Abstract
Adulteration detection or authentication is considered a type of one-class classification (OCC) in chemometrics. An effective OCC model requires representative samples. However, it is challenging to collect representative samples from all over the world. Moreover, it is also very hard to evaluate the representativeness of collected samples. In this study, we blazed a new trail to propose an authentication method to identify adulterated edible oils without building a prediction model beforehand. An authentication method developed by real-time one-class classification modeling, and model population analysis was designed to identify adulterated oils in the market without building a classification model beforehand. The underlying philosophy of the method is that the sum of the absolute centered residual (ACR) of the good model built by only authentic samples is higher than that of the bad model built by authentic and adulterated samples. In detail, a large number of OCC models were built by selecting partial samples out of inspected samples using Monte Carlo sampling. Then, adulterated samples involved in the test of these good models were identified. Taking the inspected samples of avocado oils as an example, as a result, 6 out of 40 avocado oils were identified as adulterated and then validated by chemical markers. The successful identification of avocado oils adulterated with soybean oil, corn oil, or rapeseed oil validated the effectiveness of our method. The proposed method provides a novel idea for oils as well as other high-value food adulteration detection.