Prediction of Carcass Meat Percentage in Young Pigs Using Linear Regression Models and Artificial Neural Networks

Magdalena Szyndler-Nędza 1 , Robert Eckert 1 , Tadeusz Blicharski 2 , Mirosław Tyra 1  and Artur Prokowski 3
  • 1 Department of Genetics and Animal Breeding, National Research Institute of Animal Production, 32-083 Balice n. Kraków, Poland
  • 2 Institute of Genetics and Animal Breeding, Polish Academy of Sciences, Postępu 36A, Jastrzębiec, 05-552 Magdalenka, Poland
  • 3 Department of Informatics, National Research Institute of Animal Production, 32-083 Balice n. Kraków, Poland


One of the approaches to improving performance testing of pigs is to look for mathematical solutions to increase the accuracy of calculations. This is mainly done through improvement of linear regression equations based on current data on performance tested pigs in Poland. The advances in computer technology and the improvements in mathematical analysis have made it possible to use artificial neural networks (ANNs) for prediction of carcass meat percentage in young pigs. The aim of the study was to compare the potential for live estimation of carcass meat percentage in pigs using two computational methods: linear regression equations and ANNs. The experiment used 654 gilts of six breeds, which were subjected to performance testing and slaughter analysis at the Pig Performance Testing Station (SKURTCh). The collected data were used to train ANNs to estimate carcass meat percentage in young pigs. Training was performed using the Levenberg- Marquardt algorithm. Next, meatiness estimated by ANNs was compared with the results obtained using linear modelling. It is concluded that based on the fattening and slaughter performance test results of live pigs, artificial neural networks (SSN23) are significantly more accurate in estimating carcass meat percentage in young pigs compared to the three-variable linear regression model 1. The difference in meatiness estimation between SSN23 and the four-variable linear regression model 2 was statistically non-significant in most of the breeds except Duroc and Pietrain, where the meatiness of young animals was estimated more accurately by the linear regression model.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Adamczyk K., Molenda K., Szarek J., Skrzyński G. (2005). Prediction of bulls’slaughter value from growth data using artificial neural network. J. Centr. Europ. Agric., 6: 133-142.

  • Adya M., Collopy F. (1998). How effective are neural networks at forecasting and prediction? A review and evaluation. J. Forecast., l; 481-495.

  • Berg E.P., Engel B.A., Forrest J.C. (1998). Pork carcass composition derived fromaneural network model of electromagnetic scans. J. Anim. Sci., 76: 18-22.

  • Eckert R., Żak G., Bereta A. (2014). Results of performance tested gilts (in Polish). Report on pig breeding in Poland. Kraków, IZ PIB XXXII: 35-48.

  • Hervas C., Garrido A., Lucena B., Garcia N., De Pedro E. (1994). Near infrared spectroscopy for classification of Iberian pig carcasses using an artificial neural network. J. Near Infrared Spectrosc., 2: 177-184.

  • Ichikawa H. (2003). Hierarchy neural networks as applied to pharmaceutical problems. Advanc. Drug Deliv. Rev., 55: 1119-1147.

  • Klimas R., Klimiene A., Rimkevicius S. (2004). Efficiency of breeding pigs selection according to phenotypic evaluation of meatiness. Vet. Zoot., 27: 79-86.

  • Kumar U.A. (2005). Comparison of neural networks and regression analysis: Anew insight. Expert Syst. with Applic., 29: 424-430.

  • Lisiak D., Borzuta K. (2014). The influence of the SEUROPgrade and weight of pig carcasses on lean meat content evaluated using regression equations from 2003 and 2011 (in Polish). Rocz. Nauk. PTZ, 10: 65-75.

  • Migdał - Najman K., Najman K. (2000). Neural networks, use for forecasting WIG (in Polish). Katedra Statystyki, Wydział Zarządzania, Uniwersytet Gdański, pp. 1-17.

  • Paliwal M., Kumar U.A. (2009). Astudy of academic performance of business school graduates using neural network and statistical techniques. Expert Syst. with Applic., 36: 7865-7872.

  • Radović Č., Petrović M., Živković B., Radojković D., Parunović N., Brkić N., Delić N. (2013). Heritability, phenotypic and genetic correlations of the growth intensity and meat yield of pigs. Biotech. Anim. Husb., 29: 75-82.

  • Różycki M., Tyra M. (2010). Methodology for evaluating the value of fattening and slaughter pigs carried out in the stations of performance control slaughter pigs (SKURTCh) (in Polish). Report on pig breeding in Poland. IZ PIB XXVIII: 93-117.

  • Stricklin W.R.,de Bourcier P., Zhou J.Z., Gonyou H.W. (1998). Artificial pigs in space: using artificial intelligence and artificial life techniques to design animal housing. J. Anim. Sci., 76: 2609-2613.

  • Subba Narasimha P.N., Arinze B ., Anandarajan M. (2000). The predictive accuracy of artificial neural networks and multiple regression in the case of skewed data: Exploration of some issues. Expert Syst. Applic., 19: 117-123.

  • Szyndler-Nędza M., Eckert R. (2008). Relationships between live measurements of backfat and longissimus dorsi thickness and fatness as well as muscularity of carcass, ham and loin of boars and gilts (in Polish). Rocz. Nauk. PTZ., 4: 103-113.

  • Ślipek Z., Francik S., Frączek J. (2003). Methodic aspects of creating ANNmodels in agrophysical research (in Polish). Acta Agrophysica, 2: 231-241.

  • Xin H. (1999). Assessing swine thermal comfort by image analysis of postural behaviors. J. Anim. Sci., 77: 1-9.


Journal + Issues