Prediction of internal egg quality characteristics and variable selection using regularization methods: ridge, LASSO and elastic net

Abstract

This study was conducted to determine the inner quality characteristics of eggs using external egg quality characteristics. The variables were selected in order to obtain the simplest model using ridge, LASSO and elastic net regularization methods. For this purpose, measurements of the internal and external characteristics of 117 Japanese quail eggs were made. Internal quality characteristics were egg yolk weight and albumen weight; external quality characteristics were egg width, egg length, egg weight, shape index and shell weight. An ordinary least square method was applied to the data. Ridge, LASSO and elastic net regularization methods were performed to remove the multicollinearity of the data. The regression estimating equations of the internal egg quality were significant for all methods (P < 0.01). The goodness of fit of the regression estimating equations for egg yolk weight was 58.34, 59.17 and 59.11 % for the ridge, LASSO and elastic net methods, respectively. For egg albumen weight the goodness of fit of the regression estimating equations was 75.60 %, 75.94 % and 75.81 % for the respective ridge, LASSO and elastic net methods. It was revealed that LASSO, including two predictors for both egg yolk weight and egg albumen weight, was the best model with regard to high predictive accuracy.

Collagen signature as a novel biomarker to predict axillary lymph node metastasis in breast cancer using multiphoton microscopy

“…TACS score was the frequency of TACS1‐8 appearing in the effective region. Ridge regression, a regularization method, was used in this study [31]. All the regressor variables stay in the model because of regression coefficients do not become exactly zero [32].…”

The Classification Capability of Urine Biomarkers in the Diagnosis of Pancreatic Cancer with Logistic Regression Based on Regularized Approaches: A Methodological Research

“…Parameter is the ridge regularization function. 21 Lasso is one of the regularization approaches used in the multicollinearity problem, which performs variable selection and parameter estimation together. 22 The objective function of the method is based on minimizing the sum of the squares of residuals under the L1 norm.…”

Analysis of quality and prediction of external and internal egg traits in Mexican native turkey hens

“…Finally, a regression model was developed to predict YW from EW and SI, which explained 74% of the observed variation. In laying hens, the weight of the egg can be adequately predicted using the values of the albumen weight, yolk and shell with an R 2 = 93.4%, the weight of albumen from the weight of the egg and shell (R 2 = 77%) and the weight of the yolk using the weight of the egg (R2 = 60%) in a unique way (Orhan et al, 2016;Çiftsüren et al, 2018). On the other hand, in Guinea fowl the egg weight can be accurately predicted from the length (R 2 = 21%) and the width of the egg (R 2 = 16%), the weight of the shell using length as predictors, the width and weight (R 2 = 8.8%) and the weight of the yolk based on the weight of the egg (R 2 = 60%) (Fajemilehin, 2008).…”

“…Various authors suggest evaluating the relationships between some external and internal traits for a better understanding of the egg quality parameters (Khurshid et al, 2003;Abanikannda and Leigh, 2007;Alkan et al, 2015;Baykalir and Aslan, 2020). For example, the traits of weight, length and width of the egg, shape index and shell weight are highly correlated, and in turn, can be used as predictors of internal egg traits such as the weight of yolk and albumen, to facilitate their evaluation without the need to break the egg (Fajemilehin, 2008;Çiftsüren and Akkol, 2018).…”