R kullanarak Mars Veri Madencili?i Algoritmas? ile Yumurta A??rl??? Tahmini

Internal and external quality characters of poultry eggs are quitely important to determine egg weight. Also, the is for both hatching production. The purpose this study was modelling weight with MARS (Multivariate Adaptive Regression Splines) method using inner outsider in Lohmann LSL Classic white hybrit flock. For purpose, hybrid flock (n=60) were used. Weekly yields evaluated from 22nd week 62nd week. In research, prediction dependent continuous variable weight; shape index (SI), shell breaking resistance (SBS), (SW), thickness (ST), yolk diameter (YD), width (YW), height (YH), color (YC ), albumen length (AW), (AL) (AH) order obtain perfect goodness fit, “earth” package R program, definitions penalty -1, degree = 2, nprune 10 nk 60. mars model determined such as EW 63.1-0.906 * max (0,75-SI)-0.32 (0, SI-75) -62.4 (0,0.57-ST) -354 ST-0.57) + 1.13 Groupa2 75-SI) 1.49 (0.0.57-ST) YD 8.2*max(0, ST 0.57) YD-0.02*(0 YD-38.5)max* YC-0.0366*YH max(0,13-YC). As a result, some variables found be determining Variables group a2, SI, YC, ST, YD, YH estimate Other not included equation. poultry, may better alternative classical nonlinear models predicting since that it easier has higher accuracy.