中文摘要：本文提出了一种利用太赫兹光谱和化学计量学技术从非转基因甘蔗中鉴定转基因甘蔗的方法，包括线性判别分析（LDA）、支持向量机判别分析（SVM DA）和偏最小二乘判别分析（PLS-DA）。作者比较了上述方法的分类率，并考虑了不同类型的预处理。研究发现，最佳判别分析方法为偏最小二乘判别分析（PLS-DA），识别率为98%。研究结果表明，THz光谱和化学计量学技术是鉴定转基因和非转基因甘蔗的有力工具。
 
外文摘要：A methodology is proposed to identify genetically modified sugarcane from non-genetically modified sugarcane by using terahertz spectroscopy and chemometrics techniques, including linear discriminant analysis (LDA), support vector machine-discriminant analysis (SVM-DA), and partial least squares-discriminant analysis (PLS-DA). The classification rate of the above mentioned methods is compared, and different types of preprocessing are considered. According to the experimental results, the best option is PLS-DA, with an identification rate of 98%. The results indicated that THz spectroscopy and chemometrics techniques are a powerful tool to identify genetically modified and non-genetically modified sugarcane.
 
外文关键词：terahertz spectroscopy, genetically modified, spectroscopy, chemometrics
作者：Liu, J.; Xie, H.; Zha, B.; Ding, W.; Luo, J.; Hu, C.
作者单位：Southwest Univ
期刊名称：JOURNAL OF APPLIED SPECTROSCOPY
期刊影响因子：0.572
出版年份：2018
出版刊次：5
点击下载：基于太赫兹光谱和化学计量学的转基因甘蔗检测研究