Determination of the total volatile basic nitrogen (TVB-N) content in pork meat using hyperspectral fluorescence imaging

Abstract

The total volatile basic nitrogen (TVB-N) content of meats is a key factor in measuring meat quality; however, conventional chemical methods for measuring TVB-N contents are time-consuming, labor-intensive, and are destructive procedures. The objective of this study is therefore to investigate the possibility of using hyperspectral fluorescence imaging techniques to determine TVB-N contents in pork meat. Thus, high-intensity light-emitting diodes at 365 nm were employed to acquire hyperspectral fluorescence images of the excitation. Prediction algorithms based on partial least squares (PLS) analysis and least squares support vector machines (LS-SVM) were developed. The coefficient of determination for the prediction data set (Rp2) and the standard error of prediction (SEP) of the optimal LS-SVM model for determining the TVB-N content were 0.967 and 1.902%, respectively. This study showed that visualization of the TVB-N distribution for the optimal model was useful for the spatial interpretation of the sample, and so we could conclude that hyperspectral fluorescence imaging exhibits potential for the rapid measurement of TVB-N contents in meats.