cruz AG, Walter EHM, Cadena RS, Faria JAF, Bolini HMA, Franttini-Fileti AM. Monitoring the authenticity of low-fat yogurts by an artificial neural network. J. Dairy Sci. 92, 4797-4804. http://dx.doi.org/10.3168/jds.2009-2227 PMid :19762794

Daniels RL, Kim HJ, Min DB. 2006. Hydrogenation and interesterification effects on the oxidative stability and melting point of soybean oil. J. Agr. Food Chem. 54, 6011-6015. http://dx.doi.org/10.1021/jf053263r PMid :16881709

Eyng E, Fileti AMF. 2010. Control of absorption columns in the bioethanol process: Influence of measurement uncertainties. Eng. Appl. Artif. Intel. 23, 271-282. http://dx.doi.org/10.1016/j.engappai.2009.11.002

Erickson DR, Erickson MD. 1995. Hydrogenation and base stock formulation procedures, en Erickson DR (ed.) Pratical Handbook of Soybean Processing and Utilization. AOCS Press, Champaign, 218-238.

Gallegos-Infante JA, Rocha-Guzman NE, Gonzalez-Laredo RF, Rico-Martinez R. 2002. The Kinetics of crystalization of tripalmitin in olive oil: An artificial neural network approach. J. Food Lipids 9, 73-86. http://dx.doi.org/10.1111/j.1745-4522.2002.tb00210.x

Gandra, KM. 2011. Formulação de gorduras zero trans para recheio de biscoitos utilizando redes neurais. University of Campinas (UNICAMP). Campinas, Brazil.

Gandra KM, García RKA, Block JM, Barrera-Arellano D. 2009. Construction and training of a neural network for the formulation of specialty fats using interesterified fats. In: World Congress on Oils and Fats & 28th ISF Congress. Oils and fats essential for life - Program & Abstract Book, Sydney, p 117-118.

Garcia RKA. 2010. Formulação de gorduras para aplicação em margarinas zero trans com redes neurais a partir de gorduras interesterificadas. University of Campinas (UNICAMP). Campinas, Brazil.

García RKA, Gandra KM, Barrera-Arellano D. 2010. Formulação de blends para aplicação em margarinas zero trans por redes neurais baseado no SFC e ponto de fusão de gorduras comerciais. In: V Simpósio Internacional Tendências e Inovações em Tecnologia de Óleos e Gorduras, Campinas, Brazil.

Glassey J, Montague GA, Ward RD, Kara BV. 1994. Artificial neural networks based experimental design procedures for enhancing fermentation development. Biotechnol. Bioeng. 44, 397-405. http://dx.doi.org/10.1002/bit.260440402 PMid :18618773

Gomes HM, Awruch AM. 2004. Comparison of response surface and neural network with others methods for structural reliability analysis. Struct. Saf. 26, 49-67. http://dx.doi.org/10.1016/S0167-4730(03)00022-5

Goodacre R, Kell DB, Bianchi G. 1993. Rapid assessment of the adulteration of virgin olive oils by other seed oils using pyrolysis mass-spectrometry and artificial neural networks. J. Sci. Food Agr. 63, 297-307. http://dx.doi.org/10.1002/jsfa.2740630306

Goshawk JA, Binding DM, Kell DB. 1998. Rheological phenomena occurring during the shearing flow of mayonnaise. J. Rheol. 42, 1537-1553. http://dx.doi.org/10.1122/1.550967

Haykin, S. 1999. Neural Networks: A Comprehensive Foundation. Prentice Hall, Englewood Cliffs, NJ.

Haugen JE. 2001. Electronic noses in food analysis, en Rouseff L.R., Cadwallader K.R. (ed.) Headspace analysis of foods and flavors: Theory and Practice (Advancesin Experimental Medicine and Biology). Kluwer Academic Plenum Publishers, New York, 488, 43-57.

Huang Y, Whittaker AD, Lacey RE. 1998. Neural network prediction modeling for a continuous, snack food frying process. T ASAE 41, 1511-1517.

Humphrey KL, Narine SS. 2004. A comparison of lipid shortening functionality as a function of molecular ensemble and shear: Crystallization and melting. Food Res. Int. 37, 11-27. http://dx.doi.org/10.1016/j.foodres.2003.09.012

Hush DR, Horne BG. 1993. Progress in supervised neural networks. IEEE Signal Proc. Mag. 10, 8-39. http://dx.doi.org/10.1109/79.180705

Indahl UG, Sahni NS, Kirkhus B, Naes T. 1999. Multivariate strategies for classification based on NIR-spectra - with application to mayonnaise. Chem. Intellig. Lab. Syst. 49, 19-31. http://dx.doi.org/10.1016/S0169-7439(99)00023-4

Jayas DS, Paliwal J, Visen NS. 2000. Multi-layer neural networks for image analysis of agricultural products. J. Agr. Eng. Res. 77, 119-128. http://dx.doi.org/10.1006/jaer.2000.0559

Jansson PA. 1991. Neural networks: an overview. Anal. Chem. 63, 357-362 http://dx.doi.org/10.1021/ac00006a739

Katz WT, Snell JW, Merickel MB. 1992. Artificial Neural Networks. Method Enzymol. 210, 610-636. http://dx.doi.org/10.1016/0076-6879(92)10031-8

Khataee AR, Kasiri MB. 2010. Artificial neural networks modeling of contaminated water treatment processes by homogeneous and heterogeneous nanocatalysis. J. Mol. Catal. A: Chem. 331, 86-100. http://dx.doi.org/10.1016/j.molcata.2010.07.016

Kruzlicova D, Mocak J, Balla B, Petka J, Farkova M, Havel J. 2009. Classification of Slovak white wines using artificial neural networks and discriminant techniques. Food Chem. 112, 1046-1052 http://dx.doi.org/10.1016/j.foodchem.2008.06.047

Lange J, Wittmann C. 2002. Enzyme sensor array for the determination of biogenic amines in food samples. Analyt. Bioanalyt. Chem. 372, 276-283. http://dx.doi.org/10.1007/s00216-001-1130-9 PMid :11936099

Lefebvre J. 1983. Finished product formulation. J. Am. Oil Chem. 60, 295-300. http://dx.doi.org/10.1007/BF02543503

Lemes MR, Junior ADP. 2008. A tabela periódica dos elementos químicos prevista por redes neurais artificiais de kohonen. Quim. Nova 31, 1141-1144. http://dx.doi.org/10.1590/S0100-40422008000500040

Lichan E. Developments in the detection of adulteration of olive oil. 1994. Trends Food Sci. Tech. 5, 3-11. http://dx.doi.org/10.1016/0924-2244(94)90042-6 PMid :21299575

Lipp M. 1996. Determination of the adulteration of butter fat by its triglyceride composition obtained by GC - A comparison of the suitability of PLS and neural networks. Food Chem. 55, 389-395. http://dx.doi.org/10.1016/0308-8146(95)00162-X

Liu XQ, Tan JL. 1999. Acoustic wave analysis for food crispness evaluation. J. Text. Stud. 30, 397-408. http://dx.doi.org/10.1111/j.1745-4603.1999.tb00227.x

Lou W, Nakai S. 2001. Artificial neural network-based predictive model for bacterial growth in a simulated medium of modified-atmosphere-packed cooked meat products. J. Agric. Food Chem. 49, 1799-1804. http://dx.doi.org/10.1021/jf000650m PMid :11308328

Marini F. 2009. Artificial neural networks in foodstuff analyses: Trends and perspectives - A review. Anal. Chim. Acta 635, 121-131. http://dx.doi.org/10.1016/j.aca.2009.01.009 PMid :19216869

Márquez AJ, Herrera MPA, Ojeda UM, Maza GB. 2009. Neural network as tool for virgin olive oil elaboration process optimization. J. Food Eng. 95, 135-141. http://dx.doi.org/10.1016/j.jfoodeng.2009.04.021

Martin YG, Pavon JLP, Cordero BM. 1999. Classification of vegetable oils by linear discriminant analysis of Electronic Nose data. Anal. Chim. Acta 384, 83-94. http://dx.doi.org/10.1016/S0003-2670(98)00851-4

Mattioni B. 2010. Aplicação de redes neurais na formulação de gorduras para massa folhada baseada em gorduras interesterificadas de soja e algodão. University of Santa Catarina. Florianópolis, Brazil.

McCulloch WS, Pitts W. 1943. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophysics 5, 115-133. http://dx.doi.org/10.1007/BF02478259

Meisel H, Lorenzen PC, Martin D. 1997. Chemometric identification of butter types by analysis of compositional parameters with neural networks. Nahrung 41, 75-80. http://dx.doi.org/10.1002/food.19970410204

Mutlu AC, Boyaci IH, Genis HE, Ozturk R, Basaran-Akgul N, Sanal T, Evlice AK. 2011. Prediction of wheat quality parameters using near-infrared spectroscopy and artificial neural networks. Eur. Food Res. Technol. 233, 267-274. http://dx.doi.org/10.1007/s00217-011-1515-8

Ni HX, Gunasekaran S. 1998. Food quality prediction with neural networks. Food Technol. 52, 60-65. Nitatori CY, Gandra KM, Garcia RKA, Barrera-Arellano D. 2010. Construção e treinamento de uma rede neural para formulação de gorduras especiais a partir de gorduras interesterificadas, óleos de soja e palma. In: XVII Congresso de Iniciação Científica da Unicamp, Campinas, Brazil.

O’Brien RD. 2004. Fats and Oils - Formulating and Processing for Applications. CRC Press, New York.

Poulton MM. 2002. Neural networks as an intelligence amplification tool: A review of applications. Geophysics 67, 979-993.

Przybylski R, Zambiazi R. 2000. Predicting Oxidative Stability of Vegetable Oils Using Neural Network System and Endogenous Oil Components. J. Am. Oil Chem. Soc. 77, 925-931. http://dx.doi.org/10.1007/s11746-000-0146-x

Ramli N, Said M, Loon NT. 2005. Physicochemical characteristics of binary mixtures of hydrogenated palm kernel oil and Goat milk fat. J. Food Lipids 12, 243-260. http://dx.doi.org/10.1111/j.1745-4522.2005.00021.x

Ribeiro APB, Masuchi MH, Grimaldi R, Gonçalves LAG. 2009. Interesterificação química de óleo de soja e óleo de soja totalmente hidrogenado: influência do tempo de reação. Quim Nova 32, 939-945. http://dx.doi.org/10.1590/S0100-40422009000400021

Romero RAF, Lanças FM, Guizo SJ, Berton SR. 1991. Classification of edible oils using neural networks. Proceedings/Anais of International Meeting on Fats and Oils Technology - Symposium and Exhibition, Campinas, Brazil, 9-11.

Rumelhart DE, Hinton GE, Williams RJ. 1986. Learning internal representations by error propagation. En: Rumelhart DE, McClelland JL (ed) Parallel Distribuited Processing: Explorations in the Microstruture of Cognition. MIT Press, Cambridge, 318-362.

Scaranto BAA. 2010. Aplicação de redes neurais na formulação de gorduras para bolo baseada em gorduras interesterificadas de soja e algodão. University of Santa Catarina, Florianópolis, Brazil.

Smallwood NJ. 1989. Using computers for oil blending. J. Am. Oil Chem. Soc. 66, 644-648. http://dx.doi.org/10.1007/BF02669943

Sofu A, Ekinci FY. 2007. Estimation of Storage Time of Yogurt with Artificial Neural Network Modeling. J. Dairy Sci. 90, 3118-3125. http://dx.doi.org/10.3168/jds.2006-591 PMid :17582093

Sorsa T, Koivo H, Koivisto H. 1991. Neural networks in process fault diagnosis. IEEE Trans. Systems Man, and Cybernetics 21, 815-825. http://dx.doi.org/10.1109/21.108299

Sousa EA, Teixeira LCV, Mello MRPA, Torres EAFS, Neto JMM. 2003. Aplicação de redes neurais para avaliação do teor de carne mecanicamente separada em salsicha de frango. Ciênc. e Tecnol. de Alim. 23, 307-311. http://dx.doi.org/10.1590/S0101-20612003000300002

Stauffer CE. 2006. Uso de las grasas y los aceites en productos de panadería y confíteria. Grasas Aceites 3, 420-432.

Timms RE. 1985. Physical properties of oils and mixture. J. Am. Oil Chem. Soc. 62, 241-248. http://dx.doi.org/10.1007/BF02541385

Widrow B, Lehr M. 1990. 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proceedings of IEEE 78, 1415-1442. http://dx.doi.org/10.1109/5.58323

Vafaei MT, Eslamloueyan R, Ayatollahi SH. 2009. Simulation of steam distillation process using neural networks. Chem. Eng. Res. Des. 87, 997-1002 http://dx.doi.org/10.1016/j.cherd.2009.02.006

Vieira WG, Santos VML, Carvalho FR, Pereira JAFR, Fileti AMF. 2005. Identification and predictive control of a FCC unit using a MIMO neural model. Chem. Eng. Process 44, 855-868. http://dx.doi.org/10.1016/j.cep.2004.08.008

Yuan JQ, Vanrolleghem PA. 1999. Rolling learningprediction of product formation in bioprocesses. J. Biotechnol. 69, 47-62. http://dx.doi.org/10.1016/S0168-1656(99)00002-4

Zafra A. 1993. Automation and refining. Inform 4, 166.

Zhang Q, Reid JF, Litchfield B, Ren J, Chang S. 1994. A prototype neural network supervised control system for Bacillus thuringiensis fermentations. Biotechnol. Bioeng. 43, 483-489. http://dx.doi.org/10.1002/bit.260430608 PMid :18615745




Copyright (c) 2012 Consejo Superior de Investigaciones Científicas (CSIC)

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.


Contact us grasasyaceites@ig.csic.es

Technical support soporte.tecnico.revistas@csic.es