Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed

• Published in: Acta scientiarum. Animal sciences Vol. 41; no. 1; pp. 45282 - e45282
• Main Authors: Ghotbaldini, Hamidreza, Mohammadabadi, Mohammadreza, Nezamabadi-pour, Hossein, Babenko, Olena Ivanivna, Bushtruk, Maryna Vitaliivna, Tkachenko, Serhii Vasyliovych
• Format: Journal Article
• Language: English; Portuguese
• Published: Maringa Editora da Universidade Estadual de Maringá - EDUEM 2019; Editora da Universidade Estadual de Maringá (Eduem)
• Subjects: Age; Algorithms; Animals; Artificial neural networks; Back propagation; Back propagation networks; Birth weight; Body weight; Breeding; Computer architecture; Computer programs; Domestic animals; estimate; genetic parameters; growth traits; lamb; Multilayer perceptrons; Neural networks; Parameter estimation; Sheep; Software; VETERINARY SCIENCES; Weaning; estimate; lamb; genetic parameters; growth traits
• ISSN: 1806-2636; 1807-8672; 1807-8672
• DOI: 10.4025/actascianimsci.v41i1.45282

The present study aimed to apply artificial neural networks to predict the breeding values of body weight in 6-month age of Kermani sheep. For this purpose, records of 867 lambs including lamb sex, dam age, birth weight, weaning weight, age at 3-month (3 months old), age at 6-month (6 months old) and body weight at 3 months of age were used. Firstly, genetic parameters of the animals were estimated using ASReml software. The data was then pre-processed for using in MATLAB software. After initial experiments on the appropriate neural network architecture for body weight at 6-month age, two networks were examined. A feed-forward backpropagation multilayer perceptron (MLP) algorithm was used and 70% of all data used as training data, 15% as testing data and 15% as validating data, to prevent over-fitting of the artificial neural network. Results showed that the both networks capable to predict breeding values for body weight at 6 month-age in Kermani sheep. It can be concluded that artificial neural network has a good ability to predict growth traits in Kermani sheep with an acceptable speed and accuracy. Therefore, this network, instead of commonly-used procedures can be used to estimate the breeding values for productive and reproductive traits in domestic animals.