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.

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.

Electrochemical investigation of edible oils: Experimentation, electrical signatures, and a supervised learning-case study of adulterated peanut oils.

Traditional approaches to characterize edible oils such as chemical, chromatographic and light absorption techniques are laborious, expensive, and bulky to implement. This paper presents the electrochemical impedance spectroscopy of 13 types of edible oils, a rapid robust approach to characterizing the electrical behavior of oils without sample preparation. This is achieved through probing the oils via oscillating electric fields to capture oil-specific electrical behaviors. The principal component analysis discriminates the oil types well and establishes repetitive behavioral trends, perceived as electrical signatures. This data is applied in a case study of adulterated peanut oils to quantify adulteration via supervised machine learning with batch-wise leave-one-out implementation. The mean absolute errors and R2 values measure 2.18-3.27 and 0.975-0.991 respectively across 4 test batches. This work provides an exemplar for the electrochemical study of edible oils, with potential for portable proof-of-value device configurations for rapid in situ analysis of edible oils and adulterated oils.