牛奶蛋白质含量的SSA-SVM高光谱预测模型  

Hyperspectral Analysis of Milk Protein Content Using SVM Optimized by Sparrow Search Algorithm

作　　者：刘美辰 薛河儒[1] 刘江平[1] 代荣荣 胡鹏伟 黄清 姜新华[1] LIU Mei-chen;XUE He-ru;LIU Jiang-ping;DAI Rong-rong;HU Peng-wei;HUANG Qing;JIANG Xin-hua(College of Computer and Information Engineering,Inner Mongolia Agricultural Un iversity,Huhhot 010000,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010000

出　　处：《光谱学与光谱分析》2022年第5期1601-1606,共6页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(61461041,31960494);内蒙古科技厅关键技术攻关项目(2020GG0169)资助。

摘　　要：牛奶中包含着很多人体需要的营养元素,如脂肪、蛋白质、钙等;对牛奶营养元素进行分析是牛奶安全检测关键的一部分。高光谱技术可以有效地结合图像和光谱数据识别牛奶种营养元素。为了实现对牛奶中蛋白质含量快速、精确的预测,采用竞争性自适应重加权(CARS)算法选取特征波长,并提出一种基于麻雀搜索算法(SSA)优化支持向量机(SVM)实现对牛奶蛋白质含量预测。利用高光谱仪获取牛奶反射光谱(400~1000nm)。通过选取归一化(N)、标准化(Standardization)和多元散射校正(MSC)对原始的牛奶数据进行光谱降噪处理提高光谱利用率;利用竞争性自适应重加权算法和连续投影算法(SPA)对经过处理的牛奶光谱数据提取特征波长,求取蛋白质和光谱间的相关系数并进行重要性排序,获取重要的特征波段;最后,通过遗传算法(GA)优化SVM,粒子群算法(PSO)优化SVM和偏最小二乘法(PLS)算法对牛奶蛋白质进行预测并比较预测结果,为了提高蛋白质预测的精度和模型稳定性,提出利用SSA对SVM的核函数g和惩罚参数c进行优化,以均方根误差(RMSE)作为适应度函数,通过迭代选择最优的回归参数训练模型。牛奶数据预测结果表明最优组合模型为:MSC-CARS-SSA-SVM。模型测试集的决定系数R^(2)为0.9996,均方根误差RMSE为0.0011,耗时4.1121s。结果表明:使用CARS算法能实现特征波段的提取和冗余信息的剔除,从而提高模型效率,简化了算法的复杂度;SSA算法优化SVM的参数,通过迭代更新麻雀最优位置,可以快速得到全局最优解,与SVM,GA-SVM,PSO-SVM和PLS相比,牛奶蛋白质的预测准确度和模型稳定性都得到了明显提高,满足了对乳品检测的精确度要求,是快速检测牛奶蛋白质的一个可行新方法。为光谱模型的优化及预测模型精度的提高提供参考。Milk contains many nutritional elements needed by the human body,such as fat,protein,calcium,etc.Therefore,analysing nutritional elements in milk is a key part of milk safety detection.Hyperspectral technology can effectively identify nutritional elements in milk by combining image and spectral data.In order to quickly and accurately predict protein content in milk,the Competitive Adaptive Reweighted Sampling(CARS)algorithm was used to select characteristic wavelengths.A method based on Sparrow Search Algorithm(SSA)to optimize Support Vector Machine(SVM)was proposed to predict milk protein content.The reflectance spectra of milk(400~1000 nm)extracted by the hyperspectral spectrometer were used for the experiment.During Normalization(N),Standardization and Multiplicative Scatter Correction(MSC),the original milk data are used for spectral noise reduction to improve spectral utilization.The successive projections algorithm(SPA)and the competitive adaptive re-weighting algorithm were used to extract the feature wavelengths from the processed milk spectral data.The correlation coefficients between proteins and the spectrum were calculated and ranked by importance to obtain the important feature wavelengths.In the end,through SVM,the Genetic Algorithm(GA)-SVM,Particle Swarm Optimization(PSO)-SVM and Partial Least-Regression(PLS)algorithm was used to predict milk proteins and compare the prediction results.In order to improve the accuracy of protein prediction and model stability,SSA was proposed to optimize the kernel function G and penalty parameter C of SVM.Root Mean Squared Error(RMSE)was used as the fitness function,and the optimal regression parameters were selected through iteration to train the model.The results of milk data prediction showed that the optimal combination model was MSC-CARS-SSA-SVM.The determination coefficient R^(2)of the model test set was 0.9996,the root means square error RMSE was 0.0011,and the time was 4.1121 seconds.The results show that the CARS algorithm can extract the characteristic b

关 键 词：高光谱 牛奶蛋白质 竞争性自适应重加权算法 支持向量机 麻雀算法 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]