Chromatographic fingerprints supported by artificial neural network for differentiation of fresh and frozen pork

The sale of defrosted meat without reporting the use of frozen storage is a method of food adulteration. The aim of this study was to determine the possibility of differentiating fresh pork neck, loin and ham from frozen pork neck, loin, ham and also from spoiled pork with an electronic nose (E-nose) based on ultra-fast gas chromatography (UFGC) supported by supervised artificial neural network (ANN). The performance of the Principal Components Analysis (PCA) models was applied in this research to check the possibility to classify pork samples in the respective freshness group. The applied ANN was a three-layer (excluding input layer) non-linear perceptron consisting of more than 200 cells and using sigmoidal function and no bias. The ANN was implemented as a C program with automated (batch) learning capability. Tests were carried out on pork meat from pigs obtained from a breeding farm. The chromatographic fingerprint of samples of fresh meat, frozen-thawed meat and spoiled meat were analyzed by the ANN. The study has shown that use of E-nose with the ANN allows to effectively recognize fresh (80%), frozen-then-thawed (85%) and spoiled meat (90%). In practice this technique may be applied to quick, cheap and reliable introduction and rapid recognition of chopped pork and for the differentiation of fresh and frozen pork.