SIMCA (Soft Independent Modeling of Class Analogy) Demonstrated with Characterization and Classification of Italian Olive Oil

Abstract

Abstract The multivariate technique SIMCA (soft independent modeling of class analogy) has been applied to the classification of foodstuffs on the basis of gas chromatographic profiles of some of their constituents. The data set used in this investigation consists of the percentage distribution of 7 fatty acids (7 variables) in 100 samples of virgin olive oil from 2 different regions (2 classes) of Italy, East and West Liguria. The SIMCA method can be used to compute whether an olive oil sample from Liguria originated in the western or eastern part of this region, while 98.8% of samples that do not originate in Liguria are correctly classified as outliers. The developed classification rules are adequate for identifying oils according to their origin. Standard decision diagrams (SDD) are very attractive tools for classification of new samples; the similarity between a new sample and each of the classes is easily computed. Consequently, the SDD visualizes any similarity toward each of the classes, and enables a decision on whether the new sample originates in one of the regions under study.