Comparison of chemometrics and AOCS official methods for predicting the shelf life of edible oil

Abstract

The present study addressed the determination of the shelf life of edible oil using the non-destructive method of electronic nose (E-Nose) and compared it with the AOCS official ​method. The studied oils included two samples: newly-produced oils (a) and those produced 6 months before (b). These samples were assessed for 150 days. Data collection was conducted using an electronic nose equipped with 8 metal oxide semiconductor (MOS) sensors. Data analysis was also achieved by various methods including cluster analysis (CA), linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA), support vector machine (SVM), and AOCS official method. According to the results, the classification accuracy of SVM, QDA, and LDA methods was 96.25, 95.8, and 94.4%, respectively. All the methods were in line with the results obtained by AOCS.