Near Infrared to Classify Dry Cured Hams05 October 2013
Research from institutes and universities in Slovenia and Spain has found that near infrared spectroscopy and artificial neural networks have a practical relevance in the classification of dry cured hams.
The research drew together a team from Slovenia’s University of Maribor, University of Ljubljana, National Institute for Chemistry and the Agricultural Institute of Slovenia and the Institute of Agri-Food Research and Technology (IRTA) in Girona in Spain.
The team of M. Prevolnik, D. Andronikov, B. Žlender, M. Font-i-Furnols, M. Novic, D. Škorjanc and M. Candek-Potokar found the results represent practical relevance for control purposes in dry ham processing.
However, the team said that the results were valid for the Slovenian style dry cured ham, Kraški pršut, and for other products further verification is needed.
Kraški pršut’ is an air-dried/matured meat product made from whole fresh hind legs of pork.
A distinguishing feature of ‘Kraški pršut’ is its standard and recognisable shape.
Fresh hind legs are prepared without the feet, but with the rind and fat, if any.
A fresh hind leg must weigh at least 9 kg. The muscle meat extends 5-7 cm from below the head of the thigh bone (Caput ossis femoris). On the inside of the hind
leg, the muscle meat is uncovered; the rind and fat are trimmed slightly more towards the shank.
The study attempted to classify dry-cured hams according to the maturation time on the basis of near infrared (NIR) spectra.
The study comprised 128 samples of biceps femoris (BF) muscle from dry-cured hams matured for 10 (n = 32), 12 (n = 32), 14 (n = 32) or 16 months (n = 32).
Samples were minced and scanned in the wavelength range from 400 to 2500 nm using spectrometer NIR System model 6500 (Silver Spring, MD, USA).
Spectral data were used for i) splitting of samples into the training and test set using 2D Kohonen artificial neural networks (ANN) and for ii) construction of classification models using counter-propagation ANN (CP-ANN).
Different models were tested, and the one selected was based on the lowest percentage of misclassified test samples (external validation).
Overall correctness of the classification was 79.7 per cent, which demonstrates practical relevance of using NIR spectroscopy and ANN for dry-cured ham processing control.
The research is published in the January 2014 issue of Meat Science.