This chapter presents the description of some chemometric approaches to the prediction and verification of the botanical and geographical origin of extra virgin oil samples together with some examples taken from the authors' experience. It focuses on the geographical and varietal origin. When the complexity of the problem increases, it is necessary also that the complexity and non-linearity of the model used increases accordingly. One of the examples involving the use of class-modeling techniques has shown how these methods are more suited to use in the problems involving the authentication of Protected Denomination of Origin (PDO) products. They not only provide the usual non-error rate, but also additional figures of merit like sensitivity and specificity that can help understand which class is more likely to be confounded with which. Moreover, they allow the identification of samples not fitting any model. © 2010 Copyright © 2010 Elsevier Inc. All rights reserved.
An Overview of the Chemometric Methods for the Authentication of the Geographical and Varietal Origin of Olive Oils / Marini, Federico; Bucci, Remo; Magri', Antonio; Magri', Andrea. - STAMPA. - (2010), pp. 569-579. [10.1016/b978-0-12-374420-3.00062-0].
An Overview of the Chemometric Methods for the Authentication of the Geographical and Varietal Origin of Olive Oils
MARINI, Federico;BUCCI, Remo;MAGRI', Antonio;MAGRI', Andrea
2010
Abstract
This chapter presents the description of some chemometric approaches to the prediction and verification of the botanical and geographical origin of extra virgin oil samples together with some examples taken from the authors' experience. It focuses on the geographical and varietal origin. When the complexity of the problem increases, it is necessary also that the complexity and non-linearity of the model used increases accordingly. One of the examples involving the use of class-modeling techniques has shown how these methods are more suited to use in the problems involving the authentication of Protected Denomination of Origin (PDO) products. They not only provide the usual non-error rate, but also additional figures of merit like sensitivity and specificity that can help understand which class is more likely to be confounded with which. Moreover, they allow the identification of samples not fitting any model. © 2010 Copyright © 2010 Elsevier Inc. All rights reserved.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.