Rapid discrimination of intact beef, venison and lamb meat using Raman spectroscopy

With increasing demand for fast and reliable techniques for intact meat discrimination, we explore the potential of Raman spectroscopy in combination with three chemometric techniques to discriminate beef, lamb and ve nison meat samples. Ninety (90) intact red meat samples were measured using Raman spectroscopy, with the acquired spectral data preprocessed using a combination of rubber-band baseline correction, Savitzky-Golay smoothing and standard normal variate transformation. PLSDA and SVM classification were utilized in building classification models for the meat discrimination, whereas PCA was used for exploratory studies. Results obtained using linear and non-linear kernel SVM models yielded sensitivities of over 87 and 90 % respectively, with the corresponding specificities above 88 % on validation against a test set. The PLSDA model yielded over 80 % accuracy in classifying each of the meat specie. PLSDA and SVM classification models in combination with Raman spectroscopy posit an effective technique for red meat discrimination.

Automated summary

Raman spectroscopy combined with chemometric techniques such as PLSDA and SVM proved to be an effective method for discriminating between beef, lamb, and venison meat samples, with high sensitivity and specificity levels achieved.