Institute for Agro-food Standards and Testing Technology, Shanghai Academy of Agricultural Sciences, Shanghai 201403, China; Shanghai Service Platform of Agro-products Quality and Safety Evaluation Technology, Shanghai 201403, China.
State Key Laboratory for Managing Biotic and Chemical Threats to the Quality and Safety of Agro-products, Hangzhou 310021, China; Institute of Quality and Standard for Agricultural Products, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China.
Food Chem. 2021 Apr 16;342:128379. doi: 10.1016/j.foodchem.2020.128379. Epub 2020 Oct 15.
Shanghai city has encountered possible food fraud regarding the geographical mislabeling of vegetables for economic gain. A combination of δC, δN, δH and δO values and partial least squares discrimination analysis and support vector machine (SVM) methods were used for the first time to assess farming methods and determine the origin of vegetables from Shanghai city, Anhui and Zhejiang provinces. The results showed that 65.8% of Shanghai vegetables, 38.2% of Anhui vegetables and 23.6% of Zhejiang vegetables appeared to be grown using green or organic farming methods. The optimal discriminant model was obtained using SVM with a predictive accuracy of 100% for Shanghai vegetables. Zhejiang vegetables had a predictive accuracy of 91.7%, while it was difficult to distinguish Anhui vegetables from Shanghai or Zhejiang vegetables. Therefore, this study provided a useful method to identify vegetable farming methods and discriminate vegetables from Shanghai and Zhejiang.
上海可能存在蔬菜以次充好、以假当真的欺诈行为，涉及经济利益。本研究首次采用 δC、δN、δH 和 δO 值组合，偏最小二乘判别分析和支持向量机（SVM）方法，评估蔬菜的种植方式，并确定蔬菜的产地是来自上海、安徽和浙江。结果表明，上海蔬菜中有 65.8%、安徽蔬菜中有 38.2%、浙江蔬菜中有 23.6%的蔬菜可能采用绿色或有机种植方式。利用 SVM 建立的最优判别模型对上海蔬菜的预测准确率为 100%。浙江蔬菜的预测准确率为 91.7%，而安徽蔬菜则难以与上海或浙江的蔬菜区分。因此，本研究为鉴别蔬菜种植方式以及区分上海和浙江的蔬菜提供了一种有用的方法。
