近红外光谱结合化学计量学方法快速检测蓝莓可溶性固形物和维生素C含量  

Rapid Determination of Soluble Solids and Vitamin C in Blueberry by Near Infrared Spectroscopy Combined with Chemometrics

作　　者：王甜甜 冯国红[1] 朱玉杰[1] WANG Tiantian;FENG Guohong;ZHU Yujie(College of Engineering and Technology,Northeast Forestry University,Harbin 150040,China)

机构地区：[1]东北林业大学工程技术学院,黑龙江哈尔滨150040

出　　处：《食品工业科技》2023年第16期297-305,共9页Science and Technology of Food Industry

基　　金：中央高校基本科研业务费专项资金项目(2572020BL01);黑龙江省自然科学基金项目(LH2020C050)。

摘　　要：采用近红外光谱技术,对不同贮藏时间的蓝莓营养成分进行定量分析,以寻求其化学成分与近红外光谱数据的相关性,实现利用光谱技术对蓝莓营养成分的无损检测。对获取的近红外光谱数据,运用偏最小二乘回归(Partial Least Square Regression,PLSR)和支持向量回归(Support Vector Regression,SVR)两种机器学习算法预测蓝莓可溶性固形物(Soluble Solids Content,SSC)和维生素C(Vitamin C,V_(C))含量。为增加预测精度,采用一阶导数(First Derivative,1-DER)、二阶导数(Second Derivative,2-DER)、标准正态变换(Standard Normal Variate Transform,SNV)、多元散射校正(Multiplicative Scatter Correction,MSC)、Savitzky-Golay平滑(S-G)等一种或几种方法组合对光谱数据进行预处理,比较分析最佳的预处理方式;采用竞争适应性重加权采样法(Competitive Adaptive Reweighted Sampling,CARS)和随机蛙跳算法(Random Frog,RF)及两种算法组合对光谱波长进行降维处理。结果表明,降维后的SSC波长变量分别降到了全光谱变量的1.7%、4.3%和5.6%,V_(C)波长变量分别降到了全光谱变量的2.5%、2.9%、4.8%。在筛选后的光谱波长变量的基础上,采用PLSR建立蓝莓近红外光谱与SSC和V_(C)含量的预测模型。对比发现CARS结合RF算法筛选出的波长变量预测效果更好,模型校正相关系数分别为0.9001、0.8707,校正均方根误差分别为0.8234、2.9429,预测相关系数分别为0.8424、0.8350,预测均方根误差分别为0.9613、2.9482。为排除模型性能对预测结果的影响,建立SVR模型将预测结果进行对比,同样发现CARS结合RF算法的预测效果更佳,模型校正相关系数分别为0.8702、0.8503,校正均方根误差分别为0.9549、3.2431,预测相关系数分别为0.8269、0.8183,预测均方根误差分别为0.8769、2.8818。本研究为蓝莓营养品质监测提供了模型基础,且选择特征波长的方法可以为更多果蔬营养物质预测模型提供参考。The near-infrared spectroscopy technology was adopted to quantitatively analyze the nutritional components of blueberries given different storage times,so as to determine the correlation between their chemical components and near-infrared spectroscopy data.Besides,spectroscopy technology was applied to perform the nondestructive detection of blueberry nutritional components.As for the obtained near-infrared spectral data,two machine learning algorithms,Partial Least Square Regression(PLSR)and Support Vector Regression(SVR),were used to predict the content of soluble solids(SSC)and vitamin C(V_(C))in blueberries.In order to improve the accuracy of prediction,one or more of the methods,such as First Derivative(1-DER),Second Derivative(2-DER),Standard Normal Variable Transform(SNV),Multivariate Scatter Correction(MSC),Savitzky Golay smoothing(S-G),were used to preprocess the spectral data,and the best-performing methods were comparatively analyzed.Competitive Adaptive Weighted Sampling(CARS)and Random Frog(RF)were adopted either separately or in combination to reduce the dimensions of spectral wavelengths.Results showed that,after dimension reduction,the SSC wavelength as a variable was reduced to 1.7%,4.3%and 5.6%of the full spectral variable,while the VC wavelength as a variable was reduced to 2.5%,2.9%and 4.8%of the full spectral variable,respectively.With the screened spectral wavelength as a variable,PLSR was used to construct a prediction model of near-infrared spectroscopy for SSC and V_(C) contents in blueberry.The comparison showed that the wavelength variables screened by CARS in combination with RF algorithm produced a better outcome of prediction.The model correction correlation coefficients were 0.9001 and 0.8707 respectively,the correction root mean square errors were 0.8234 and 2.9429 respectively,the prediction correlation coefficients were 0.8424 and 0.8350 respectively,and the prediction root mean square errors were 0.9613 and 2.9482 respectively.To eliminate the impact of model performance on the

关 键 词：近红外光谱 竞争适应性重加权采样法 随机蛙跳 偏最小二乘回归 支持向量回归 

分 类 号：TS255.1[轻工技术与工程—农产品加工及贮藏工程]