Predicting the body weight of Balochi sheep using a machine learning approach

Various machine learning algorithms have been used to model and predict the body weight of rams of the Balochi sheepbreed of Pakistan. The traditional generalized linear model along with regression trees, support vector machine, and random forestsmethods have been used to develop models for the prediction of the body weight of animals. The independent variables (inputs) includethe body (body length, heart girth, withers height) and testicular (scrotal diameter, scrotal circumference, scrotal length, and testicularlength) measurements of 131 male sheep 2–36 months of age. The performance of the models is assessed based on evaluation criteriaof mean absolute error, mean absolute percentage error, correlation between observed and fitted values, coefficient of determination,and root mean squared error. A 10-fold cross-validation is done on a training dataset to check the stability of the models. A separatetraining dataset is used to assess the predictive performance of the developed models. The random forests model was found to providethe best results for both training and testing datasets. It was concluded that machine learning methods may provide better results thanthe traditional models and may help practitioners and researchers choose the best predictors for body weight of farm animals.

PDF

___

1. Bilgin OC, Emsen E, Davis MH. Comparison of non-linear models for describing the growth of scrotal circumference in Awassi male lambs. Small Rumin Res 2004; 52: 155-160. doi: 10.1016/S0921-4488(03)00251-7
2. Koyuncu M, Uzun SK, Ozis S, Duru S. Development of testicular dimensions and size, and their relationship to age and body weight in growing. Kivircik (Western Thrace) ram lambs. Czech J Anim Sci 2005; 50: 243-248. doi: 10.17221/4164-CJAS
3. Land RB, Gauld FK, Lee GS, Webb R. Further possibilities for manipulating the reproductive process. In: Barker SF, Hammond K, McClintock AE, editors. Further Development in the Genetic Improvement of Animals. Sydney, Australia: Academic Press; 1982. pp. 59-87.
4. Cam, MA, Olfaz M, Soydan E. Possibilities of using morphometrics characteristics as a tool for body weight production in Turkish hair goats (Kilkeci). Asian J Anim Vet Adv 2010; 5: 52-59. doi: 10.3923/ajava.2010.52.59
5. Tariq MM, Eyduran E, Bajwa MA, Waheed A, Iqbal F, Javed Y. Prediction of body weight from testicular and morphological characteristics in indigenous Mengali sheep of Pakistan: using factor analysis scores in multiple linear regression analysis. Int J Agric Biol 2012; 14: 590-594.
6. Rahman F. Prediction of carcass weight from the body characteristics of black goats. Int J Agric Biol 2007; 9: 431-434.
7. Cam MA, Olfaz M, Soydan E. Body measurement reflect body weights and carcass yields in Karakaya sheep. Asian J Anim Vet Adv 2010; 5: 120-127. doi: 10.3923/ajava.2010.120.127
8. Siddiqui MU, Lateef M, Bashir MK, Bilal MQ, Muhammad G, Mustafa MI, Rehman S. Estimation of live weight using different body measurements in Sahiwal Cattle. Pak J Life Soc Sci 2015; 13: 12-15.
9. Karadas K, Tariq M. Tariq MM, Eyduran E. Measuring predictive performance of data mining and artificial neural network algorithms for predicting lactation milk yield in indigenous Akkaraman sheep. Pak J Zool 2017; 49: 1-7. doi: 10.17582/journal.pjz/2017.49.1.1.7
10. Jahan M, Tariq MM, Kakar MA, Eudyran E, Waheed A. Predicting body weight from body and testicular characteristics of Balochi male sheep in Pakistan using different statistical analyses. J Anim Plant Sci 2013; 23: 14-19.
11. Khan MA, Tariq MM, Eyduran E, Tatliyer A, Rafeeq M, Abbas F, Rashid N, Awan MA, Javed, K. Estimating body weight from several body measurements in Harnai sheep without multicollinearity problem. J Anim Plant Sci 2014; 24: 120-126.
12. Ali M, Eyduran E, Tariq MM, Tirink C, Abbas F, Bajwa MA, Baloch MH, Nizamani AH, Waheed A, Awan MA, Shah SH, Ahmad Z, Jan S. Comparison of artificial neural network and decision tree algorithms used for predicting live weight at post weaning period from some biometrical characteristics in Harnai sheep. Pak J Zool 2015; 47: 1579-1585. doi: 10.17582/ journal.pjz/2015.47.6.1579.1585
13. Celik S, Yilmaz O. Comparison of different data mining algorithms for prediction of body weight from several morphological measurements in dogs. J Anim Plant Sci 2017; 27: 57-64.
14. Celik S, Yilmaz O. Prediction of body weight of Turkish Tazi dogs using data mining techniques: Classification and Regression Tree (CART) and Multivariate Adaptive Regression Splines (MARS). Pak J Zool 2018; 50: 575-583. doi: 10.17582/ journal.pjz/2018.50.2.55.583
15. Eyduran E, Zaborski D, Waheed A, Celik S, Karadas K, Grzesiak W. Comparison of the predictive capabilities of several data mining algorithms and multiple linear regression in the prediction of body weight by means of body measurements in the indigenous Beetal goat of Pakistan. Pak J Zool 2017; 49: 273-282. doi: 10.17582/journal.pjz/2017.49.1.273.282
16. Aytekin I, Eyduran E, Karadas K, Aksahan R, Keskin I. Prediction of fattening final live weight from some body measurements and fattening period in young bulls of crossbred and exotic breeds using MARS data mining algorithm. Pak J Zool 2018; 50: 189-195. doi: 10.17582/journal.pjz/2018.50.1.189.195
17. Nelder JA, Wedderburn RWM. Generalized linear models. J R Stat Soc Ser A 1972; 135: 370-384. doi: 10.2307/2344614
18. Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and Regression Trees. Boca Raton, FL, USA: Chapman & Hall/ CRC; 1984.
19. Breiman L. Random forests. Mach Learn 2001; 45: 5-32. doi: 10.1023/A:101093340
20. Vapnik V, Golowich S, Samola A. Support vector method for function approximation, regression estimation, and signal processing. In: Mozer M, Jordan M, and PetscheT, editors. Neural Information Processing Systems, Vol. 9. Cambridge, MA, USA: MIT Press; 1977.
21. Vapnik V. Statistical Learning Theory. DBLP; 2010.
22. Team RC. R: A Language and Environment for Statistical Computing. (Version 3.4.2). [Computer Software]. Vienna, Austria: R Foundation for Statistical Computing; 2017.
23. Mohammad MT, Rafeeq M, Bajwa MA, Awan A, Abbas F, Waheed A, Bukhari A, Akhtar P. Prediction of body weights from body measurements using Regression Tree (RT) method for indigenous sheep breed in Balochistan, Pakistan. J Anim Plant Sci 2012; 22: 20-24.