TY - GEN
T1 - Prediction of Quality Attributes of Fresh Unpasteurized Milk Using Dielectric Spectroscopy Coupled to Chemometric Tools
AU - Chuquizuta, T.
AU - Colunche, Y.
AU - Rubio, M.
AU - Oblitas, J.
AU - Arteaga, H.
AU - Castro, W.
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The objective of this research is to predict the quality attributes of fresh unpasteurized milk using dielectric spectroscopy coupled to chemometric tools. For the fulfillment of the purpose, we have worked with fresh unpasteurized milk of the Brown Swiss breed, obtained from the 'La lechera' stable; dilutions of water - fresh milk were obtained, from 70 to 100% at 25{circ}mathrm{C}, followed by the physicochemical characterization (density, total solids, freezing point, fatty solids, proteins and added water) and dielectric properties in the range of 0.5 to 9 GHz using an open ended coaxial probe (N1501A-001), connected to a Vector Network Analyzer, model N9915A-Keysight Technologies. Likewise, the partial least squares regression was used to correlate the physicochemical properties with the dielectric properties; the results obtained in the prediction of freezing point, proteins, fatty solids and added water from fresh milk unpasteurized have presented a coefficient of determination and a mean square error in the range of [0.95-0.98] and [2.57times 10{-7}-7.46times 10{-2}] respectively. Consequently, it is concluded that the technique of dielectric spectroscopy and machine learning presents potential for prediction of physicochemical characteristics of fresh milk unpasteurized, being able to be implemented in the production lines to quickly and reliably evaluate the quality of cow's milk.
AB - The objective of this research is to predict the quality attributes of fresh unpasteurized milk using dielectric spectroscopy coupled to chemometric tools. For the fulfillment of the purpose, we have worked with fresh unpasteurized milk of the Brown Swiss breed, obtained from the 'La lechera' stable; dilutions of water - fresh milk were obtained, from 70 to 100% at 25{circ}mathrm{C}, followed by the physicochemical characterization (density, total solids, freezing point, fatty solids, proteins and added water) and dielectric properties in the range of 0.5 to 9 GHz using an open ended coaxial probe (N1501A-001), connected to a Vector Network Analyzer, model N9915A-Keysight Technologies. Likewise, the partial least squares regression was used to correlate the physicochemical properties with the dielectric properties; the results obtained in the prediction of freezing point, proteins, fatty solids and added water from fresh milk unpasteurized have presented a coefficient of determination and a mean square error in the range of [0.95-0.98] and [2.57times 10{-7}-7.46times 10{-2}] respectively. Consequently, it is concluded that the technique of dielectric spectroscopy and machine learning presents potential for prediction of physicochemical characteristics of fresh milk unpasteurized, being able to be implemented in the production lines to quickly and reliably evaluate the quality of cow's milk.
U2 - 10.1109/PIERS55526.2022.9792687
DO - 10.1109/PIERS55526.2022.9792687
M3 - Contribución a la conferencia
AN - SCOPUS:85132788842
T3 - Progress in Electromagnetics Research Symposium
SP - 776
EP - 782
BT - 2022 Photonics and Electromagnetics Research Symposium, PIERS 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 Photonics and Electromagnetics Research Symposium, PIERS 2022
Y2 - 25 April 2022 through 29 April 2022
ER -