Foodstuff adulteration involves addition of any low‐cost substances to the high‐price materials to reduce the content of the expensive components, and hence decrease the production cost and reach to the maximum profit. An electronic nose was used in this study to detect the adulterations in mixed edible oils. The acidity, peroxide, anisidine, and Totox values of the edible oil samples were measured according to the official American Oil Chemist Society (AOCS) standard. The results were analyzed by Cluster analysis (CA), principle component analysis (PCA), principal component regression (PCR), linear discriminant analysis (LDA), and artificial neural network (ANN) methods with accuracy of 95, 98, 98, 88, and 97.3%, respectively. According to the results, the ANN method with structure of 8‐7‐5 showed the highest accuracy in classification of oil adulteration. Its correct classification ratio, mean square errors, and correlation (r) were 97.3%, .117211, and .0963, respectively. The results also indicated that the proposed method can be used as an alternative of the official AOCS methods to innovatively detect the edible oil adulteration with high accuracy and speed.
Practical applications
Lipid oxidation is one of the major causes of food spoilage especially in those containing oil. AOCS has developed various methods to evaluate the oxidation status of the oil assets. However, these chemical tests are time‐consuming, destructive, and costly and require several glassware and reagents. E‐nose could be used for real‐time monitoring of the volatile components of the food to evaluate different features of the product. Generally, E‐nose evaluates mixture of smells released form a sample and is a reliable, nondestructive, cost‐effective, and portable method with high feasibility and speed as well as simple use. CA, PCA, and ANN methods were also applied for qualitative differentiation of different adulteration percentages in oxidized and nonoxidized oils.