一种基于改进的XGBoosting算法对婴幼儿奶粉中的脂肪含量的预测模型  

An Improved XGBoosting Algorithm Based on Fat Content in Infant Milk Powder Prediction Model

作　　者：张文婧 薛河儒[1,2] 姜新华 刘江平[1,2] 黄清 ZHANG Wen-jing;XUE He-ru;JIANG Xin-hua;LIU Jiang-ping;HUANG Qing(College of Computer and Information Engineering,Inner Mongolia Agricultural University,Huhhot 010018,China;Inner Mongolia Key Laboratory of Big Date Research and Application in Agriculture and Animal Husbandry Agricultural University,Huhhot 010018,China)

机构地区：[1]内蒙古农业大学计算机与信息工程学院,内蒙古呼和浩特010018 [2]内蒙古农牧业大数据研究与应用重点实验室,内蒙古呼和浩特010018

出　　处：《光谱学与光谱分析》2024年第5期1464-1471,共8页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(61461041,31960494);内蒙古自治区研究生科研创新项目(B20210191Z)资助。

摘　　要：婴儿奶粉成分配比中,脂肪有着重要地位。脂肪不仅是婴儿生长发育中的重要成分,同时也为婴儿的生长提供必需的能量,对于婴儿脑发育及神经髓鞘的形成具有重要意义。化学的婴儿奶粉脂肪含量检测如乙醚提取法,方法检测灵敏,但存在破坏样本和检测周期较长的缺点,因此寻求一种为婴儿奶粉成分的无损检测方法,高光谱成像技术提供了一种可能的途径。以内蒙古地区不同阶段的婴儿奶粉为研究对象,采用多元散射校正(MSC)、标准正态变换(SNV)、平滑滤波算法(Savitzky-Golay)、鲁斯特算法(Roust)等对高光谱数据进行预处理,再利用竞争性自适应重加权算法(CARS)算法从125个特征波长中筛除光谱数据中冗余的波长保留有效波长66个。对极值梯度提升算法(XGBoosting)算法进行了贝叶斯优化(BO),最终构建了基于BO-XGBoosting对婴儿奶粉脂肪含量的预测模型。结果显示,该模型预测效果优于传统的偏最小二乘回归(PLSR)和支持向量回归(SVR)模型,且优于集成算法中Bagging、GrdientBoosting算法。贝叶斯优化极值梯度提升算法BO-XGBoosting模型在测试集实验,得到的决定系数(R^(2))和均方根误差(RMSEP)分别为0.9537和0.5773,比XGBoosting算法的R^(2)和RMSEP分别提高2.91%和降低19.2%。该研究为奶粉中脂肪含量的预测提供了基于BO-XGboosting集成算法的快速无损检测的算法支持和理论依据。Fat plays an essential role in the composition of infant formula.Not only is fat a vital component of a baby's growth and development,but it also provides essential energy for growth.It is crucial for the development of the infant brain and the formation of nerve myelin.Chemical methods for determining the fat content of infant milk powder,such as ether extraction,are sensitive but have the disadvantage of destroying samples and having a long detection period.In this paper,the hyperspectral data undergoes preprocessing processes with standard normal transform(SNV),multiple scattering corrections(MSC),Savitzky-Golay smoothing,and Roust method using different stages of infant milk powder in Inner Mongolia,China.A competitive adaptive re-weighting algorithm,CARS,was used to sift out redundant wavelengths from the spectroscopic data at 125 feature wavelengths,leaving 66 valid wavelengths.The Bayesian optimization algorithm optimizes the XGBoosting prediction model,leading to a BO-XGBoosting model that predicts the fat content of infant formula better than the original model.The experimental results show that the model predicts better than the traditional partial least squares regression(PLSR)and support vector machine(SVR)regression model,outperforming the Bagging and GrdientBoosting algorithms in the integrated algorithm.In the BO-XGBoosting model in the test set experiments,the decision coefficient R^(2)and root mean square error of prediction(RMSEP)obtained are 0.9537 and 0.5773,which are 2.91%higher and 19.2%lower than the determination coefficient R^(2)and root mean squared error of prediction(RMSEP)of the XGBoosting model's R^(2)and RMSEP,respectively.This study provides algorithmic support and a theoretical foundation for BO-XGBooting based rapid,non-destructive detection of infant formula fat content.

关 键 词：高光谱 贝叶斯优化 XGBoosting模型 脂肪含量 无损检测 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]