Application of Artificial Neural Networks to Predict the Oxidation of Menhaden Fish Oil Obtained from Fourier Transform Infrared Spectroscopy Method

Abstract

Oxidation is a major cause of deterioration in fish oil, leading to considerable losses of quality and nutritional value. To date, the available methods to monitor lipid oxidation in foods are based on chemical analysis. Fourier transform infrared spectroscopy (FTIR) is an alternative technique for the study of molecular structure and compositional changes in a wide range of foods. The objectives of this study were to use attenuated total reflectance-FTIR for evaluating oxidative quality and application of artificial neural network analysis (ANN), a mathematical model, to predict the oxidative values of Menhaden fish oil. The oil was stored in the presence of light at room temperature. The oxidation was measured for primary and secondary oxidative change; peroxide value (PV) and anisidine value (AnV), respectively, using FTIR were compared with chemical analysis each day during the 3 weeks of storage. The wavenumber and absorbance values of FTIR spectra were applied to predict the oxidative values of the oil by using ANN. Inputs consisted of wavenumber and absorbance outputs were composed of PV and AnV. It was found that changes in the region between 3,500 and 1,700 cm-1 and absorbance were related to PV and AnV of the chemical analysis (R2 > 0.85). FTIR spectroscopy with the aid of ANN demonstrates its potential as an alternative and rapid technique rather than a conventional method for prediction of food lipids oxidation.