紫外光谱结合支持向量回归用于苹果汁中多菌灵的检测  

Detection of Carbendazim in Apple Juice by Ultraviolet Spectrum Combined with Support Vector Regression

作　　者：孟德龙 顾慈勇 李琳[1] MENG De-long;GU Ci-yong;LI Lin(College of Science,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China)

机构地区：[1]南京航空航天大学物理学院,南京210016

出　　处：《电光系统》2023年第2期26-28,37,共4页Electronic and Electro-optical Systems

摘　　要：文章提出了一种基于紫外光谱和支持向量回归(Support Vector Regression,SVR)定量检测苹果汁中多菌灵的方法。首先,利用紫外-可见分光光度计采集苹果汁中不同浓度多菌灵样品的紫外光谱,并采用Savitzky-Golay(S-G)平滑方法对原始光谱进行预处理;然后,建立基于光谱变量的支持向量回归模型,实现苹果汁中多菌灵的定量检测;最后,为了进一步改善模型的预测性能,采用粒子群优化算法(Particle Swarm Optimization,PSO)对支持向量回归模型的参数进行优化。结果表明,PSO-SVR模型具有最佳的预测性能,其预测集均方根误差(Root Mean Square Error,RMSE)和决定系数(Coefficient of Determination,R^(2))分别为0.9989和0.3237。文中研究为苹果汁中多菌灵的快速无损检测提供了一种新的方法,对保障食品安全具有重要意义。In this paper,a method for quantitative detection of carbendazim in apple juice based on ultraviolet spectrum and Support Vector Regression(SVR)was proposed.First,the ultraviolet spectra of carbendazim samples of different concentrations in apple juice were collected by ultraviolet visible spectrophotometer,and the original spectra were preprocessed by Savitzky-Golay(S-G)smoothing method.Then,the support vector regression models based on spectral variables were established to realize the quantitative detection of carbendazim in apple juice.Finally,in order to further improve the prediction performance of the model,Particle Swarm Optimization(PSO)were used to optimize the parameters of the support vector regression model.The results show that PSO-SVR model has the best prediction performance,and its prediction set Root Mean Square Error(RMSE)and coefficient of determination(R^(2))were 0.9989 and 0.3237,respectively.This study provides a new method for rapid nondestructive detection of carbendazim in apple juice,which is of great significance for food safety.

关 键 词：紫外光谱 支持向量回归 粒子群优化算法 农药残留 

分 类 号：O657.32[理学—分析化学]