Evaluation of Pattern Recognition for Detecting Adulteration in Sesame Oil using Machine Olfaction System Based on Multivariate Analysis

Sesame oil which is one of the most popular and expensive edible oils, is prone to adulteration. High price of Sesame oil has motivated adulterers to mix the high-quality Sesame oil with low-quality, less expensive vegetable oils. In this study, the fatty-acid profiles of sesame, rapeseed, sunflower oil samples as well as their mixtures (0, 5, 10, 20, 30, 40 and 50% levels) were determined using Gas Chromatography. Also, Machine olfaction system containing 10 MOS sensors was utilized for detection experiments. Sensor response patterns were used for analyzing and recognizing pattern of electronic-nose signals using multivariate data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analyses (LDA), Partial Least Squares (PLS), K-Nearest Neighbors (KNN) and Support Vector Machine (SVM). Results of the SVM with RFB kernel in C-SVM method had the highest classification accuracy. The accuracy of training and validation were 96.34 and 90.56%, respectively, and next were LDA and KNN models with classification accuracies of 92.30% and 89.94%, respectively. In the light of these results, the proposed models along with the measurement system represent excellent tools for the detection of sesame seed oil adulteration with cheaper vegetable oils.