Method and system for nondestructive detection of freshness in Penaeus vannamei based on hyperspectral technology

Abstract

To test the freshness of Penaeus vannamei rapidly and non-destructively, we constructed a quantitative prediction model for total volatile basic nitrogen (TVB-N) content by collecting 860–1700 nm hyperspectral data and TVB-N content of samples of P. vannamei during eight consecutive days. In this study, we compared the influence of six kinds of spectral pretreatment on the partial least-squares regression modeling (PLSR), which included multiple scattering correction (MSC), standard normal variate transformation (SNV), normalized mean centering, 11-point moving-average smoothing, and Savitzky–Golay smoothing. The results demonstrate that the prediction effect of the MSC-PLSR model has the best relative model accuracy, under the pretreatment of the MSC algorithm for spectral data. In addition, principal component analysis (PCA) and the Mahalanobis distance algorithm were used to remove anomalous samples. The results reveal that the prediction effect of the MSC-PLSR model is better than other models that we considered, and the correlation coefficient (R) of the validation set reached 0.8147. Finally, this study developed a graphical user interface system to predict freshness, based on our research, which provides a method and an analysis tool to rapidly detect the freshness of P. vannamei.