Shortwave near Infrared–Hyperspectral Imaging Spectra to Detect Pork Adulteration in Beef Using Partial Least Square Regression Coupled with VIP Wavelength Selections Method

Pork adulteration detection in beef is important due to health, economic, and religious concerns. This study explored the use of a Shortwave Near Infrared–Hyperspectral Imaging (SWNIR–HSI) system which captured spectral data across 894–2504 nm to detect adulteration of pork in beef. In this study, minced pork in various concentrations ranging from 0–50 (w/w) were added to pure minced beef. Spectra obtained from the SWNIR–HSI were used to develop a partial least square regression (PLSR) model. The study compared the PLSR results between full wavelengths (variables) and selected wavelengths obtained via the variable importance in projection (VIP) method. The best results from the full-wavelength PLSR model yielded a prediction accuracy (R2P) of 0.940 and a standard error of prediction (SEP) of 4.633, while using VIP-selected wavelengths improved performance, with R2P of 0.955 and SEP of 3.811. The study demonstrates the potency of SWNIR–HIS, particularly with selected wavelengths, as an effective and nondestructive tool for accurately predicting pork adulteration levels in beef. © 2025 by the authors.