An initial investigation into the use of machine learning methods for prediction of carcass component yields in F2 broiler chickens
Hossein Bani Saadat
A , Rasoul Vaez Torshizi A * , Ghader Manafiazar B , Ali Akbar Masoudi A , Alireza Ehsani A and Saleh Shahinfar C *
A
B
C
Abstract
As evaluation of carcass components is costly and time consuming, models for prediction of broiler carcass components are useful.
The aim was to investigate the feasibility of machine learning methods in the prediction of carcass components from measurements on live birds during the rearing period.
Three machine learning methods, including regression tree, random forest and gradient-boosting trees, were applied to predict carcass yields, and benchmarked against classical linear regression. Two scenarios were defined for prediction. In the first scenario, carcass yields were predicted by live bodyweight, shank length and shank diameter features, recorded at 2, 3 and 4 weeks of age. In the second scenario, predictor features recorded at 5, 6 and 7 weeks of age were used. The two scenarios were reanalysed by including effective single-nucleotide polymorphisms associated with bodyweight, shank length and shank diameter as new predictor features.
The correlation coefficient between predicted and observed values for predicting weight of carcass traits ranged from 0.50 for wing to 0.59 for thigh in the first scenario, and from 0.63 for wing to 0.74 for carcass in the second scenario. These predictions for the percentage of carcass components ranged from 0.30 for wing to 0.39 for carcass and breast in the first scenario, and from 0.34 for thigh to 0.43 for carcass in the second scenario when random forest was used.
Predictive accuracy in the first scenario was lower than in the second scenario for all prediction methods. Including single-nucleotide polymorphisms as predictor features in either scenario did not increase the accuracy of the prediction.
In general, random forest had the best performance among machine learning methods, and classical linear regression in two scenarios, suggesting that it may be considered as an alternative to conventional linear models for prediction of carcass traits in broiler chickens.
Keywords: broilers, carcass traits, gradient boosting machine, linear regression, machine learning, prediction, random forest, supply chain.
References
Ajayi FO, Ejiofor O, Ironkwe MO (2008) Estimation of body weight from linear body measurements in two commercial meat-type chicken. Global Journal of Agricultural Sciences 7, 57-59.
| Crossref | Google Scholar |
Alves AAC, Chaparro Pinzon A, Costa RMd, Silva MSd, Vieira EHM, Mendonca IBd, Lobo RNB (2019) Multiple regression and machine learning based methods for carcass traits and saleable meat cuts prediction using non-invasive in vivo measurements in commercial lambs. Small Ruminant Research 171, 49-56.
| Crossref | Google Scholar |
Andrássy-Baka G, Romvári R, Milisits G, Sütő Z, Szabó A, Locsmándi L, Horn P (2003) Non-invasive body composition measurement of broiler chickens between 4–18 weeks of age by computer tomography. Archives Animal Breeding 46, 585-595.
| Crossref | Google Scholar |
Bakoev S, Getmantseva L, Kolosova M, Kostyunina O, Chartier DR, Tatarinova TV (2020) PigLeg: prediction of swine phenotype using machine learning. PeerJ 8, e8764.
| Crossref | Google Scholar | PubMed |
Bani Saadat H, Vaez Torshizi R, Manafiazar G, Masoudi AA, Ehsani A, Shahinfar S (2024) Comparing machine learning algorithms and linear model for detecting significant SNPs for genomic evaluation of growth traits in F2 chickens. Journal of Agricultural Science and Technology in press.
| Google Scholar |
Breiman L (2001) Random forest. Machine Learning 45, 5-32.
| Crossref | Google Scholar |
Cha J, Choo H, Srikanth K, Lee S-H, Son J-W, Park M-R, et al. (2021) Genome-wide association study identifies 12 Loci associated with body weight at age 8 weeks in Korean Native Chickens. Genes 12, 1170.
| Crossref | Google Scholar | PubMed |
Chen J-T, He P-G, Jiang J-S, Yang Y-F, Wang S-Y, Pan C-H, Zeng L, He Y-F, Chen Z-H, Lin H-J, Pan J-M (2023) In vivo prediction of abdominal fat and breast muscle in broiler chicken using live body measurements based on machine learning. Poultry Science 102(1), 102239.
| Crossref | Google Scholar | PubMed |
Chu TT, Madsen P, Norberg E, Wang L, Marois D, Henshall J, Jensen J (2020) Genetic analysis on body weight at different ages in broiler chicken raised in commercial environment. Journal of Animal Breeding and Genetics 137(2), 245-259.
| Crossref | Google Scholar | PubMed |
Diez J, Bahamonde A, Alonso J, Lopez S, del Coz JJ, Quevedo JR, Ranilla J, Luaces O, Alvarez I, Royo LJ, Goyache F (2003) Artificial intelligence techniques point out differences in classification performance between light and standard bovine carcasses. Meat Science 64, 249-258.
| Crossref | Google Scholar | PubMed |
Ekiz B, Baygul O, Yalcintan H, Ozcan M (2020) Comparison of the decision tree, artificial neural network and multiple regression methods for prediction of carcass tissues composition of goat kids. Meat Science 161, 108011.
| Crossref | Google Scholar | PubMed |
Emrani H, Vaez Torshizi R, Akbar Masoudi A, Ehsani A (2017) Identification of new loci for body weight traits in F2 chicken population using genome-wide association study. Livestock Science 206, 125-131.
| Crossref | Google Scholar |
Erensoy K, Noubandiguim M, Cilavdaroglu E, Sarica M, Yamak US (2020) Correlations between breast yield and morphometric traits in broiler pure lines. Brazilian Journal of Poultry Science 22, eRBCA-2019-1148.
| Crossref | Google Scholar |
Faridi A, Sakomura NK, Golian A, Marcato SM (2012) Predicting body and carcass characteristics of 2 broiler chicken strains using support vector regression and neural network models. Poultry Science 91, 3286-3294.
| Crossref | Google Scholar | PubMed |
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. The Annals of Statistics 29, 1189-1232.
| Crossref | Google Scholar |
Greenwood PL (2020) Prediction of dressing percentage, carcass characteristics and meat yield of goats, and implications for live assessment and carcass-grading systems. Animal Production Science 61(3), 313-325.
| Crossref | Google Scholar |
Gu X, Feng C, Ma L, Song C, Wang Y, Da Y, et al. (2011) Genome-wide association study of body weight in chicken F2 resource population. PLoS ONE 6, e21872.
| Crossref | Google Scholar | PubMed |
Holcman A, Vadnjal R, Zlender B, Stibilj V (2003) Chemical composition of chicken meat from free range and extensive indoor rearing. Archiv für Geflügelkunde 67(3), 120-124.
| Google Scholar |
Jahan M, Maghsoudi A, Rokouei M, Faraji-Arough H (2020) Prediction and optimization of slaughter weight in meat-type quails using artificial neural network modeling. Poultry Science 99, 1363-1368.
| Crossref | Google Scholar | PubMed |
Liaw A, Wiener M (2002) Classification and regression by randomforest. R News 2(3), 18-22.
| Google Scholar |
Marchesi JAP, Ono RK, Cantão ME, Ibelli AMG, Peixoto JdO, Moreira GCM, Godoy TF, Coutinho LL, Munari DP, Ledur MC (2021) Exploring the genetic architecture of feed efficiency traits in chickens. Scientific Reports 11, 4622.
| Crossref | Google Scholar |
Martinez DA, Weil JT, Suesuttajit N, Umberson C, Scott A, Coon CN (2022) The Relationship between performance, body composition, and processing yield in broilers: a systematic review and meta-regression. Animals 12(19), 2706.
| Crossref | Google Scholar | PubMed |
Mebratie W, Reyer H, Wimmers K, Bovenhuis H, Jensen J (2019) Genome wide association study of body weight and feed efficiency traits in a commercial broiler chicken population, a re-visitation. Scientific Reports 9, 922.
| Crossref | Google Scholar |
Miller GA, Hyslop JJ, Barclay D, Edwards A, Thomson W, Duthie C-A (2019) Using 3D imaging and machine learning to predict liveweight and carcass characteristics of live finishing beef cattle. Frontiers in Sustainable Food Systems 3, 30.
| Crossref | Google Scholar |
Milosevic B, Ciric S, Lalic N, Milanovic V, Savic Z, Omerovic I, Doskovic V, Djordjevic S, Andjusic L (2019) Machine learning application in growth and health prediction of broiler chickens. World’s Poultry Science Journal 75, 401-410.
| Crossref | Google Scholar |
Mortensen AK, Lisouski P, Ahrendt P (2016) Weight prediction of broiler chickens using 3D computer vision. Computers and Electronics in Agriculture 123(123), 319-326.
| Crossref | Google Scholar |
Musa HH, Chen GH, Cheng JH, Li BC, Mekki DM (2006) Study on carcass characteristics of chicken breeds raised under the intensive condition. International Journal of Poultry Science 5, 530-533.
| Crossref | Google Scholar |
Nicodemus KK, Malley JD, Strobl C, Ziegler A (2010) The behaviour of random forest permutation-based variable importance measures under predictor correlation. BMC Bioinformatics 11, 110.
| Crossref | Google Scholar |
Nyalala I, Okinda C, Kunjie C, Korohou T, Nyalala L, Chao Q (2021) Weight and volume estimation of poultry and products based on computer vision systems: a review. Poultry Science 100(5), 101072.
| Crossref | Google Scholar | PubMed |
Ogah DM (2012) In vivo prediction of live weight and carcass traits using body measurements in indigenous guinea fowl. Biotechnology in Animal Husbandry 28, 137-146.
| Crossref | Google Scholar |
Pozo H, França Barcelos A, Kazue Akabane G (2018) Critical factors of success for quality and food safety management: classification and prioprization. Universal Journal of Industrial and Business Management 6(2), 30-41.
| Crossref | Google Scholar |
Raji AO, Igwebuike JU, Kwari ID (2010) Regression models for estimating breast, thigh and fat weight and yield of broilers from non invasive body measurements. International Journal of Agriculture and Biology 1(4), 469-475.
| Google Scholar |
Reyer H, Hawken R, Murani E, Ponsuksili S, Wimmers K (2015) The genetics of feed conversion efficiency traits in a commercial broiler line. Scientific Reports 5, 16387.
| Crossref | Google Scholar |
Ridgeway G (2013) Gbm: generalized boosted regression models. R Package version 2. https://cran.r-project.org/web//packages/gbm/gbm.pdf
Ruchay AN, Kolpakov VI, Kalschikov VV, Dzhulamanov KM, Dorofeev KA (2021) Predicting the body weight of Hereford cows using machine learning. IOP Conference Series: Earth and Environmental Science 624, 012056.
| Crossref | Google Scholar |
Sakamoto LS, Mercadante MEZ, Bonilha SFM, Branco RH, Bonilha EFM, Magnani E (2014) Prediction of retail beef yield and fat content from live animal and carcass measurements in Nellore cattle. Journal of Animal Science 92(11), 5230-5238.
| Crossref | Google Scholar | PubMed |
Scollan ND, Caston LJ, Liu Z, Zubair AK, Leeson S, McBride BW (1998) Nuclear magnetic resonance imaging as a tool to estimate the mass of the Pectoralis muscle of chickens in vivo. British Poultry Science 39, 221-224.
| Crossref | Google Scholar | PubMed |
Shafey TM, Alodan MA, Hussein EOS, Al-Batshan HA (2013) The effect of sex on the accuracy of predicting carcass composition of Ross broiler chickens. Journal of Animal and Plant Sciences 23, 975-980.
| Google Scholar |
Shahinfar S, Kelman K, Kahn L (2019) Prediction of sheep carcass traits from early-life records using machine learning. Computers and Electronics in Agriculture 156, 159-177.
| Crossref | Google Scholar |
Shahinfar S, Al-Mamun HA, Park B, Kim S, Gondro C (2020) Prediction of marbling score and carcass traits in Korean Hanwoo beef cattle using machine learning methods and synthetic minority oversampling technique. Meat Science 161, 107997.
| Crossref | Google Scholar | PubMed |
Silva SR, Pinheiro VM, Guedes CM, Mourao JL (2006) Prediction of carcase and breast weights and yields in broiler chickens using breast volume determined in vivo by real-time ultrasonic measurement. British Poultry Science 47, 694-699.
| Crossref | Google Scholar | PubMed |
Solano-Blanco AL, González JE, Medaglia AL (2023) Production planning decisions in the broiler chicken supply chain with growth uncertainty. Operations Research Perspectives 10, 100273.
| Crossref | Google Scholar |
Tyasi TL, Qin N, Niu X, Sun X, Chen X, Zhu H, Zhang F, Xu R (2018) Prediction of carcass weight from body measurement traits of Chinese indigenous Dagu male chickens using path coefficient analysis. The Indian Journal of Animal Science 88, 744-748.
| Crossref | Google Scholar |
Vaziri E, Maghsoudi A, Feizabadi M, Faraji-Arough H, Rokouei M (2022) Scientometric evaluation of 100-year history of Poultry Science (1921–2020). Poultry Science 101, 102134.
| Crossref | Google Scholar | PubMed |
Yigrem S, Banerjee S, Berihun K (2013) Comparison of linear with some nonlinear regression methods to estimate hot carcass weight using live weight in Arsi-Bale sheep and goats of both the sexes. World Applied Sciences Journal 21, 1603-1608.
| Crossref | Google Scholar |
Zhang GX, Fan QC, Zhang T, Wang JY, Wang WH, Xue Q, Wang YJ (2015) Genome-wide association study of growth traits in the Jinghai Yellow chicken. Genetics and Molecular Research 14, 15331-15338.
| Crossref | Google Scholar | PubMed |
Zheng C, Malbasa V, Kezunovic M (2012) Regression tree for stability margin prediction using synchrophasor measurements. IEEE Transactions on Power Systems 28, 1978-1987.
| Crossref | Google Scholar |
