Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Reflectance spectral data in the range of 350 nm to 1700 nm were collected in this research to investigate the potential application of VIS/NIR to develop rapid and non-destructive optical technology for assessing the water content of fresh pork. Two prediction models were developed using partial least squares regression (PLSR) and multiple linear regression (MLR) method. The results indicated that PLSR model based on compound pre-processing methods of median smooth filter (M-filter), multiplication scatter correction (MSC), standard normalized variant (SNV) and first derivative (FD) yielded the best result. Total 57 fresh pork samples were used for developing prediction model. Cross-validation correlation coefficient and cross-validation standard deviation were 0.90 and 0.50 respectively. The correlation coefficient of 0.81 and root mean square error of 0.70 were obtained in validation set. The research results demonstrate that the visible/near-infrared combined with PLSR modeling can well detect water content in fresh pork.