Improving Prediction of Peroxide Value of Edible Oils Using Regularized Regression Models.

William E Gilbraith,Kristl L Adams,J Chance Carter,Karl S Booksh,Joshua M Ottaway

doi:10.3390/molecules26237281

William E Gilbraith, Kristl L Adams + Show 3 more

Open Access

https://doi.org/10.3390/molecules26237281

Copy DOI

Abstract

We present four unique prediction techniques, combined with multiple data pre-processing methods, utilizing a wide range of both oil types and oil peroxide values (PV) as well as incorporating natural aging for peroxide creation. Samples were PV assayed using a standard starch titration method, AOCS Method Cd 8-53, and used as a verified reference method for PV determination. Near-infrared (NIR) spectra were collected from each sample in two unique optical pathlengths (OPLs), 2 and 24 mm, then fused into a third distinct set. All three sets were used in partial least squares (PLS) regression, ridge regression, LASSO regression, and elastic net regression model calculation. While no individual regression model was established as the best, global models for each regression type and pre-processing method show good agreement between all regression types when performed in their optimal scenarios. Furthermore, small spectral window size boxcar averaging shows prediction accuracy improvements for edible oil PVs. Best-performing models for each regression type are: PLS regression, 25 point boxcar window fused OPL spectral information RMSEP = 2.50; ridge regression, 5 point boxcar window, 24 mm OPL, RMSEP = 2.20; LASSO raw spectral information, 24 mm OPL, RMSEP = 1.80; and elastic net, 10 point boxcar window, 24 mm OPL, RMSEP = 1.91. The results show promising advancements in the development of a full global model for PV determination of edible oils.

Highlights

The peroxide value (PV) of an edible oil is an indicator of freshness as viewed through oxidative degradation
Models were optimized for degree of boxcar smoothing and optical pathlengths (OPLs) of the spectra employed
The 2 mm OPL data was shown to be outperformed by the 24 mm OPL data; the fused OPL data did marginal improve prediction errors when models were built with partial least squares (PLS)

Summary

Introduction

The peroxide value (PV) of an edible oil is an indicator of freshness as viewed through oxidative degradation. PV is a measurement of the primary oxidation of hydroxyl groups of unsaturated fats in oils by molecular oxygen into hydroperoxides and peroxides [1]. This measurement is often presented in milliequivalents O2 /kg (mEq O2 /kg) of oil. The titration endpoint, and sample PV, is determined by either colorimetric or electrochemical means. This established standard method requires toxic chemicals, is labor intensive and time consuming, and requires specialized equipment such as a chemical fume hood; for these reasons, rapid PV analysis in the field is not practical

Methods

Results

Discussion

Conclusion