Mid-infrared spectroscopy and support vector machines applied to control the hydrogenation process of soybean oil

Autor: Ronei J. Poppi, Evandro Bona, Patrícia Casarin de Lima, Jorge Leonardo Sanchez, Gabriela Possebon, Ailey Aparecida Coelho Tanamati, Sérgio Benedito Gonçalves Pereira, Augusto Tanamati
Rok vydání: 2017
Předmět:
Zdroj: European Food Research and Technology. 243:1447-1457
ISSN: 1438-2385
1438-2377
DOI: 10.1007/s00217-017-2855-9
Popis: 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.
Databáze: OpenAIRE