One-class classification based authentication of peanut oils by fatty acid profiles

摘要: Developing a method of identifying oil authenticity is becoming critical for protecting customers' rights as adulteration edible oils particular concern in food quality. Since adulterants are usually unknown, the identification one-class classification problem chemometrics. In this study, model was built to identify peanut by fatty acid profiles. Based on previous studies, 28 acids were identified and quantified oils. The partial least squares (OCPLS) classifier Subsequently, established validated independent test sets. results indicated that OCPLS could effectively detect adulterated therefore employed assessment. Moreover, counterfeit with different levels other simulated Monte Carlo lowest level classifier. As result, sensitively vegetable at more than 4%.