A Data Mining Application in Animal Breeding: Determination of Some Factors in Japanese Quail Eggs Affecting Fertility

Abstract

The purpose of this study, classification with data mining methods according to the factors of season, selection, and frequency of settlement which have an effect on fertility in Japanese quail eggs, and is to determine the effect of these factors. In this study, 180 female quails in three different seasons (summer, winter and autumn) which were obtained from a selection line and a control line were used. 1141 hatching eggs collected from quails which were hosted on two different types of cages (160-240 cm(2)/quail) during a week at 12 weeks of age have formed the material of study. Classification algorithms used in the study are YSA, RBF Network, Naive Bayes, KStar, and Ridor algorythms, respectively. In the comparison of the models formed according to these algorithms, Kappa statistic, Mean Absolute Deviation (MAD), Mean Square Root Error (MSE), Relative Absolute Error (RAE), Relative Square Root Error (RSE) performance criteria were used. As a result of analysis, it has been seen in the comparison made that the model formed according to Ridor algorithm that has MAD: 0.002, MSE: 0.05, RAE: 1.07%, RSE: 14.50% and Kappa: 0.98 performance criteria values, respectively, has made the classification with minimum error. With this study conducted, it was determined that 85% of the quail eggs fertile and 15% of them has low reproduction capacity with the accurate classification success of 99.73%.