Nondestructive measurement of total volatile basic nitrogen (TVB-N) content in salted pork in jelly using a hyperspectral imaging technique combined with efficient hypercube processing algorithms

Abstract

Total volatile basic nitrogen (TVB-N) content is an important index in evaluating the freshness of salted pork in jelly (SPIJ). This work attempted the nondestructive measurement of TVB-N content in the SPIJ using hyperspectral imaging (HSI) with efficient hypercube processing algorithms. Firstly, we developed a VIS-NIR HSI system for data acquisition and extracted the spectra (430–960 nm) from a 3-dimensional hypercube; then selected the efficient spectral intervals using a synergy interval PLS (Si-PLS) algorithm and further selected four dominant waveband images using a genetic algorithm (GA); next we extracted 6 characteristic variables from each dominant waveband image using texture analysis based on statistical feature calculation; finally, principal component analysis (PCA) was implemented on spectral variables and image variables, respectively. A back-propagation artificial neural network (BP-ANN) was used to achieve data fusion and construct a model for TVB-N content prediction. The optimum results were achieved with the root mean square error of prediction (RMSEP) = 6.3435 mg per 100 g and the correlation coefficient (Rp) = 0.8334 in the prediction set. This work demonstrates that HSI with an efficient hypercube processing algorithm has a high potential in nondestructive measurement of TVB-N content in SPIJ.