Body Weight Prediction of Thalli Sheep Reared in Southern Punjab Using Different Data Mining Algorithms

Abstract

This study is conducted to predict the body weight (BW) for Thalli sheep of southern Punjab from different body measurements. In the BW prediction, several body measurements viz., withers height, body length, head length, head width, ear length, ear width, neck length, neck width, heart girth, rump length, rump width, tail length, barrel depth and sacral pelvic width are used as predictors. The data mining algorithms such as Chi-square Automatic Interaction Detector (CHAID), Exhaustive CHAID, Classification and Regression Tree (CART) and Artificial Neural Network (ANN) are used to predict the BW for a total of 85 female Thalli sheep. The data set is partitioned into training (80 %) and test (20 %) sets before the algorithms are used. The minimum number of parent (4) and child nodes (2) are set in order to ensure their predictive ability. The R2 % and RMSE values for CHAID, Exhaustive CHAID, ANN and CART algorithms are 67.38(1.003), 64.37(1.049), 61.45(1.093) and 59.02(1.125), respectively. The mostsignificant predictor is BL in the BW prediction of Thalli sheep. The heaviest BW average of 9.596 kg is obtained from the subgroup of those having BL > 25.000 inches. On behalf of the several goodness of fit criteria, we conclude that the CHAID algorithm performance is better in order to predict the BW of Thalli sheep and more suitable decision tree diagram visually. Also, the obtained CHAID results may help to determine body measurements positively associated with BW for developing better selection strategies with the scope of indirect selection criteria.

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

“…Body measurements vary depending on significant traits such as breed, age, sex, and type of yield during growth and development periods (Pesmen and Yardimci, 2008). There have been many studies of literature in which the relationships between body weight and body measurements are defined and the body weight estimation is made with some data mining algorithms by using body measurements (Yakubu, 2012;Ali et al, 2015;Eyduran et al, 2017;Aytekin et al, 2018;Çelik and Yılmaz, 2018;Huma ve Iqbal, 2019;Abbas et al, 2021;Louis-Tyasi et al, 2021;Mathapo and Tyasi, 2021;Altay, 2022;Coşkun et al, 2022;Mathapo et al, 2022). However, the fact that there is no study that predicts final live weight (FLW) by using both Anatolian Merino breed and initial fattening body characteristics distinguishes this study from others.…”

“…stated that the highest coefficient of determination observed for Bayesian Regularization (BR), Levenberg Marquardt (LM) and Scaled Conjugate Gradient (SCG) respective algorithms were 82.67, 74.22 and 76.69 % respectively, in the comparative study of artificial neural network algorithms performance for prediction of first lactation 305-day milk yield in crossbred cattle. In a study made ofAbbas et al (2021), R 2 values of ANN algorithms were found to be 61.45 % to predict body weight from body measurements by using four algorithms in 152 head Thalli sheep. Although the researchers stated that all algorithms could be used in prediction, they stated that CHAID was the best prediction algorithm.…”