您好，欢迎访问甘肃省农业科学院 机构知识库！
甘肃省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Machine learning model interpretability using SHAP values: Applied to the task of classifying and predicting the nutritional content of different cuts of mutton

文献类型： 外文期刊

作者： Wang, Li 1 ; Sun, Xuchun 4 ; Liang, Jing 5 ; Ma, Zhiyuan 1 ; Li, Fei 1 ; Hao, Shengyan 6 ; Liu, Baocang 7 ; Guo, Long 1 ; Weng, Xiuxiu 1 ;

作者机构： 1.Lanzhou Univ, State Key Lab Herbage Improvement & Grassland Agro, Lanzhou 730020, Peoples R China

2.Lanzhou Univ, Minist Agr & Rural Affairs, Key Lab Grassland Livestock Ind Innovat, Lanzhou 730020, Peoples R China

3.Lanzhou Univ, Coll Pastoral Agr Sci & Technol, Lanzhou 730020, Peoples R China

4.Linxia Hui Autonomous Prefecture Anim Husb Technol, Linxia 731100, Peoples R China

5.Gansu Agr Univ, Lanzhou 730070, Peoples R China

6.Gansu Acad Agr Sci, Inst Anim Husb Pasture & Green Agr, Lanzhou 730070, Peoples R China

7.Xinjiang Aksu Taikun Feed Co Ltd, Aksu 842008, Peoples R China

关键词： Vis-NIR; Mutton; SHAP; SVM; Fatty acid

期刊名称：FOOD CHEMISTRY-X （ 影响因子：8.2； 五年影响因子：8.2 ）

ISSN： 2590-1575

年卷期： 2025 年 29 卷

页码：

收录情况： SCI

摘要： The rapid identification and prediction of nutritional components in fresh meat products pose a significant challenge. This study aims to classify different cuts of fresh mutton and predict their nutritional components using SVM and PLS model, focusing on the differences in fatty acid composition among the longissimus lumborum, hindshank, and foreshank. An SVM-SHAP model predicted crude fat, protein, and fatty acids, while interpreting feature contributions. PUFA were significantly higher in the hindshank than in the longissimus lumborum and foreshank. The SVM model achieved a classification accuracy of 92.5 % and successfully predicted key nutritional parameters such as EE, CP, MUFA and PUFA with RPD values exceeding 2.7 in the test set. SHAP value analysis revealed that lipid-related variables and wavelengths in the 2300-2500 nm region were major contributors to the model. Vis-NIR-based SVM modeling technology is a fast, non-destructive, and accurate tool for evaluating fresh mutton.

  • 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：甘肃省农业科学院

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