ESTIMATION OF 305-DAYS MILK YIELD USING FUZZY LINEAR REGRESSION IN JERSEY DAIRY CATTLE
O. Gorgulu, A. Akilli
O. Gorgulu, A. Akilli
1 Department of Biostatistics and Medical Informatics, Faculty of Medicine, Ahi Evran University, K1r_ehir, Turkey
2 Department of Biometry and Genetic, Faculty of Agriculture, Ahi Evran University, Kirsehir, Turkey
Page Number(s):
1174-1181
Published Online First:
August 01, 2018
Publication Date:
August 01, 2018
ABSTRACT
Fuzzy linear regression analysis helps to produce successful assumptions in situations with uncertainty between variables and provides researchers with a flexible perspective. In this study, 305 days milk yield estimation studies were carried out using partial lactation records of Jersey cattle with the fuzzy linear regression method. Calving age, number of lactation, days of milk, calving season, and the first four milk test days records were used as the independent variables in the study. Also,305 days milk yield was used as the dependent variable. Reliability of the obtained estimates was discussed using graphical representations of h values and three different statistical error criteria ( RMSE, MAPE and R) . In addition, the estimated values obtained were compared with the observed values. The fuzzy linear regression equations developed for 10 different h values shows that the equations obtained for the h = 0.4 and h = 0.5 values are the closest observed values to305 days milk yield. The difference between the predicted values and the observed values was statistically insignificant (p>0.05). These results show that the fuzzy linear regression method can be successfully used to predict 305 days milk yield at the beginning of the lactation. Keyword: Fuzzy regression, Fuzzy linear programming, Dairy cattle, Milk yield. CHAID, and Exhaustive CHAID data mining algorithms
Keywords:
NA