Wang Li, Sun Xuchun, Liang Jing, Ma Zhiyuan, Li Fei, Hao Shengyan, Liu Baocang, Guo Long, Weng Xiuxiu
State Key Laboratory of Herbage Improvement and Grassland Agro-ecosystems; Key Laboratory of Grassland Livestock Industry Innovation, Ministry of Agriculture and Rural Affairs; College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730020, PR China.
Linxia Hui Autonomous Prefecture Animal Husbandry Technology Promotion Station, Linxia 731100, China.
Food Chem X. 2025 Jul 4;29:102739. doi: 10.1016/j.fochx.2025.102739. eCollection 2025 Jul.
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 , 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.
新鲜肉类产品中营养成分的快速识别和预测是一项重大挑战。本研究旨在利用支持向量机（SVM）和偏最小二乘法（PLS）模型对不同部位的新鲜羊肉进行分类，并预测其营养成分，重点关注腰大肌、后小腿和前小腿之间脂肪酸组成的差异。一个支持向量机-夏普利值（SVM-SHAP）模型在解释特征贡献的同时，对粗脂肪、蛋白质和脂肪酸进行了预测。后小腿中的多不饱和脂肪酸（PUFA）显著高于腰大肌和前小腿。支持向量机模型的分类准确率达到92.5%，并在测试集中成功预测了关键营养参数，如粗脂肪（EE）、粗蛋白（CP）、单不饱和脂肪酸（MUFA）和多不饱和脂肪酸（PUFA），其残差预测偏差（RPD）值超过2.7。夏普利值（SHAP）分析表明，脂质相关变量和2300 - 2500纳米区域的波长是该模型的主要贡献因素。基于可见-近红外光谱的支持向量机建模技术是一种快速、无损且准确的新鲜羊肉评估工具。
