Pattern recognition analysis applied to classification of honeys from two geographic origins

Eleven legal parameters of quality control of honey were determined in 67 honey samples from Galicia (northwestern Spain) which were obtained from two production areas: Lugo and Orense. Classification of these honeys according to their geographic origin was achieved by pattern recognition techniques to the chemical data. Humidity and free acidity were found to be the most important features for the classification. In this case the use of pollen data to achieve a correct geographic classification of the honey samples is not necessary