Final Fattening Live Weight Prediction in Anatolian Merinos Lambs from Some Body Characteristics at the Initial of Fattening by Using Some Data Mining Algorithms

Authors : Gizem COŞKUN, Özcan ŞAHİN, Yasin ALTAY, İbrahim AYTEKİN

Pages : 47-53

Doi:10.47115/bsagriculture.1181444

View : 16 | Download : 10

Publication Date : 2023-01-01

Article Type : Research Paper

Abstract :This study\`s objective was to compare the performances of Random Forest insert ignore into journalissuearticles values(RF);, eXtreme Gradient Boosting insert ignore into journalissuearticles values(XGBoost);, and Bayesian Regularization Neural Network insert ignore into journalissuearticles values(BRNN); algorithms, which are some data mining algorithms used in final fattening live weight prediction. As the independent variable in the design of the algorithms, some body characteristics taken before fattening of 54 heads of Anatolian Merino lambs, with single birth and male, were withers height insert ignore into journalissuearticles values(WH);, rump height insert ignore into journalissuearticles values(RH);, body length insert ignore into journalissuearticles values(BL);, chest girth insert ignore into journalissuearticles values(CG);, leg girth insert ignore into journalissuearticles values(LG);, and chest depth insert ignore into journalissuearticles values(CD); was used. The mean±standart errors for the body characteristics of Anatolian Merino lambs were determined to be 63.481±0.538, 63.315±0.501, 78.930±1.140, 60.037±0.549, 47.704±0.543, and 29.926±0.377, respectively. The mean initial live weight insert ignore into journalissuearticles values(ILW); and the mean final live weight insert ignore into journalissuearticles values(FLW); were found as 35.89±0.84 and 49.49±0.88 kg, respectively. There was difference of 13.60 kg between ILW and FLW means. The ILW and FLW were shown to positively correlate with body characteristics, and this correlation was statistically significant insert ignore into journalissuearticles values(P<0.01);. While the highest Pearson’s correlation insert ignore into journalissuearticles values(r=0.95); of FLW was between WH and RH, the lowest Pearson’s correlation insert ignore into journalissuearticles values(r=0.51); was found between LG and CD. While the largest share of body characteristics in the total variance in the FLW estimation was BL insert ignore into journalissuearticles values(42.969%); in the XGBoost algorithm, the lowest share was found to be CD insert ignore into journalissuearticles values(0.00); in the XGBoost algorithm and LG insert ignore into journalissuearticles values(0.00); in the BRNN algorithm. The model evaluation criterias which were Root mean square error insert ignore into journalissuearticles values(RMSE);, Standard deviation ratio insert ignore into journalissuearticles values(SDR);, Mean absolute percentage error insert ignore into journalissuearticles values(MAPE);, and Adjusted coefficient of determination insert ignore into journalissuearticles values(R2Adj); performed as 1.492, 0.233, 2.241 and 0.944, in the XGBoost algorithm, as 2.220, 0.347, 3.139 and 0.880 in the BRNN algorithm, as 2.859, 0.446, 4.340 and 0.792 in the RF model, respectively. As a result, it can be said that the data mining algorithms used in prediction FLW taking advantage of body measurements of Anatolian Merino lambs at the beginning of fattening will benefit from their use in fattening due to their high prediction performance.
Keywords : Anatolian Merino, Body characteristics, Data mining algorithms, Fattening, Prediction