RT Journal
T1 EXPLORING DATA MINING ALGORITHMS FOR PREDICTING DUCK EGG WEIGHT BASED ON EGG QUALITY CHARACTERISTICS
A1 Lahouari DAHLOUM
A1 Qada BENAMEUR
A1 Abdulmojeed YAKUBU
JF Journal of Animal and Plant Sciences
JO JAPS
SN 1018-7081
VO 34
IS 2
SP 336
OP 350
YR 2024
FD 2024/03/31
DO DOI https://doi.org/10.36899/JAPS.2024.2.0721
AB <p>The present investigation aimed to compare the performance of two data mining algorithms, Automatic Linear Modeling (ALM) and Artificial Neural Network (ANN), and the traditional Multivariate Linear Regression model (MLR) to predict the egg weight (EWT) of Mallard duck from some egg traits including egg length (EL), egg width (EWd), egg shape index (ESI), eggshell weight (ESW), albumen weight (AW), albumen height (AH), yolk weight (YW), yolk height (YH), yolk diameter (YD), and Haugh unit (HU). The Pearson correlation between observed and predicted values (r), coefficient of determination (R<sup>2</sup>), adjusted coefficient of determination (R<sup>2</sup><sub>adj</sub>), Root Mean Squared Error (RMSE), and Relative Approximation Error (RAE) were used to estimate model performance. EWT had a strong correlation with egg dimensions (EL and EWd, r= 0,752 and 0,790, respectively), AW (r= 0,815), and YW (r= 0,784). The R<sup>2</sup><sub>adj</sub> values were 0.972, 0.963, and 0.960 for ALR, ANN, and MLR models, respectively. RMSE values were 0,924, 1.067, and 1.090 for ALR, ANN, and MLR models, respectively. Overall, all three models provided nearly similar results. However, the ALM algorithm showed better predictive performance in comparison to MLR and ANN models and could be considered the most appropriate for the prediction of egg weight in Mallard duck.</p>
K1 egg weight, Mallard duck, artificial neural network, automatic linear modeling, multivariate linear
PB Pakistan Agricultural Scientists Forum
LK https://thejaps.org.pk/AbstractView.aspx?mid=2022-JAPS-574