Characterization of Galician (NW Spain) quality brand potatoes: a comparison study of several pattern recognition techniques

Authenticity is an important food quality criterion and rapid methods to gu arantee it ale widely demanded by food producers, processors, consumers and regulatory bodies. The objective of this work was to develop a classificat ion system in order to confirm the authenticity of Galician potatoes with a Certified Brand of Origin and Quality (CBOQ) 'Denominacion Especifica: Pat ata de Galicia' and to differentiate them from other potatoes that did not have this CBOQ. Ten selected metals were determined by atomic spectroscopy in 102 potato samples which were divided into two categories: CBOQ and non- CBOQ potatoes. Multivariate chemometric techniques, such as cluster analysi s and principal component analysis, were applied to perform a preliminary s tudy of the data structure. Four supervised pattern recognition procedures [including linear discriminant analysis (LDA), K-nearest neighbours (KNN), soft independent modelling of class analogy(SIMCA) and multilayer feed-forw ard neural networks (MLF-ANN)] were used to classify samples into the two c ategories considered on the basis of the chemical data. Results for LDA, KN N and MLF-ANN are acceptable for the non-CBOQ class, whereas SIMCA showed b etter recognition and prediction abilities for the CBOQ class. A more sophi sticated neural network approach performed by the combination of the self-o rganizing with adaptive neigbourhood network (SOAN) and MLF network was emp loyed to optimize the classification. Using this combined method, excellent performance in terms of classification and prediction abilities was obtain ed for the two categories with a success rate ranging from 98 to 100%. The metal profiles provided sufficient information to enable classification rul es to be developed for identifying potatoes according to their origin brand based on SOAN-MLF neural networks.