Detection of fraud in sesame oil with the help of artificial intelligence combined with chemometrics methods and chemical compounds characterization by gas chromatography-mass spectrometry

The majority of current approaches to identify adulterated edible vegetable oils are of limited practical benefits because they require long analysis times, expensive equipment, and professional training. In this study, a new, simple, accurate, and fast detection method was proposed based on the odor fingerprint obtained by measuring the volatile odors of edible vegetable oils with an electronic nose. The odor fingerprints were obtained for 8 different levels of sunflower and canola oil added to sesame oil, and the samples were analyzed simultaneously by gas chromatography-mass spectrometry (GC-MS). The chemometric methods such as Principal Component Analysis (PCA), Liner Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machine (SVM), and Artificial Neural Networks (ANN) were used to analyze the signals from the electronic nose. According to results, low level fraud (25% sunflower oil to 75% sesame oil), which is difficult to detect using the GC-MS method, was detected with very high accuracy via the electronic nose. This indicates that the current approach has the potential to detect and quantify edible oil fraud to improve efficiency and monitoring and to ensure the safety of consumption of edible vegetable oils.