Establishing the provenance of eggs from backyard growing system of hens can be challenging, in the context of high-value commercial products (the price of an egg from backyard chicken rearing system is double comparing with one from barn rearing regime). In this study, 90 egg yolk samples were investigated from isotopic, elemental and fatty acids profiles point of view. To identify the egg production system (backyard versus barn), three pattern recognition techniques were applied: linear discriminant analysis (LDA), k-nearest neighbor (k-NN) and multilayer perceptron artificial neural networks (MLP-ANN). LDA revealed a perfect separation for initial classification, while a percentage of 98.9% in cross-validation procedure was reached. From k-NN analysis, the overall classification rate was 98.4% for training set and 85.7% for testing set. After running the MLP-ANN, an overall percent of 100% for training set was obtained, while for the testing step decreased up to 92.3%, two samples being misclassified.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.