Egg freshness during storage: the effect of laying hen age and shelf life prediction using a novel hybrid modeling method

IF 5.2 Q1 FOOD SCIENCE & TECHNOLOGY
Yifeng Lu , Jing Li , Zihao He , Linyun Chen , Huixin Tian , Chen Xu , Xinglian Xu , Minyi Han
{"title":"Egg freshness during storage: the effect of laying hen age and shelf life prediction using a novel hybrid modeling method","authors":"Yifeng Lu ,&nbsp;Jing Li ,&nbsp;Zihao He ,&nbsp;Linyun Chen ,&nbsp;Huixin Tian ,&nbsp;Chen Xu ,&nbsp;Xinglian Xu ,&nbsp;Minyi Han","doi":"10.1016/j.jfutfo.2024.11.009","DOIUrl":null,"url":null,"abstract":"<div><div>Changes in the quality of eggs during storage relate to their shelf life and economic value. Factors such as temperature, relative humidity, the operation of cleaning, and microorganisms have been shown to play a role in the storage quality of eggs. This study thus aimed at investigating the effect of hen age on the storage quality of egg, and predicting egg shelf life using back propagation artificial neural network (BP-ANN) based models. Eggs laid by Jingfen No.1 (27 and 58 weeks of age) and Jingfen No.6 (26 and 57 weeks of age) hens were stored under ambient conditions and evaluated by physicochemical properties. It was found that the shelf life of the lower age group was significantly longer than that of the higher age group. A novel hybrid model combining BP-ANN, cuckoo search and adaptive boosting (CS-BP-AdaBoost) was proposed for predicting the remaining egg shelf life, with the input being Haugh unit, yolk index, air cell depth, albumen pH, hen age, and breed. The tuning process of hyperparameters such as learning rate, training function, and transfer function was presented in detail. Results show that CS-BP-AdaBoost had satisfactory performance on the test set with root mean square error (RMSE) and coefficient of determination (<em>R</em><sup>2</sup>) of 0.68 and 0.97, respectively. And it outperformed BP-ANN by reducing RMSE by 0.39 and improving <em>R</em><sup>2</sup> by 0.05. The model used solved the problem that the traditional BP-ANN tends to fall into local minima. The removal of hen age from the input parameters caused a decrease in prediction accuracy (<em>R</em><sup>2</sup> = 0.95, RMSE = 1.00), suggesting an important role of hen age in shelf life prediction. This study demonstrates the great potential of applying combinatorial modeling approaches to predict egg shelf life and the crucial impact of hen age on egg shelf life prediction.</div></div>","PeriodicalId":100784,"journal":{"name":"Journal of Future Foods","volume":"5 6","pages":"Pages 614-627"},"PeriodicalIF":5.2000,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Future Foods","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S277256692400096X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Changes in the quality of eggs during storage relate to their shelf life and economic value. Factors such as temperature, relative humidity, the operation of cleaning, and microorganisms have been shown to play a role in the storage quality of eggs. This study thus aimed at investigating the effect of hen age on the storage quality of egg, and predicting egg shelf life using back propagation artificial neural network (BP-ANN) based models. Eggs laid by Jingfen No.1 (27 and 58 weeks of age) and Jingfen No.6 (26 and 57 weeks of age) hens were stored under ambient conditions and evaluated by physicochemical properties. It was found that the shelf life of the lower age group was significantly longer than that of the higher age group. A novel hybrid model combining BP-ANN, cuckoo search and adaptive boosting (CS-BP-AdaBoost) was proposed for predicting the remaining egg shelf life, with the input being Haugh unit, yolk index, air cell depth, albumen pH, hen age, and breed. The tuning process of hyperparameters such as learning rate, training function, and transfer function was presented in detail. Results show that CS-BP-AdaBoost had satisfactory performance on the test set with root mean square error (RMSE) and coefficient of determination (R2) of 0.68 and 0.97, respectively. And it outperformed BP-ANN by reducing RMSE by 0.39 and improving R2 by 0.05. The model used solved the problem that the traditional BP-ANN tends to fall into local minima. The removal of hen age from the input parameters caused a decrease in prediction accuracy (R2 = 0.95, RMSE = 1.00), suggesting an important role of hen age in shelf life prediction. This study demonstrates the great potential of applying combinatorial modeling approaches to predict egg shelf life and the crucial impact of hen age on egg shelf life prediction.
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
5.80
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信