AUTHOR=Pérez-González C. , Salvo-Comino C. , Martin-Pedrosa F. , Dias L. , Rodriguez-Perez M. A. , Garcia-Cabezon C. , Rodriguez-Mendez M. L. TITLE=Analysis of Milk Using a Portable Potentiometric Electronic Tongue Based on Five Polymeric Membrane Sensors JOURNAL=Frontiers in Chemistry VOLUME=Volume 9 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/chemistry/articles/10.3389/fchem.2021.706460 DOI=10.3389/fchem.2021.706460 ISSN=2296-2646 ABSTRACT=A portable potentiometric electronic tongue (PE-tongue) was developed and applied to evaluate the quality of milks with different fat content (skimmed, semi-skimmed and whole) and with different nutritional content (classic, calcium-enriched, lactose-free, folic acid-enriched and enriched in sterols of vegetal origin). The system consisted of a simplified array of 5 sensors based on PVC membranes, coupled to a data logger. The 5 sensors were selected from a larger set of 20 sensors by applying Genetic Algorithms (GA) to the responses to compounds usually found in milks including salts ( KCl, CaCl2, NaCl), sugars (lactose, glucose and galactose) and organic acids (citric acid and lactic acid). The results of Principal Component Analysis (PCA) and Support Vector Machine (SVM) indicated the PE-tongue formed by an array of 5 electrodes could successfully discriminate and classify milks according to their nutritional content. The PE-tongue provided similar discrimination capability than a more complex system formed by arrays of 20 sensors. SVM regression models were used to predict the physicochemical parameters classically used in quality control of milks (acidity, density, %proteins, %lactose and %fat). The prediction results were excellent and similar to those obtained with a much complex array formed by 20 sensors. Moreover, SVM method confirmed that spoilage of unsealed milks could be correctly identified with the simplified system and the increase in acidity could be predicted accurately. The results obtained demonstrate the possibility of using the simplified PE-tongue to predict the quality of milk and to provide information about the chemical composition of milks using a simple and portable system.