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

Can Near-Infrared Spectroscopy Replace a Panel of Tasters in Sensory Analysis of Dry-Cured Bísaro Loin?

This study involved a comprehensive examination of sensory attributes in dry-cured Bísaro loins, including odor, androsterone, scatol, lean color, fat color, hardness, juiciness, chewiness, flavor intensity and flavor persistence. An analysis of 40 samples revealed a wide variation in these attributes, ensuring a robust margin for multivariate calibration purposes. The respective near-infrared (NIR) spectra unveiled distinct peaks associated with significant components, such as proteins, lipids and water. Support vector regression (SVR) models were methodically calibrated for all sensory attributes, with optimal results using multiplicative scattering correction pre-treatment, MinMax normalization and the radial base kernel (non-linear SVR model). This process involved partitioning the data into calibration (67%) and prediction (33%) subsets using the SPXY algorithm. The model parameters were optimized via a hybrid algorithm based on particle swarm optimization (PSO) to effectively minimize the root-mean-square error (RMSECV) derived from five-fold cross-validation and ensure the attainment of optimal model performance and predictive accuracy. The predictive models exhibited acceptable results, characterized by R-squared values close to 1 (0.9616-0.9955) and low RMSE values (0.0400-0.1031). The prediction set's relative standard deviation (RSD) remained under 5%. Comparisons with prior research revealed significant improvements in prediction accuracy, particularly when considering attributes like pig meat aroma, hardness, fat color and flavor intensity. This research underscores the potential of advanced analytical techniques to improve the precision of sensory evaluations in food quality assessment. Such advancements have the potential to benefit both the research community and the meat industry by closely aligning their practices with consumer preferences and expectations.

Statistical FT-IR Spectroscopy for the Characterization of 17 Vegetable Oils

Vegetable oils have been utilized for centuries in the food, cosmetic, and pharmaceutical industries, and they contribute beneficially to overall human health, to active skincare, and to effective treatments. Monitoring of the vegetable oils is carried out by the methods described in the European Pharmacopeia, which is time-consuming, has poor repeatability, and involves the use of toxic organic chemicals and expensive laboratory equipment. Many successful studies using IR spectroscopy have been carried out for the detection of geographical origin and adulteration as well as quantification of oxidation parameters. The aim of our research was to explore FT-IR spectroscopy for assessing the quality parameters and fatty acid composition of cranberry, elderberry, borage, blackcurrant, raspberry, black mustard, walnut, sea buckthorn, evening primrose, rosehip, chia, perilla, black cumin, sacha inchi, kiwi, hemp, and linseed oil. Very good models were obtained for the α-linolenic acid and linoleic acid contents, with R2 = 1.00; Rv2 values of 0.98, 0.92, 0.89, and 0.84 were obtained for iodine value prediction, stearic acid content, palmitic acid content, and unsaponifiable matter content, respectively. However, we were not able to obtain good models for all parameters, and the use of the same process for variable selection was found to be not suitable for all cases.

Compact low-field NMR spectroscopy and chemometrics applied to the analysis of edible oils

Compact nuclear magnetic resonance (NMR) spectroscopy combined with chemometric tools opens new perspectives for NMR use. This work compares the potential of 43, 60 and 400 MHz NMR spectroscopy for quality control of edible oils. Partial least squares regression (PLSR) and support vector regression (SVR) models built on the three NMR devices had equivalent performances for fatty acids and iodine value, and the models built with the low field spectra were equivalent to the high field. Moreover, performances for calibration indicated that most of the models built with medium/or high-resolution fields presented reproducibility values lower than the minimum accepted by the American Oil Chemists' Society (AOCS). Compared to classical methods, this new approach allows the application of medium resolution devices as a sample screening tool in analytical laboratories since it allows the spectrum obtention in a few seconds, without the need for sample preparation or the use of deuterated solvents.

Comparison of the Performance of Partial Least Squares and Support Vector Regressions for Predicting Fatty Acids and Fatty Acid Classes in Marine Oil Dietary Supplements by Using Vibrational Spectroscopic Data

ABSTRACT

Simple, fast, and accurate analytical techniques for verifying the accuracy of label declarations for marine oil dietary supplements containing eicosapentaenoic acid (EPA) and docosahexaenoic acid (DHA) are required because of the increased consumption of these products. We recently developed broad-based partial least squares regression (PLS-R) models to quantify six fatty acids (FAs) and FA classes by using the spectroscopic data from a portable Fourier transform infrared (FTIR) device and a benchtop Fourier transform near infrared (FT-NIR) spectrometer. We developed an improved quantification method for these FAs and FA classes by incorporating a nonlinear calibration approach based on the machine learning technique support vector machines. For the two spectroscopic methods, high accuracy in prediction was indicated by low root mean square error of prediction and by correlation coefficients (R2) close to 1, indicating excellent model performance. The percent accuracy of the support vector regression (SV-R) model predicted values for EPA and DHA in the reference material was 90 to 110%. In comparison to PLS-R, SV-R accuracy for prediction of FA and FA class concentrations was up to 2.4 times higher for both ATR-FTIR and FT-NIR spectroscopic data. The SV-R models also provided closer agreement with the certified and reference values for the prediction of EPA and DHA in the reference standard. Based on our findings, the SV-R methods had superior accuracy and predictive quality for predicting the FA concentrations in marine oil dietary supplements. The combination of SV-R with ATR-FTIR and/or FT-NIR spectroscopic data can potentially be applied for the rapid screening of marine oil products to verify the accuracy of label declarations.

HIGHLIGHTS