Food monitoring: Screening of the geographical origin of white asparagus using FT-NIR and machine learning

By Bernadette Richter, Marc Rurik, S. Gurk, Oliver Kohlbacher, M. Fischer. Food Control, 2019

75 citations recorded by the source corpus.

Abstract The aim of this study was to experimentally monitor the geographical origin of white asparagus based on near-infrared spectroscopy (NIR). 275 asparagus samples from six countries of origin and three years of harvest were analyzed. Support vector machine (SVM) classifiers were trained to predict the geographical origin and validated using nested cross-validation. When coupled with feature selection, a linear SVM was able to predict the country of origin with an accuracy of 89%. Confidence estimation based on posterior class probabilities can be used to exclude unreliable classifications leading to an accuracy up to 97%. These results demonstrate the potential of NIR spectroscopy combined with machine learning methods as a screening technique for provenance distinction of asparagus.

Subfields: Analytical Chemistry, Biomedical Engineering, Biophysics

View Paper: https://www.semanticscholar.org/paper/1a37c307248da96cd4be42a556143dca409fb1b1