应用同步荧光光谱和支持向量机快速鉴别油茶籽油真伪

Identification of authenticity of Camellia oleif era seed oil by using synchronous fluorescence spectroscopy with support vector machines

为快速鉴别油茶籽油真伪,采用同步荧光光谱和支持向量机建立油茶籽油真伪鉴别模型。结果表明,原始同步荧光光谱通过标准归一化(SNV)预处理,经过主成分分析提取5个主成分,选用径向基函数(RBF)作为核函数,采用经网格搜索和交叉验证优化得到的两个建模参数惩罚因子C=0.5和核参数γ=0.0313,建立的模型最佳。该模型对训练集和预测集的判别率均可达到100%。说明采用同步荧光光谱结合支持向量机可以快速、准确地鉴别油茶籽油真伪。

To identify authenticity of Camellia oleif era seed oil quickly,the model was built up by using synchronous fluorescence spectroscopy with support vector machines（SVM）.The experimental results showed that the best model was established by the standard normal variate（SNV） preprocessing,when 5 principal components were selected and the radial basis function（RBF） was used as the kernel function and the optimal penalty factor C and kernel function γ were 0.5 and 0.0313 respectively obtained by the grid searching and cross validation.The discriminate rate of the model was 100% for both training sets and prediction sets.Thus,it was quick and accurate to apply synchronous fluorescence spectroscopy to discriminate the authenticity of Camellia oleif era seed oil based on SVM.