Czech J. Anim. Sci., 2022, 67(11):454-464 | DOI: 10.17221/129/2022-CJAS

Comparison of some non-linear functions to describe the growth for Linda geese with CART and XGBoost algorithmsOriginal Paper

Cem Tirink ORCID...*,1, Hasan Önder2, Sabri Yurtseven3, Zeliha Kaya Akil3
1 Department of Animal Science, Faculty of Agriculture, Igdir University, Igdir, Turkey
2 Department of Animal Science, Faculty of Agriculture, Ondokuz Mayis University, Samsun, Turkey
3 Department of Animal Science, Faculty of Agriculture, Harran University, Sanliurfa, Turkey

The aim of this study was to determine the best non-linear function describing the growth of the Linda goose breed. To achieve this aim, five non-linear functions, such as exponential, logistic, von Bertalanffy, Brody and Gompertz, were employed to define the live weight-age relationship for male and female Linda geese. In the study, 2 397 body weight-age records from 75 females and 66 males collected from three days to 17 weeks of age were evaluated using the "easynls" and "nlstools" packages for growth modelling of the Linda goose in R software. Each model was analysed in the live weight records of all the geese separately for males and females. To measure the predictive quality of the growth functions used individually here, model goodness of fit criteria, such as the coefficient of determination (R2), adjusted coefficient of determination (R2adj), root mean square error (RMSE), Akaike's information criterion (AIC) and Bayesian information criterion (BIC) were implemented. Among the evaluated non-linear functions, von Bertalanffy model gave the best fit of describing the growth curve of female and male Linda geese. Based on the "rpart", "rpart.plot", and "caret" R packages, the CART and XGBoost algorithms were specified in the prediction of live weight of Linda geese at 17 weeks of age from the growth parameters of the von Bertalanffy model and the sex factor. XGBoost produced better results in superiority compared with the CART algorithm. In conclusion, it could be suggested that the von Bertalanffy model might help geese breeders to determine the appropriate slaughtering time, feeding regimes, and overcome flock management problems. The results of the XGBoost algorithm might present a good reference for breeders to establish breed standards and selection strategies of Linda geese in the growth parameters for breeding purposes.

Keywords: body weight; goose growth curve; non-linear models; XGBoost; CART

Published: November 30, 2022  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Tirink C, Önder H, Yurtseven S, Akil ZK. Comparison of some non-linear functions to describe the growth for Linda geese with CART and XGBoost algorithms. Czech J. Anim. Sci. 2022;67(11):454-464. doi: 10.17221/129/2022-CJAS.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Abedi R, Costache R, Shafizadeh-Moghadam H, Pham QB. Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees. Geocarto Int. 2022;37(19):5479-96. Go to original source...
    2. Arnhold E. easynls: Easy nonlinear model. R package version 5.0. 2017 Nov 15 [cited 2021 Dec 8]. 9 p. Available from: https://CRAN.R-project.org/package=easynls
    3. Bahreini BMR, Aslaminejad AA, Sharifi AR, Simianer H. Comparison of mathematical models for describing the growth of Baluchi sheep. J Agric Sci Technol. 2014; 16(1):57-68.
    4. Baty F, Ritz C, Charles S, Brutsche M, Flandrois JP, Delignette-Muller ML. A toolbox for nonlinear regression in R: The package nlstools. J Stat Softw. 2015;66(5):1-21. Go to original source...
    5. Bharti JP, Mishra P, Moorthy U, Sathishkumar VE, Cho Y, Samui P. Slope stability analysis using Rf, gbm, cart, bt and xgboost. Geotech Geol Eng. 2021 Jun;39(5):3741-52. Go to original source...
    6. Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. 1st ed. New York: Routledge; 2017. 368 p. Go to original source...
    7. Cilavdaroglu E, Yamak US, Boz MA. Geese meat production. BSJ Agri. 2020;3(1):66-70.
    8. Do DN, Miar Y. Evaluation of growth curve models for body weight in American mink. Animals. 2019 Dec 20; 10(1): 10 p. Go to original source... Go to PubMed...
    9. Friedman J. Greedy function approximation: A gradient boosting machine. Ann Stat. 2001 Oct 1;29(5):1189-232. Go to original source...
    10. Gertz M, Grobe-Butenuth K, Junge W, Maassen-Francke B, Renner C, Sparenberg H, Krieter J. Using the XGBoost algorithm to classify neck and leg activity sensor data using on-farm health recordings for locomotor-associated diseases. Comput Electron Agric. 2020 Jun 1; 173: 105404. Go to original source...
    11. Gompertz B. On the nature of the function expressive of the law of human mortality, and on a new mode of determining the value of life contingencies. In a letter to Francis Baily. London, UK: Royal Society; 1825. p. 513-83. Go to original source...
    12. Gulbe A, Eyduran E. ehaGoF: Calculates goodness of fit statistics. R package version 0.1.1. 2020 Aug 11 [cited 2021 Dec 8]. 28 p. Available from: https://CRAN.R-project.org/package=ehaGoF Go to original source...
    13. Hrncar C, Josef B, Widya PBP. The growth curve of Gompertz model in body weight of mixed-sex goose breeds in Slovakia. Genet Biodiv J. 2021 Jan 25;5(1):28-32. Go to original source...
    14. Ibtisham F, An L, Li T, Niu Y, Xiao M, Zhang L, Jia R. Growth patterns of two Chinese native goose breeds. Braz J Poult Sci. 2017 Apr;19(2):203-9. Go to original source...
    15. Kaplan S, Gurcan EK. Comparison of growth curves using non-linear regression function in Japanese quail. J Appl Anim Res. 2018 Jan 1;46(1):112-7. Go to original source...
    16. Kaya Z, Yurtseven S. Effects of feeding systems on yield and performance of Linda geese (Anserinae sp.) in hot climatic conditions. S Afr J Anim Sci. 2021;51(5):628-34. Go to original source...
    17. Kopuzlu S, Sezgin E, Esenbuga N, Bilgin OC. Estimation of growth curve characteristics of Hemsin male and female sheep. J Appl Anim Res. 2014 Apr 3;42(2):228-32. Go to original source...
    18. Kuhn M. caret: Classification and regression training. R package version 6.0-86. 2020 [cited 2021 Dec 8]. 224 p. Available from: https://CRAN.R-project.org/package=caret
    19. Li Y, Shu H, Bindelle J, Xu B, Zhang W, Jin Z, Guo L, Wang W. Classification and analysis of multiple cattle unitary behaviors and movements based on machine learning methods. Animals. 2022 Apr 20;12(9): 13 p. Go to original source... Go to PubMed...
    20. Ma X, Sha J, Wang D, Yu Y, Yang Q, Niu X. Study on a prediction of P2P network loan default based on the machine learning LightGBM and XGboost algorithms according to different high dimensional data cleaning. Electron Commer Res Appl. 2018 Sep 1;31:24-39. Go to original source...
    21. Milborrow S. rpart.plot: Plot 'rpart' models: An enhanced version of 'plot.rpart'. R package version 3.0.9. 2020 [cited 2021 Dec 8]. 25 p. Available from: https://CRAN.R-project.org/package=rpart.plot
    22. Onder H, Boz MA, Sarica M, Abaci SH, Yamak US. Comparison of growth curve models in Turkish native geese. Eur Poult Sci. 2017 Jul 6;81:1-8. Go to original source...
    23. Onk K, Sari M, Gurcan IS, Adiguzel Isik S. Live weight and body measurements of male and female native ducks raised in different raising systems. Braz J Anim Sci. 2018 May 3;47: 7 p. Go to original source...
    24. R Core Team. R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. 2020 [cited 2021 Dec 8]. Available from: https://www.R-project.org/
    25. Ramos SB, Caetano SL, Savegnago RP, Nunes BN, Ramos AA, Munari DP. Growth curves for ostriches (Struthio camelus) in a Brazilian population. Poult Sci. 2013 Jan 1;92(1):277-82. Go to original source... Go to PubMed...
    26. Revelle W. psych: Procedures for personality and psychological research. R package version 2.0.12. Evanston, IL, USA: Northwestern University. 2020 [cited 2021 Dec 8]. Available from: https://CRAN.R-project.org/package=psych
    27. Sakar CM, Erisek A. Development of Akkaraman lambs in Cankiri region from birth to 120 days. Black Sea J Agric. 2019;2(1):16-20.
    28. Stevenson H, Bly B, Stevenson H. Nutrition of domestic geese. Proc Nutr Soc. 1989 Jan;48(1):103-11. Go to original source... Go to PubMed...
    29. Therneau T, Atkinson B. rpart: Recursive partitioning and regression trees. R package version 4.1-15. 2019 [cited 2021 Dec 8]. Available from: https://CRAN.R-project.org/package=rpart
    30. Topal M, Ozdemir M, Aksakal V, Yildiz N, Dogru U. Determination of the best nonlinear function in order to estimate growth in Morkaraman and Awassi lambs. Small Rumin Res. 2004 Oct 1;55(1-3):229-32. Go to original source...
    31. von Bertalanffy L. Quantitative laws in metabolism and growth. Q Rev Biol. 1957 Sep 1;32(3):217-31. Go to original source... Go to PubMed...
    32. Warner D, Vasseur E, Lefebvre DM, Lacroix RL. A machine learning based decision aid for lameness in dairy herds using farm-based records. Comput Electron Agric. 2020 Feb 1;169: 105193. Go to original source...
    33. Wu HL, Zhou B, Wang HY, Liu Y, Hu YD, Zhu Q, He DQ. Analyze on growth curve fitting of Zhejiang White goose. China Anim Husb & Vet Med. 2011;38(5):134-7.
    34. Yang X, Fang T, Li Y, Guo L, Li F, Huang F, Li L. Pre-diabetes diagnosis based on ATR-FTIR spectroscopy combined with CART and XGBoots. Optik. 2019 Feb 1;180:189-98. Go to original source...
    35. Yu X, Wang Y, Wu L, Chen G, Wang L, Qin H. Comparison of support vector regression and extreme gradient boosting for decomposition-based data-driven 10-day streamflow forecasting. J Hydrol. 2020 Mar 1;582: 124293. Go to original source...
    36. Zaborski D, Ali M, Eyduran E, Grzesiak W, Tariq MM, Abbas F, Waheed A, Tirink C. Prediction of selected reproductive traits of indigenous Harnai sheep under the farm management system via various data mining algorithms. Pak J Zool. 2019 Apr 30;51(2):421-31. Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content