School of Veterinary and Life Sciences, Murdoch University, WA 6150, Australia; Advanced Livestock Measurement Technologies project, Meat and Livestock Australia, NSW 2060, Australia.
School of Veterinary and Life Sciences, Murdoch University, WA 6150, Australia; Advanced Livestock Measurement Technologies project, Meat and Livestock Australia, NSW 2060, Australia.
Meat Sci. 2021 Nov;181:108398. doi: 10.1016/j.meatsci.2020.108398. Epub 2020 Dec 4.
The experiment evaluated the ability of portable ultra-wide band microwave coupled with a Vivaldi patch antenna to predict carcase C-site fat and GR tissue depth. For C-site, 1070 lambs, across 8 slaughter groups were scanned and for GR, 286 lambs across 2 slaughter groups. Prediction equations for reflected microwave signals were constructed with a partial least squares regression two-components model and a machine learning Ensemble Stacking technique. Models were trained and validated using cross validation methods in actual datasets and then in datasets balanced for tissue depth. The precision and accuracy indicators of microwave predicted C-site fat depth across pooled and balanced datasets were RMSEP 1.53 mm, R2 0.54, and bias of 0.03 mm. The precision and accuracy for GR tissue depth across pooled and balanced datasets were RMSEP 2.57 mm, R2 0.79 and bias of 0.33 mm. Using the AUS-MEAT fat score accreditation framework this device was able to accurately predict GR 92.7% of the time.
该实验评估了便携式超宽带微波与 Vivaldi 贴片天线相结合，预测胴体 C 部位脂肪和 GR 组织深度的能力。对于 C 部位，对 8 个屠宰组的 1070 只羔羊进行了扫描，对于 GR，对 2 个屠宰组的 286 只羔羊进行了扫描。使用偏最小二乘回归双组分模型和机器学习集成堆叠技术构建了反射微波信号的预测方程。使用实际数据集和平衡组织深度的数据集的交叉验证方法对模型进行了训练和验证。微波预测 C 部位脂肪深度的综合和平衡数据集的精度和准确性指标为 RMSEP 1.53mm，R2 0.54，偏差为 0.03mm。综合和平衡数据集的 GR 组织深度的精度和准确性指标为 RMSEP 2.57mm，R2 0.79 和偏差为 0.33mm。使用 AUS-MEAT 脂肪评分认证框架，该设备能够准确预测 GR 的时间为 92.7%。
