中国农业科学院农业信息研究所 中国农学会
Agricultural Information Institute of CAAS China Association of Agricultural Science Societies
En
Ch
中国农业科学院农业信息研究所 中国农学会 主办

AI检索

订阅

返回顶部
当前位置: 首页 > 文章 > 中红外光谱预测牛奶及奶产品成分含量的回归模型及其特点 中国奶牛 2019 (5)
Position: Home > Articles > 中红外光谱预测牛奶及奶产品成分含量的回归模型及其特点 China Dairy Cattle 2019 (5)

中红外光谱预测牛奶及奶产品成分含量的回归模型及其特点

作  者：
阮健;陈焱森;万平民;潘中保;张震;闫磊;任小丽;张淑君
单  位：
河南省奶牛生产性能测定中心;华中农业大学动物遗传育种与繁殖教育部实验室;武汉金旭畜牧科技发展有限公司;华中农业大学
关键词：
牛奶;奶产品;MIR;回归模型;建模方法
摘  要：
牛奶中各种成分含量是影响牛奶品质的重要因素,也是决定其价格的重要因素之一,高品质的牛奶和奶产品往往对人们的健康具有重要的意义.而具有高效低成本的中红外光谱(MIR)已逐渐成为奶产品品质检测的有效新方法.十多年来,欧美发达国家已利用MIR建立了牛奶和奶产品中脂肪酸、蛋白质、矿物质等成分含量预测模型,并投入生产使用.然而,我国在利用MIR预测牛奶中成分的研究较晚、没有得到有效应用.在建立模型的过程中,可选择较多的建模方法,其中回归建模方法的正确选用是决定模型预测能力的关键所在,而正确的预测方法往往意味着更高的预测精度和更强的泛化能力.偏最小二乘法(PLS)、最小二乘支持向量机(LS-SVM)、人工神经网络(ANN)以及贝叶斯回归(Bayes-R)因为其各自不同的优点已成为目前使用较多的几种预测方法.本文对这些方法及其特征进行介绍和总结.
作  者：
RUAN Jian;CHEN Yan-sen;WAN Ping-min;PAN Zhong-bao;ZHANG Zhen;YAN Lei;REN Xiao-li;ZHANG Shu-jun;Key Laboratory of Animal Breeding and Reproduction of Ministry of Education, Huazhong Agricultural University;Wuhan Jinxu Animal Husbandry Technology Development Co., Ltd.;Dairy Herd Improvement Center of Henan Province;
单  位：
RUAN Jian%CHEN Yan-sen%WAN Ping-min%PAN Zhong-bao%ZHANG Zhen%YAN Lei%REN Xiao-li%ZHANG Shu-jun%Key Laboratory of Animal Breeding and Reproduction of Ministry of Education, Huazhong Agricultural University%Wuhan Jinxu Animal Husbandry Technology Development Co., Ltd.%Dairy Herd Improvement Center of Henan Province
关键词：
Milk;;Milk products;;MIR;;Regression model;;Modeling methods
摘  要：
The content of various ingredients in milk is an important factor affecting the quality of milk, and is also an important factor in determining its price. High-quality milk and milk products are often of great significance to people's health. The high-efficiency and low-cost mid-infrared spectroscopy(MIR) has gradually become an effective new method for quality testing of dairy products. For more than a decade, developed countries in Europe and the United States have used MIR to establish prediction models for the content of fatty acids, proteins, minerals and other components in milk and milk products, and put them into production. However, China's research on using MIR to predict the composition of milk is relatively late and has not been effectively applied. In the process of building a model, more modeling methods can be selected. The correct choice of regression modeling method is the key to determine the predictive ability of the model, and the correct prediction method often means higher prediction accuracy and stronger generalization ability. Partial least squares(PLS), least squares support vector machine(LSSVM), artificial neural network(ANN), and Bayesian regression(Bayes-R) have become more widely used forecast methods because of their different advantages. This paper introduces and summarizes these methods and their characteristics.

相似文章

导出引用
计量
文章访问数: 12
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊

友情链接Friendly link
农业信息研究所Agricultural information institute 农业智能知识服务平台Agricultural intelligent knowledge service platform 农业学术服务平台Agricultural Knowledge Service System 中国知网CNKI 维普网VIP 万方WANFANG DATA
联系我们Contact us

电话Tell：010-82109652-808

邮箱E-mail：agrijournal@caas.cn

服务Service
关于我们About us 意见建议Opinions and suggest
版权说明Copyright
单位：中国农业科学院农业信息研究所 中国农学会 © 2017中国农业科学院农业信息研究所 ICP备案号：京ICP备09089781号-46