This study was performed to develop a hierarchical approach for detection and quantification of adulteration
of sesame oil with vegetable oils using gas chromatography (GC). At first, a model was constructed
to discriminate the difference between authentic sesame oils and adulterated sesame oils using support
vector machine (SVM) algorithm. Then, another SVM-based model is developed to identify the type of
adulterant in the mixed oil. At last, prediction models for sesame oil were built for each kind of oil using
partial least square method. To validate this approach, 746 samples were prepared by mixing authentic
sesame oils with five types of vegetable oil. The prediction results show that the detection limit for
authentication is as low as 5% in mixing ratio and the root-mean-square errors for prediction range from
1.19% to 4.29%, meaning that this approach is a valuable tool to detect and quantify the adulteration of
sesame oil.