数据挖掘算法在根据波切夫斯特鲁姆科科克蛋鸡的蛋品质性状预测蛋壳厚度中的应用。

Use of data mining algorithms in prediction of eggshell thickness from egg quality traits of Potchefstroom Koekoek layers.

作者信息

Molabe Kagisho Madikadike, Tyasi Thobela Louis, Mbazima Vusi Gordon

机构信息

Department of Agricultural Economics and Animal Production, University of Limpopo, Private Bag X1106, Sovenga, 0727, South Africa.

Department of Biochemistry, Microbiology &Biotechnology, University of Limpopo, Private BagX1106, Sovenga, Limpopo, 0727, South Africa.

出版信息

Sci Rep. 2025 Jan 11;15(1):1717. doi: 10.1038/s41598-025-86356-6.

DOI:10.1038/s41598-025-86356-6

PMID:39814941

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11735974/

Abstract

Egg quality is affected by lot of factors. Study was conducted to compare performance of data mining algorithms; Classification and regression tree (CART), Chi-square automatic interaction detection (CHAID), Exhaustive chi-square automatic interaction detection (Ex-CHAID) and Multivariate adaptive regression spline (MARS) in prediction of Potchefstroom Koekoek's eggshell thickness from egg quality traits. 350 eggs were collected at 31st to 39th week to examine the egg quality traits. MARS with R(0.86) revealed yolk ratio, shell weight, egg shape index, yolk ratio, shell ratio, albumen weight and albumen ratio as explanatory variables predicting eggshell thickness. CART with R (0.37), yolk/albumen ratio was noted to be influential predictor of eggshell thickness. CHAID and Ex-CHAID (R= 0.35) discovered egg weight as the best predictor of eggshell thickness. MARS with R(0.86) revealed yolk ratio, shell weight, egg shape index, yolk ratio, shell ratio, albumen weight and albumen ratio as explanatory variables predicting eggshell thickness. MARS had high r (0.925), R (0.856) and lower RMSE (0.129) and AIC (-975.331) compared to CHAID, Ex-CHAID and CART leading MARS to be the best data mining algorithm when predicting the eggshell thickness using egg quality traits.

摘要

鸡蛋品质受多种因素影响。本研究旨在比较数据挖掘算法（分类与回归树（CART）、卡方自动交互检测（CHAID）、穷举卡方自动交互检测（Ex-CHAID）和多元自适应回归样条（MARS））在根据鸡蛋品质性状预测波切夫斯特鲁姆科科克鸡蛋蛋壳厚度方面的性能。在第31至39周收集了350枚鸡蛋以检测鸡蛋品质性状。相关系数R为0.86的MARS模型显示，蛋黄比例、蛋壳重量、蛋形指数、蛋黄比例、蛋壳比例、蛋白重量和蛋白比例是预测蛋壳厚度的解释变量。相关系数R为0.37的CART模型指出，蛋黄/蛋白比例是蛋壳厚度的有影响的预测因子。CHAID和Ex-CHAID（相关系数R = 0.35）发现蛋重是蛋壳厚度的最佳预测因子。相关系数R为0.86的MARS模型显示，蛋黄比例、蛋壳重量、蛋形指数、蛋黄比例、蛋壳比例、蛋白重量和蛋白比例是预测蛋壳厚度的解释变量。与CHAID、Ex-CHAID和CART相比，MARS的相关系数r为0.925、相关系数R为0.856，且均方根误差（RMSE）较低（0.129），赤池信息准则（AIC）为-975.331，这使得MARS成为利用鸡蛋品质性状预测蛋壳厚度时最佳的数据挖掘算法。