基于太赫兹时域光谱的芝麻油品种识别研究

Identification of Sesame Oil Varieties Based on Terahertz Time Domain Spectroscopy

为了实现对芝麻油品种的快速鉴别,本文基于太赫兹时域光谱(THz-TDS)提出一种芝麻油品种识别的方法。选取0~2.5 THz范围内的光谱进行分析,通过主成分分析法(PCA)对时域光谱数据进行降维,选择前4个主成分(累计贡献率大于99%)代表原始数据,然后利用支持向量机(SVM)方法对不同品种芝麻油进行分类识别,分类时使用3种不同的核函数建模,并采用网格搜索算法获得最优模型及其模型参数。使用径向基核函数(参数为惩罚函数C=0.01,核函数系数γ=0.1)的模型识别率最高,达到100%,说明太赫兹时域光谱技术结合PCA和SVM方法可以快速可靠的进行食用油的识别,为食品安全的识别提供一种新的技术手段。

In order to realize the rapid identification of sesame oil varieties,this paper proposed a method for sesame oil variety identification based on terahertz time domain spectroscopy( THz-TDS).The spectrum in the range of 0~2.5 THz was selected for analysis,and the time domain spectral data was reduced by principal component analysis( PCA). The first four principal components( cumulative contribution rate was over than 99%) were selected to represent the original data,and then the support vector machine( SVM) method was used to classify and identify different varieties of sesame oil.Three different kernel functions were used for classification,and the grid model was used to obtain the optimal model and its model parameters.Using the radial basis kernel function( parameter penalty function C = 0.01,kernel function coefficient γ = 0.1),the model recognition rate was the highest,reaching 100%.It indicated that the terahertz time domain spectroscopy technology combined with PCA and SVM methods could be quickly and reliably consumed,providing a new technical means for the identification of food safety.