An electronic nose to classify Iberian pig fats with different fatty acid composition

Fatty acid analysis is frequently performed in fat and other raw materials to classify them according to their fatty acid composition, but the need to carry out online determinations has generated a growing interest in more r apid options. This research was done to evaluate the ability of a polymer-s ensor based electronic nose to classify Iberian pig fat samples with differ ent fatty acid compositions. Significant correlations were found between in dividual fatty acids and sensor responses, proving that sensor response dat a were not fortuitously sorted. Significant correlations also appeared betw een some sensors and water activity, which was considered during the sample classification. Two supervised pattern recognition techniques were attempt ed to process the sensor responses: 85.5% of the samples were correctly cla ssified by discriminant analysis, but the percentage increased to 97.8% usi ng a one-hidden layer back-propagation artificial neural network. The elect ronic nose (specifically, sensor responses analyzed by a neural network) ac hieved success similar to that obtained using the more usual fatty acid ana lysis by gas chromatography.