Geographic origin discrimination of pork from different Chinese regions using mineral elements analysis assisted by machine learning techniques. (1st February 2021)

• Record Type: Journal Article
• Authors: Qi, Jing; Li, Yingying; Zhang, Chen; Wang, Cheng; Wang, Juanqiang; Guo, Wenping; Wang, Shouwei
• Is Part Of: Food chemistry. Volume 337(2021)
• Publication Date: 2021-02-01
• Subjects: Geographic origin -- Traceability -- Mineral elements -- Machine learning -- Pork; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2020.127779
• Languages: English
• ISSNs: 0308-8146

Abstract

Highlights: Mineral elements were used to trace the origin of pork in China. Pork samples from each region had a profile of characteristic element content. Machine learning had a great potential for tracing the geographical origin of pork. Feedforward neural network was the best choice in this research. Abstract: Pork is the largest-produced and most-consumed meat in the world, and the food market globalization has increased public attention to food origin. Therefore, advanced techniques are required to determine the geographical origin of pork. This study investigated the prospects of using fingerprint analysis of mineral elements and machine learning to facilitate the traceability of pork origin in China. The results showed that each of seven regions had a characteristic element content profile. To improve the performance of the origin traceability model, popular machine learning techniques in food authenticity were introduced. This resulted in a high-performance origin tracing model. Comparing various machine learning algorithms, the feedforward neural network achieved superior performance with an overall accuracy of 95.71% and area under the curve close to one. Thus, this study proves that mineral elements analysis assisted by machine learning can be applied to distinguish pork samples within a country.