A recent study (here – purchase needed) piloted the use of a non-destructive in-line sensor to detected minced beef adulteration at economically-significant levels. The authors used hyperspectral imaging (HSI) in the 400–1000 nm spectral range in tandem with multivariate analysis. They evaluated the use of partial least squares regression (PLSR) method, the ensemble Monte Carlo variable selection method (EMCVS), a range of spectral pre-treatments, and combinations of any two of them to predict the amount of minced beef in each prepared sample scanned. They developed a prediction model using data from beef adulterated with minced chicken and turkey meats and validated with data from beef adulterated with pork meat at adulteration levels ranging from 0 to 51% at approximately 3% increments. They reported good prediction results using the EMCVS, on the asymmetric least squares (AsLs) + Standard Normal variate (SNV) pre-treated reflectance spectra, using 23 selected wavelengths. They then tested the model on an independent set of beef samples adulterated with lamb and duck meat at concentrations ranging from 3 to 21% and reported good results with 9 optimum wavelengths. They reported almost perfect classification for calibration, cross-validation, and prediction using 12 selected spectral bands. They concluded that this method could be used to further develop low-cost portable sensors for the digital sorting of adulterated minced beef and that their study demonstrates the feasibility of generic models to detect minced beef meat adulterated with other types of meat.
Picture by Charlie Harris on Unsplash
Comments