Abstract
The industrial hydrogenation of soybean oil is well established. However, its control is carried out through time-consuming methods. The objective of this study was to evaluate the mid-infrared spectroscopy (FTIR-ATR) in tandem with support vector machines (SVM) in controlling the hydrogenation process. Models were constructed to predict the content of saturated fatty acids (SFA), unsaturated fatty acids (UFA), monounsaturated fatty acids (MUFA), trans fatty acids (TFA), polyunsaturated fatty acids (PUFA) and the iodine value (IV). The values predicted by the SVM models were compared to values obtained through gas chromatography. Feasible multivariate models were obtained with r 2 minimum of 0.96 and RMSEP in the range of 0.65–2.65. Feature selection using correlation spectra was also efficient, maintaining the performance of the models and reducing the number of variables used by up to 94%. Therefore, it was demonstrated that FTIR-ATR methodology with SVM could be applied to monitor industrial hydrogenation.
Similar content being viewed by others
References
Dijkstra AJ (2012) Kinetics and mechanism of the hydrogenation process - the state of the art. Eur J Lipid Sci Technol 114:985–998. doi:10.1002/ejlt.201100405
Dijkstra AJ (2010) Selectivities in Partial Hydrogenation. J Am Oil Chem Soc 87:115–117. doi:10.1007/s11746-009-1507-z
Karabulut I, Kayahan M, Yaprak S (2003) Determination of changes in some physical and chemical properties of soybean oil during hydrogenation. Food Chem 81:453–456. doi:10.1016/S0308-8146(02)00397-7
Gupta MK (2010) Practical Guide to Vegetable Oil Processing, 1st edn. AOCS, Illinois
Philippaerts A, Jacobs PA, Sels BF (2013) Is there still a future for hydrogenated vegetable oils? Angew Chemie Int Ed 52:5220–5226. doi:10.1002/anie.201209731
AOCS (2012) Iodine value (Wijs). In: Firestone D (ed) Off methods Recomm. Pract. AOCS, 6th edn. AOCS, USA, p 1200
AOCS (2012) Iodine Value (calculated from GLC). In: Firestone D (ed) Off. Methods Recomm. Pract. AOCS, 6th edn. AOCS, USA, p 1200t;/bib>
Yang H, Irudayaraj J, Paradkar M (2005) Discriminant analysis of edible oils and fats by FTIR, FT-NIR and FT-Raman spectroscopy. Food Chem 93:25–32. doi:10.1016/j.foodchem.2004.08.039
Karoui R, Downey G, Blecker C (2010) Mid-infrared spectroscopy coupled with chemometrics: A tool for the analysis of intact food systems and the exploration of their molecular structure-quality relationships-A review. Chem Rev 110:6144–6168. doi:10.1021/cr100090k
Hiri A, De Luca M, Ioele G et al (2015) Chemometric classification of citrus juices of Moroccan cultivars by infrared spectroscopy. Czech J Food Sci 33:137–142. doi:10.17221/284/2014-CJFS
Terouzi W, De Luca M, Bolli A et al (2011) A discriminant method for classification of Moroccan olive varieties by using direct FT-IR analysis of the mesocarp section. Vib Spectrosc 56:123–128. doi:10.1016/j.vibspec.2011.01.004
Zhang Q, Liu C, Sun Z et al (2012) Authentication of edible vegetable oils adulterated with used frying oil by Fourier Transform Infrared Spectroscopy. Food Chem 132:1607–1613. doi:10.1016/j.foodchem.2011.11.129
Bona E, Marquetti I, Link JV et al (2017) Support vector machines in tandem with infrared spectroscopy for geographical classification of green arabica coffee. LWT Food Sci Technol 76:330–336. doi:10.1016/j.lwt.2016.04.048
Argyri A a., Jarvis RM, Wedge D et al (2013) A comparison of Raman and FT-IR spectroscopy for the prediction of meat spoilage. Food Control 29:461–470. doi:10.1016/j.foodcont.2012.05.040
Haykin S (2008) Neural networks and learning machines, 3rd edn. Prentice Hall, New York
Bishop CM (2006) Pattern recognition and machine learning, 1st edn. Springer, New York
Liu C, Yang SX, Deng L (2015) A comparative study for least angle regression on NIR spectra analysis to determine internal qualities of navel oranges. Expert Syst Appl 42:8497–8503. doi:10.1016/j.eswa.2015.07.005
Maia EL, Rodrigues-Amaya D (1993) Avaliação de um método simples e econômico para metilação de ácidos graxos com lipídios de diversas espécies de peixes. Rev Inst Adolfo Lutz 53:27–35
Hartman L, Lago RCA (1973) Rapid determination of fatty acid methyl esthers from lipids. Lab Pract 22:475–477
Visentainer JV (2012) Aspectos analíticos da resposta do detector de ionização em chama para ésteres de ácidos graxos em biodiesel e alimentos. Quim Nova 35:274–279. doi:10.1590/S0100-40422012000200008
Lai YW, Kemsley EK, Wilson RH (1994) Potential of Fourier transform infrared spectroscopy for the authentication of vegetable oils. J Agric Food Chem 42:1154–1159. doi:10.1021/jf00041a020
Kompany-Zareh M (2011) On-line monitoring of a continuous pharmaceutical process using parallel factor analysis and unfolding multivariate statistical process control representation. J Iran Chem Soc 8:209–222
Savitzky A, Golay MJE (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36:1627–1639
Ferreira MMC (2015) Quimiometria, Conceitos, Metodos e aplicações, Editora Ca. Campinas, SP
Westad F, Marini F (2015) Validation of chemometric models—a tutorial. Anal Chim Acta 893:14–24. doi:10.1016/j.aca.2015.06.056
Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199–222. doi:10.1023/B:STCO.0000035301.49549.88
Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1–27. doi:10.1145/1961189.1961199
Li H, Liang Y, Xu Q (2009) Support vector machines and its applications in chemistry. Chemom Intell Lab Syst 95:188–198. doi:10.1016/j.chemolab.2008.10.007
Papadopoulou OS, Panagou EZ, Mohareb FR, Nychas G-JE (2013) Sensory and microbiological quality assessment of beef fillets using a portable electronic nose in tandem with support vector machine analysis. Food Res Int 50:241–249. doi:10.1016/j.foodres.2012.10.020
Gao F, Han L (2012) Implementing the Nelder-Mead simplex algorithm with adaptive parameters. Comput Optim Appl 51:259–277. doi:10.1007/s10589-010-9329-3
Bona E, Borsato D, Sérgio R, Herrera P (2000) Aplicativo para otimização empregando o método simplex seqüencial. Acta Sci 22:1201–1206
Botelho BG, Mendes BAP, Sena MM (2013) Implementação de um método robusto para o controle fiscal de umidade em queijo minas artesanal. Abordegem metrológica multivariada. Quim Nova 36:1416–1422
Valderrama P, Braga JWB, Poppi RJ (2009) Estado da arte de figuras de mérito em calibração multivariada. Quim Nova 32:1278–1287
Shen K-Q, Ong C-J, Li X-P, Wilder-Smith EP V (2008) Feature selection via sensitivity analysis of SVM probabilistic outputs. Mach Learn 70:1–20. doi:10.1007/s10994-007-5025-7
Teófilo RF, Martins JPA, Ferreira MMC (2009) Sorting variables by using informative vectors as a strategy for feature selection in multivariate regression. J Chemom 23:32–48. doi:10.1002/cem.1192
Jovanović D, Čupí Ž̌, Stankoví M et al (2000) The influence of the isomerization reactions on the soybean oil hydrogenation process. J Mol Catal A Chem 159:353–357. doi:10.1016/S1381-1169(00)00154-0
Vlachos N, Skopelitis Y, Psaroudaki M et al (2006) Applications of Fourier transform-infrared spectroscopy to edible oils. Anal Chim Acta 573–574:459–465. doi:10.1016/j.aca.2006.05.034
Guillén MD, Cabo N (1997) Characterization of edible oils and lard by fourier transform infrared spectroscopy. Relationships between composition and frequency of concrete bands in the fingerprint region. J Am Oil Chem Soc 74:1281–1286. doi:10.1007/s11746-997-0058-4
Tyburczy C, Mossoba MM, Rader JI (2013) Determination of trans fat in edible oils: current official methods and overview of recent developments. Anal Bioanal Chem 405:5759–5772. doi:10.1007/s00216-013-7005-z
Brereton RG, Lloyd GR (2010) Support vector machines for classification and regression. Analyst 135:230–267. doi:10.1039/b918972f
Hocevar L, Soares VRB, Oliveira FS et al (2012) Application of multivariate analysis in mid-infrared spectroscopy as a tool for the evaluation of waste frying oil blends. J Am Oil Chem Soc 89:781–786. doi:10.1007/s11746-011-1968-8
Currie LA (1999) Nomenclature in evaluation of analytical methods including detection and quantification capabilities (IUPAC Recommendations 1995). Anal Chim Acta 391:105–126. doi:10.1016/S0003-2670(99)00104-X
Cunha S (2003) Estabilidade relativa de alcenos: análise dos critérios encontrados nos livros textos de graduação e uma proposta de explicação operacional para alcenos dissubstituídos. Quim Nov 26:948–951.
Acknowledgements
The authors thank CNPq (448249/2014-6) and Fundação Araucária (36652.410.40381.28022013) for their financial support.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Ethical approval
This article does not contain any studies with human or animal subjects.
Rights and permissions
About this article
Cite this article
Sanchez, J.L., Pereira, S.B.G., de Lima, P.C. et al. Mid-infrared spectroscopy and support vector machines applied to control the hydrogenation process of soybean oil. Eur Food Res Technol 243, 1447–1457 (2017). https://doi.org/10.1007/s00217-017-2855-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00217-017-2855-9