Zuo Jiewen, Peng Yankun, Li Yongyu, Chen Yahui, Yin Tianzhen, Chao Kuanglin
College of Engineering, China Agricultural University, Beijing 100083, China.
Environmental Microbial and Food Safety Laboratory, USDA-ARS, Beltsville, MD 20705, United States.
Food Chem. 2025 Feb 15;465(Pt 2):142117. doi: 10.1016/j.foodchem.2024.142117. Epub 2024 Nov 21.
Accurate Total Viable Count (TVC) detection is vital for food quality monitoring. In this study, we investigated the feasibility of using visible near-infrared (VNIR) spectroscopy (400-1000 nm) combined with transfer learning (TL) to track the chemical spoilage of pork. The base models developed using the full band for pork TVC, total volatile basic nitrogen, pH, and color showed predictability; the correlation coefficient of prediction set (R) for all models ranged from 0.821 to 0.916; and the root mean square error of prediction set (RMSEP) of the TVC model was 0.617 (lg CFU/g). A correlation analysis of the different indexes of pork was carried out to optimize the TVC calibration model. Different TL methods for TVC optimization were designed. The results showed that multiple correlation chain stacking-partial least squares performed best with R, RMSEP, and the relative percent deviation of 0.947, 0.425 lg CFU/g, and 2.355, respectively, the RMSEP of TVC was reduced by 31.12 % as compared to the base model. This study demonstrated the possibility of combining the VNIR spectroscopy system with TL to monitor the degree of meat's chemical spoilage.
准确的总活菌数（TVC）检测对于食品质量监测至关重要。在本研究中，我们研究了使用可见近红外（VNIR）光谱（400 - 1000 nm）结合迁移学习（TL）来追踪猪肉化学变质情况的可行性。使用全波段建立的用于预测猪肉TVC、总挥发性盐基氮、pH值和颜色的基础模型显示出可预测性；所有模型预测集的相关系数（R）范围为0.821至0.916；TVC模型预测集的均方根误差（RMSEP）为0.617（lg CFU/g）。对猪肉的不同指标进行了相关性分析以优化TVC校准模型。设计了用于TVC优化的不同迁移学习方法。结果表明，多重相关链堆叠 - 偏最小二乘法表现最佳，其R、RMSEP和相对百分偏差分别为0.947、0.425 lg CFU/g和2.355，与基础模型相比，TVC的RMSEP降低了31.12%。本研究证明了将VNIR光谱系统与迁移学习相结合以监测肉类化学变质程度的可能性。
