Automated classification of food products using 2D low-field NMR

Mason Greer; Cheng Chen; Soumyajit Mandal

doi:10.1016/j.jmr.2018.06.011

Automated classification of food products using 2D low-field NMR

J Magn Reson. 2018 Sep:294:44-58. doi: 10.1016/j.jmr.2018.06.011. Epub 2018 Jun 30.

Authors

Mason Greer¹, Cheng Chen², Soumyajit Mandal³

Affiliations

¹ Case Western Reserve University, 10900 Euclid Ave, Cleveland, OH 44106, USA. Electronic address: mkg53@case.edu.
² Case Western Reserve University, 10900 Euclid Ave, Cleveland, OH 44106, USA. Electronic address: cxc717@case.edu.
³ Case Western Reserve University, 10900 Euclid Ave, Cleveland, OH 44106, USA. Electronic address: sxm833@case.edu.

PMID: 30005193
DOI: 10.1016/j.jmr.2018.06.011

Abstract

In this work, low-field proton (¹H) and sodium (²³Na) relaxation and diffusion measurements are used to detect and classify different types of food products. A compact and low-cost system based on a small 0.5 T permanent magnet has been developed to autonomously authenticate such products. The system uses a simple but efficient double-tuned matching network suitable for ¹H/²³Na NMR. Various machine learning algorithms are used to classify food samples based on T₁-T₂ and D-T₂ data generated by the system, and the accuracy and prediction speed of these algorithms are studied in detail. The influence of temperature drift upon prediction accuracy is also studied. Experimental results demonstrate reliable classification of cooking oils, milk, and soy sauces.

Keywords: (1)H/(23)Na NMR; Double-tuned network; Food products authentication; Machine learning.

Publication types

Research Support, U.S. Gov't, Non-P.H.S.