您好，欢迎访问中国水产科学研究院 机构知识库！
中国水产科学研究院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Geographic origin discrimination of red swamp crayfish Procambarus clarkii from different Chinese regions using mineral element analysis assisted by machine learning techniques

文献类型： 外文期刊

作者： Bai, Shuyan 1 ; Qin, Dongli 1 ; Chen, Zhongxiang 1 ; Wu, Song 1 ; Tang, Shizhan 1 ; Gao, Lei 1 ; Wang, Peng 1 ;

作者机构： 1.Chinese Acad Fishery Sci, Heilongjiang River Fisheries Res Inst, Harbin 150070, Peoples R China

2.Inspection & Testing Ctr Harbin, Minist Agr, Rural Affairs Fishery Environm, Aquat Prod Qual Supervis, Harbin 150070, Peoples R China

关键词： Geographic origin; Traceability; Mineral elements; Machine learning; Red swamp crayfish

期刊名称：FOOD CONTROL （ 影响因子：6.652； 五年影响因子：6.498 ）

ISSN： 0956-7135

年卷期： 2022 年 138 卷

页码：

收录情况： SCI

摘要： To explore the application prospects of mineral element analysis assisted by machine learning in the geographical origin traceability of red swamp crayfish (Procambarus clarkii) and establish an origin traceability model for it, we used inductively coupled plasma mass spectrometry (ICP-MS) to determine the content of 24 mineral elements, including Cu, Zn, Ga, As, Se, Rb, Sr, and Mo, in red swamp crayfish muscle tissues from Anhui, Hunan, and Hubei provinces of China. The ten characteristic elements, screened by the principal component analysis (PCA), were incorporated into the linear discriminant analysis (LDA) to establish an origin discriminant model of red swamp crayfish. We have verified the feasibility of the mineral element fingerprinting to trace the geographical origin of red swamp crayfish in three regions of China. To improve the discrimination performance, three machine learning classification algorithms, the support vector machine (SVM), the feed-forward neural networks (FNN), and the back-propagation neural network (BPNN), were combined to classify the red swamp crayfish of different origins based on mineral element content. The discriminative accuracy of the training models of both FNN and BPNN reached 100%, and their cross-validation accuracy were 91.88% and 93.13%, respectively, with the area under the receiver operating characteristic (ROC) curve (AUC) values close to 1. Thus, the overall performance of the FNN and BPNN was better than that of SVM. Taken together, our results showed that mineral elements combined with neural networks showed great advantages and potential in geographic origin traceability of red swamp crayfish.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国水产科学研究院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台