Machine learning-based predictive analysis of total polar compounds (TPC) content in frying oils: A comprehensive electrochemical study of 6 types of frying oils with various frying timepoints

Abstract

Standard approaches to determining the total polar compounds (TPC) content in frying oils such as the chromatographic techniques are slow, bulky, and expensive. This paper presents the electrochemical analysis of 6 types of frying oils inclusive of 52 frying timepoints, without sample preparation. This is achieved via impedance spectroscopy to capture sample-specific electrical polarization states. To the best of our knowledge, this is a first-of-its-kind comprehensive study of various types of frying oils, with progressively increasing frying timepoints for each type. The principal component analysis distinguishes the frying timepoints well for all oil types. TPC prediction follows, involving supervised machine learning with sample-wise leave-one-out implementation. The R² values and mean absolute errors across the test samples measure 0.93-0.97 and 0.43-1.19 respectively. This work serves as a reference for electrochemical analysis of frying oils, with the potential for portable TPC predictors for rapid accurate screening of frying oils.

Keywords: Edible oils; Electrochemical analysis; Frying oils; Frying time; Machine learning; PCA.