Rapid screening for hazelnut oil and high‐oleic sunflower oil in extra virgin olive oil using low‐field nuclear magnetic resonance relaxometry and machine learning

Abstract

BACKGROUND As extra virgin olive oil (EVOO) has high commercial value, it is routinely adulterated with other oils. The present study investigated the feasibility of rapidly identifying adulterated EVOO using low‐field nuclear magnetic resonance (LF‐NMR) relaxometry and machine learning approaches (decision tree, K‐nearest neighbor, linear discriminant analysis, support vector machines and convolutional neural network (CNN)). RESULTS LF‐NMR spectroscopy effectively distinguished pure EVOO from that which was adulterated with hazelnut oil (HO) and high‐oleic sunflower oil (HOSO). The applied CNN algorithm had an accuracy of 89.29%, a precision of 81.25% and a recall of 81.25%, and enabled the rapid (2 min) discrimination of pure EVOO that was adulterated with HO and HOSO in the volumetric ratio range of 10–100%. CONCLUSIONS LF‐NMR coupled with the CNN algorithm is a viable candidate for rapid EVOO authentication. © 2020 Society of Chemical Industry

Rapid Identification of Adulteration in Edible Vegetable Oils Based on Low-Field Nuclear Magnetic Resonance Relaxation Fingerprints

“…Similarly, Zhu et al [ 23 ] applied discriminant analysis (DA) for estimating the adulteration ratios of peanut oil adulterated with soybean oil, rapeseed oil, or palm oil based on LF-NMR relaxometry measurements. The accuracy of edible oil adulteration detection and analysis based on these LF-NMR relaxometry techniques has been further enhanced by applying machine learning algorithms, such as support vector machine (SVM) [ 24 ], convolutional neural network (CNN) [ 25 ], and combined SVM and CNN machine learning approaches [ 26 ]. These studies have demonstrated the substantial potential for applying LF-NMR relaxometry for the rapid identification of oil adulteration.…”

Recent Advances in Analytical Detection of Olive Oil Adulteration

“…The results showed that the CVM achieved 84.92% accuracy, 54 while the convolutional neural network (CNN) algorithm had an accuracy of 89.29%, a precision of 81.25%, and a recall of 81.25% and enabled the rapid discrimination of pure EVOO from the counterparts adulterated with hazelnut or high-oleic sunflower oils in the range of 10−100% (v/v) in 2 min. 55 ■ OTHER DETECTION TECHNIQUES…”

New Method Based on Polarity Reversal for Detecting Adulteration of Extra Virgin Olive Oil with Refined Olive Pomace Oil

“…Combined with chemometric spectrum methods, FTIR and Raman spectroscopy can be used to detect the adulteration of EVOO with high accuracy. [21][22][23][24][25] Other spectroscopic methods have been developed, for instance, Fluorescence spectroscopy, [26,27] Nuclear magnetic resonance (NMR) analysis, [28] Low-field NMR, [29] Nonthermal plasma used to induce the detectable oxidation products. [30] Other works employed determination of carbon stable isotopes, [31] detection of DNA and metabolite-based markers, [32,33] and dielectric spectroscopy.…”