基于近红外光谱和LSSVM方法的转基因大米鉴别研究  

Study on identification of genetically modified rice by using near-infrared spectroscopy combined with LSSVM

作　　者：郝勇 温钦华[1] 罗秋红 饶敏 陈斌 

机构地区：[1]华东交通大学机电与车辆工程学院,江西南昌330013 [2]江苏大学食品与生物工程学院,江苏镇江212013 [3]赣州出入境检验检疫局,江西赣州341000

出　　处：《食品工业科技》2017年第22期242-245,共4页Science and Technology of Food Industry

基　　金：国家自然科学基金项目(21265006)

摘　　要：采用近红外漫反射光谱结合主成分分析(principal component analysis,PCA)和最小二乘支持向量机(least squares support vector machine,LSSVM)研究转基因大米的鉴别方法。采用PCA方法分析大米样品光谱空间分布;不同的光谱预处理方法:5点平滑、多元散射校正(multiplicative scatter correction,MSC)和标准正态变量变换(standard normal variate transformation,SNV)结合LSSVM用于定性判别模型的建立和优化;采用格点搜索方法对LSSVM模型的惩罚因子(c)和径向基核函数宽度(g)进行优化;正确识别率(correct recognition rate,CRR)用于判别模型的评价。结果表明:MSC结合LSSVM可用于转基因大米定性判别模型的建立,最优模型的CRR为97.50%。该方法有望成为转基因食品快速鉴别的一种辅助方法。Near-infrared diffuse reflectance spectroscopy（NIDRS） combined with principal component analysis（PCA） and least squares support vector machine （LSSVM）were used for the identification of transgenic rice. PCA was used to analyze the spectral spatial distribution of rice. Different spectral preprocessing methods including 5- point smoothing, multivariate scatter correction（MSC） and standard normal variate transformation（SNV） combined with LSSVM were used to build and optimize qualitative models.The grid search algorithm was employed to obtain the optimal solution of the penalty factor （ c ） and the parameters gamma（g）of RBF kernel.The correct recognition rate（CRR） were used to evaluate models.The results showed that MSC combined with LSSVM could be used to establish the qualitative identification model of transgenic rice.The CRR of the optimal model was 97.50%.The method was expected to be an auxiliary method for rapid detection of genetically modified foods.

关 键 词：近红外光谱 转基因大米 主成分分析 最小二乘支持向量机 

分 类 号：TS201.1[轻工技术与工程—食品科学]