Near-Infrared (NIR) Spectroscopy to Differentiate Longissimus thoracis et lumborum (LTL) Muscles of Game Species

Abstract

Near-infrared (NIR) spectroscopy was used to distinguish between game meat from six different species, i.e. three medium-sized (impala, blesbok and springbok) and three large-sized (eland, black wildebeest and zebra) that were harvested (collected and slaughtered) from different farms across South Africa. Longissimus thoracis et lumborum (LTL) muscle steaks were removed and scanned with a handheld NIR spectrophotometer in the spectral range of 908 to 1700 nm. Spectra were treated with two different pre-processing combinations: (1) smoothing, standard normal variate and de-trending (SNV-Detrend), and (2) SNV-Detrend and Savitzky-Golay 2nd derivative. Data were explored with principal component analysis (PCA) and classified with linear discriminant analysis (LDA), soft independent modelling by class analogy (SIMCA) and partial least squares discriminant analysis (PLS-DA). For discrimination and classification, models were developed within each of the medium- and large-sized groups. LDA resulted in good classification accuracies ranging from 68 to 100%, irrespective of the pre-processing combination used. PLS-DA performed well (classification accuracies ranging from 70 to 96%) when spectra were treated with SNV-Detrend and Savitzky-Golay 2nd derivative. The prediction results obtained with SIMCA, pre-processed with smoothing and SNV-Detrend, ranged from 67% (springbok) to 100% (impala and eland). Although accurate models were obtained, they could still be improved by extending the sample set with meat samples from each species to cover variation in terms of season, geographical location, age and sex.