Food Research International, 2020, 137, 109353
DOI: 10.1016/j.foodres.2020.109353

Food Research International, 2020, 137, 109353
DOI: 10.1016/j.foodres.2020.109353

Trends in Food Science & Technology, 2020, 101, 150-164
DOI: 10.1016/j.tifs.2020.05.017

Critical Reviews in Food Science and Nutrition
Agriculture, Ecosystems & Environment, 2020, 297, 106969
DOI:10.1016/j.agee.2020.106969

Critical Reviews in Food Science and Nutrition

Different separated protein fractions by the electrophoretic method in polyacrylamide gel were used to classify two different types of honeys, Galician honeys and commercial honeys produced and packaged outside of Galicia. Random forest, artificial neural network, and support vector machine models were tested to differentiate Galician honeys and other commercial honeys produced and packaged outside of Galicia. The results obtained for the best random forest model allowed us to determine the origin of honeys with an accuracy of 95.2%. The random forest model, and the other developed models, could be improved with the inclusion of new data from different commercial honeys.