基于太赫兹光谱和机器学习算法的二元及三元混合物定量分析

Quantitative Analysis of Binary and Ternary Mixtures Based on Terahertz Spectroscopy and Machine Learning Algorithm

利用太赫兹时域光谱系统测量了苯甲酸、山梨酸、木糖醇3种常用食品添加剂及其混合物的太赫兹吸收光谱,并选取了偏最小二乘回归(PLS)、最小二乘支持向量机(LSSVM)及反向传播神经网络(BPNN)3种机器学习算法,对食品添加剂二元及三元混合物进行了定量分析。研究发现,在多元混合物的定量分析中,非线性模型LSSVM及BPNN较线性模型PLS更具优势,且随着混合物成分的增加,非线性模型的优势愈趋明显;两种非线性模型中,LSSVM较BPNN建模步骤固定,无需进行复杂的参数讨论与优化,可高效地实现多元混合物的定量分析;此外,观察分析物光谱特征发现,除算法适用性讨论外,分析物的光谱特征也会在一定程度上影响定量检测的精度。

In this paper,we use the terahertz timedomain spectroscopy system to measure the terahertz absorption spectra of three common food additives,namely,benzoic acid,sorbic acid,and xylitol,along with their mixtures.In addition,we select three machine learning algorithms to analyze the binary and ternary mixtures of food additives,namely,the partial least squares regression(PLS),the least squares support vector machine(LSSVM),and the backpropagation neural network(BPNN).We find that in the quantitative analysis of multivariate mixtures,the nonlinear models LSSVM and BPNN are more advantageous than the linear model PLS.As the mixture composition increased,the advantages of using a nonlinear model for analysis become more obvious.Among the two nonlinear models,we find that LSSVM has a fixed modeling step compared with that of BPNN and does not require complicated parameter discussion and optimization,which can efficiently realize the quantitative analysis of multivariate mixtures.Moreover,by observing the spectral characteristics of the analyte,it is found that in addition to the discussion of the applicability of the algorithm,the spectral characteristics of the analyte also affect the accuracy of quantitative detection to a certain extent.