Combination model for freshness prediction of pork using VIS/NIR hyperspectral imaging with chemometrics
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objective: This study aimed to develop an enhanced model for predicting pork freshness by integrating hyperspectral imaging (HSI) and chemometric analysisMethods: A total of 30 <i>Longissimus thoracis</i> samples from three sows were stored under vacuum conditions at 4°C±2°C for 27 days to acquire data. The freshness prediction model for pork loin employed partial least squares regression (PLSR) with Monte Carlo data augmentation. Total bacterial count (TBC) and volatile basic nitrogen (VBN), which exhibited increases correlating with metabolite changes during storage, were designated as freshness indicators. Metabolic contents of the sample were quantified using nuclear magnetic resonance.Results: A total of 64 metabolites were identified, with 34 and 35 showing high correlations with TBC and VBN, respectively. Lysine and malate for TBC (R<sup>2</sup> = 0.886) and methionine and niacinamide for VBN (R<sup>2</sup> = 0.909) were identified as the main metabolites in each indicator by Model 1. Model 2 predicted main metabolites using HSI spectral data. Model 3, which predicted freshness indicators with HSI spectral data, demonstrated high prediction coefficients; TBC R<sup>2</sup><sub>p</sub> = 0.7220 and VBN R<sup>2</sup><sub>p</sub> = 0.8392. Furthermore, the combination model (Model 4), utilizing HSI spectral data and predicted metabolites from Model 2 to predict freshness indicators, improved the prediction coefficients compared to Model 3; TBC R<sup>2</sup><sub>p</sub> = 0.7583 and VBN R<sup>2</sup><sub>p</sub> = 0.8441.Conclusion: Combining HSI spectral data with metabolites correlated to the meat freshness may elucidate why certain HSI spectra indicate meat freshness and prove to be more effective in predicting the freshness state of pork loin compared to using only HSI spectral data.
Abstract
Objective: This study aimed to develop an enhanced model for predicting pork freshness by integrating hyperspectral imaging (HSI) and chemometric analysis Methods: A total of 30 Longissimus thoracis samples from three sows were stored under vacuum conditions at 4°C±2°C for 27 days to acquire data. The freshness prediction model for pork loin employed partial least squares regression (PLSR) with Monte Carlo data augmentation. Total bacterial count (TBC) and volatile basic nitrogen (VBN), which exhibited increases correlating with metabolite changes during storage, were designated as freshness indicators. Metabolic contents of the sample were quantified using nuclear magnetic resonance. Results: A total of 64 metabolites were identified, with 34 and 35 showing high correlations with TBC and VBN, respectively. Lysine and malate for TBC (R2 = 0.886) and methionine and niacinamide for VBN (R2 = 0.909) were identified as the main metabolites in each indicator by Model 1. Model 2 predicted main metabolites using HSI spectral data. Model 3, which predicted freshness indicators with HSI spectral data, demonstrated high prediction coefficients; TBC R2 p = 0.7220 and VBN R2 p = 0.8392. Furthermore, the combination model (Model 4), utilizing HSI spectral data and predicted metabolites from Model 2 to predict freshness indicators, improved the prediction coefficients compared to Model 3; TBC R2 p = 0.7583 and VBN R2 p = 0.8441. Conclusion: Combining HSI spectral data with metabolites correlated to the meat freshness may elucidate why certain HSI spectra indicate meat freshness and prove to be more effective in predicting the freshness state of pork loin compared to using only HSI spectral data.