Food monitoring: Screening of the geographical origin of white asparagus using FT-NIR and machine learning
| Autor: | Stephanie Gurk, Marc Rurik, Markus Fischer, Bernadette Richter, Oliver Kohlbacher |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
biology
business.industry 010401 analytical chemistry Linear svm Feature selection 04 agricultural and veterinary sciences Machine learning computer.software_genre biology.organism_classification 040401 food science 01 natural sciences 0104 chemical sciences Support vector machine 0404 agricultural biotechnology Asparagus Artificial intelligence business computer Food Science Biotechnology Mathematics |
| Zdroj: | Food Control. 104:318-325 |
| ISSN: | 0956-7135 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect