Detection of Adulteration in Edible Oil Using FT-IR Spectroscopy and Machine Learning

Abstract

Aims: To detect the adulterant in edible oil rapidly.
 Study Design: Authenticity and adulteration detection in edible oils are the increasing challenges for researchers, consumers, industries and regulatory agencies. Traditional approaches may not be the most effective option to combat against adulteration in edible oils as that’s are complex, laborious, expensive, require a high degree of technical knowledge when interpreting data and produce hazardous chemical. Consequently, a cost effective, rapid and reliable method is required.
 Place and Duration of the Study: The experiment was conducted jointly in the laboratory of the Department of Food Technology and Rural Industries, Bangladesh Agricultural University, Mymensingh and the Institute of Food Science and Technology, BCSIR, Dhaka.
 Methods: In this study, Fourier Transform Infrared spectroscopy coupled with multivariate analysis was used for adulteration detection in sunflower and rice bran oil. Sunflower oil was adulterated with soybean oil in the range of 10-50% (v/v) and rice bran oil was adulterated with palm oil in the range of 4-40% (v/v) at approximately 10% and 5% increments respectively. FTIR spectra were recorded in the wavenumber range of 4000-650cm-1.
 Results: FTIR spectra data in the whole spectral range and reduced spectral range were used to develop a partial least square regression (PLSR) model to predict the level of adulteration in sunflower and palm oils. Good prediction model was obtained for all PLSR models with a coefficient of determination (R2) of >= 0.985 and root mean square errors of calibration (RMSEC) in the range of 0-1.7325%.
 Conclusion: The result suggested that FTIR spectroscopy associated with multivariate analysis has the great potential for a rapid and non-destructive detection of adulteration in edible oils laborious conventional analytical techniques.

Authenticating Edible Oils Using Fourier Transform Infrared Spectroscopy: A Review

“…Hence, there were five peaks (3006 cm-1, 2852 cm-1, 1117 cm-1, 1236 cm-1 and 1159 cm-1) that were determined to be the most important discriminatory ability. Based on the five peaks except at region 3006 cm -1, the intensity of the absorbance decreases as the concentration of lard increases, agreeing with the theory from Oyerinde and Bello (2016) [3], Gopal and Lakshmi Kantha (2017) [34] and [54] Antora et al ( 2019). Contrast can be seen at region 3006 cm-1 because lard is richer in cis C=CH bond compared to palm olein oil that was used in this study.…”

Classification of target tissues of Eisenia fetida using sequential multimodal chemical analysis and machine learning

“…Through correlation of molecular signatures with histological features of an analyzed tissue section, it further allows for characterization of different tissue types (Großerueschkamp et al 2015 ). This may be supported by algorithms such as machine learning (Nguyen et al 2021 ), which provide the possibility for fast and reproducible analysis of the spectral data (Antora et al 2019 ; Kedzierski et al 2019 ).…”