Non-Destructive Detection of Meat Quality Based on Multiple Spectral Dimension Reduction Methods by Near-Infrared Spectroscopy

The potential of four dimension reduction methods for near-infrared spectroscopy was investigated, in terms of predicting the protein, fat, and moisture contents in lamb meat. With visible/near-infrared spectroscopy at 400-1050 nm and 900-1700 nm, respectively, calibration models using partial least squares regression (PLSR) or multiple linear regression (MLR) between spectra and quality parameters were established and compared. The MLR prediction models for all three quality parameters based on the wavelengths selected by stepwise regression achieved the best results in the spectral region of 400-1050 nm. As for the spectral region of 900-1700 nm, the PLSR prediction model based on the raw spectra or high-correlation spectra achieved better results. The results of this study indicate that sampling interval shortening and of peak-to-trough jump features are worthy of further study, due to their great potential in explaining the quality parameters.

Automated summary

The potential of four dimension reduction methods for near-infrared spectroscopy in predicting the protein, fat, and moisture contents in lamb meat was investigated. Calibration models based on partial least squares regression (PLSR) or multiple linear regression (MLR) were established and compared for spectra and quality parameters at different spectral regions. The results showed that MLR prediction models with wavelengths selected by stepwise regression achieved the best results in the spectral region of 400-1050 nm, while PLSR prediction models based on raw spectra or high-correlation spectra achieved better results in the spectral region of 900-1700 nm. Sampling interval shortening and peak-to-trough jump features were identified as potential areas for further study in explaining the quality parameters.