Muhammad ALI, Farhat IQBAL, Abdul RAZIQ, Zil E HUMA

An application of least square support vector machine model with parameters optimization for predicting body weight of Harnai sheep breed

This study utilized a model based on the least square support vector machine (LSSVM) for the prediction of body weight (BW) of sheep. Two heuristic algorithms, namely, coupled simulated annealing (CSA) and simplex method (S) were applied to tune the hyperparameters of the LSSVM model. The hybrid CSA-S-LSSVM method is then applied to the male, female and total data of the Harnai sheep breed of Pakistan. Various biometric traits such as withers height, body length, chest girth, face length, paunch circumference, ear length, the length between ears, fat tail width and fat tail length were used as predictors. Goodness of fit measures such as mean absolute error (MAE), root mean square error (RMSE), adjusted coefficient of determination (Adj.R2 ), normalized mean square error (NMSE) and mean absolute percentage error (MAPE) were used for evaluation. Comparison of the predictive performance of the proposed model on 10-fold cross-validation against both conventional (ridge regression) and state of the art machine learning (artificial neural networks) methods showed that the CSA-S-LSSVM outperformed both competing models by achieving the least values for MAE, RMSE, NMSE and MAPE and the highest value for Adj.R2 in both training and testing data sets. The results were promising, accurate and viable for the prediction of BW of sheep.

PDF

___

1. Obike OM, Ibe SN, Oke UK. Estimation of pre- and postweaning body weight of rabbits in a humid tropical environment using linear body measurements. American-Eurasian Journal of Agricultural & Environmental Sciences 2010; 9 (4): 440-444.
2. Waheed HM, Moaeen-ud-Din M, Khan MS, Saif-ur-Rehman M, Nawaz-ul-Rehman MS. Prediction of monthly body weight from body measurements in Beetal goats reared under field and farm conditions. Journal of Animal and Plant Sciences 2020; 30 (1): 25-31.
3. Khan MA, Tariq MM, Eyduran E, Tatliyer A, Rafeeq M et al. Estimating body weight from several body measurements in Harnai sheep without multicollinearity problem. Journal of Animal and Plant Sciences 2014; 24 (1): 120-126.
4. Eyduran E, Waheed A, Tariq MM, Iqbal F, Ahmed S. Prediction of live weight from morphological characteristics of commercial goat in Pakistan using factor and principal component scores on multiple linear regression. Journal of Animal and Plant Sciences 2013; 23 (6): 1532-1540.
5. Hoerl AE, Kennard RW. Ridge regression: biased estimation for nonorthogonal problems. Technometrics 1970; 12 (1): 55- 67. doi: 10.1080/00401706.1970.10488634
6. Malau-Aduli AEO, Aziz MA, Kojina T, Niibayashi T, Oshima K et al. Fixing collinearity instability using principal component and ridge regression analyses in the relationship between body measurements and body weight in Japanese black cattle. Journal of Animal and Veterinary Advances 2004; 3 (12): 856- 863.
7. Akkol S. The prediction of live weight of hair goats through penalized regression methods: LASSO and adaptive LASSO. Archives of Animal Breeding 2018; 61 (4): 451-458. doi: 10.5194/aab-61-451-2018
8. Iqbal F, Ali M, Huma ZE, Raziq A. Predicting live body weight of Harnai sheep through penalized regression models. Journalof Animal and Plant Sciences 2019; 29 (6): 1541-1548.
9. Wamatu J, Alkhtib A, Rischkowsky B. Simple and robust model to estimate liveweight of Ethiopian Menz sheep. Animal Production Science 2019; 59 (12): 2265-2272. doi: 10.1071/ AN18006
10. Ali M, Eyduran E, Tariq MM, Tirink C, Abbas F et al. 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. Pakistan Journal of Zoology 2015; 47 (6): 1579-1585.
11. Celik S, Eyduran E, Karadas K, Tariq MM. Comparison of predictive performance of data mining algorithms in predicting body weight in Mengali rams of Pakistan. Revista Brasileira de Zootecnia 2017; 46 (11): 863-872. doi: 10.1590/ s1806-9290201700110000512
12. Eyduran E, Zaborski D, Waheed A, Celik S, Karadas K et al. 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. Pakistan Journal of Zoology 2017; 49 (1): 257-265. doi: 10.17582/journal.pjz/2017.49.1.257.265
13. Ghotbaldini H, Mohammadabadi M, Nezamabadi-pour H, Babenko OI, Bushtruk MV et al. Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed. Acta Scientiarum, Animal Sciences 2019; 41: e45282. doi: 10.4025/actascianimsci.v41i1.45282
14. Khorshidi-Jalali M, Mohammadabadi MR, Esmailizadeh A, Barazandeh A, Babenko OI. Comparison of artificial neural network and regression models for prediction of body weight in Raini Cashmere goat. Iranian Journal of Applied Animal Science 2019; 9 (3): 453-461.
15. Cortes C, Vapnik V. Support-vector networks. Machine Learning 1995; 20 (3): 273-297. doi: 10.1007/BF00994018
16. Suykens JAK, Vandewalle J. Least squares support vector machine classifiers. Neural Processing Letters 1999; 9 (3): 293- 300. doi: 10.1023/A:1018628609742
17. Zhang Y, Yang Y. Cross-validation for selecting a model selection procedure. Journal of Economics 2015;187 (1): 95- 112. doi: 10.1016/j.jeconom.2015.02.006
18. Liu X, Jia D, Li H. Research on kernel parameter optimization of support machine in speaker recognition. Science Technology and Engineering 2010; 10: 1669-1673.
19. Xavier-de-Souza S, Suykens JAK, Vandewalle J, Bolle D. Coupled simulated annealing. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics 2010; 40 (2): 320- 335. doi: 10.1109/TSMCB.2009.2020435
20. Nelder JA, Mead R. A simplex method for function minimization. The Computer Journal 1965;7 (4): 308-313. doi: 10.1093/comjnl/7.4.308
21. Das SK, Yadav BPS. Productive performance of Jamunapari goat under semi intensive system of management. Indian Journal of Animal Research 2015; 49 (2): 254-257.
22. Zou H, Hastie T. Regularization and variable selection via the elastic net. Journal of Royal Statistical Society Series B Statistical Methodology 2005; 67 (2): 301-320.
23. McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics 1943; 5 (4): 115-133. doi: 10.1007/BF02478259
24. Tsegaye D, Belay B, Haile A. Linear body measurements as predictor of body weight in Hararghe Highland goats under farmers environment Ethiopia. Global Veterinaria 2013; 11 (5): 649-656. doi: 10.5829/idosi.gv.2013.11.5.76135
25. Sam I, Ekpo J, Ukpanah U, Eyoh G, Warrie M. Relationship between linear body measurement and live body weight in West African Dwarf Goats in Obio Akpa. Journal of Biology, Agriculture and Healthcare 2016; 6 (16): 118-124.