基于太赫兹光谱技术与CS-SVM的转基因产品鉴别

提出了一种基于太赫兹(THz)光谱技术以及布谷鸟搜索(CS)算法优化支持向量机(SVM)的有效的转基因产品鉴别方法(CS-SVM)。实验采用太赫兹时域光谱(THz-TDS)系统测量了三种转基因大豆种子及其亲本样品在0.2~1.2 THz波段的THz光谱，并采用SVM方法对转基因和非转基因大豆种子进行了分类鉴别研究，其中SVM的两个重要参数(惩罚因子和核参数)采用CS算法进行优化。实验结果表明，应用THz光谱技术结合CS-SVM方法为转基因和非转基因生物的检测和识别提供了一种快速、无损和可靠的分析方法。

Discrimination of GMOs Using Terahertz Spectroscopy and CS-SVM

This paper develops an effective identification method to discriminate genetical ly modified (GM) and non-GM organisms.The method is proposed based on terahert z (THz) spectroscopy and support vector machines optimized by Cuckoo Search algo rithm (CS-SVM).In this study,the THz spectra of three GM and non-GM soya see d samples were obtained by using terahertz time-domain spectroscopy (THz-TDS) system between 0.2 and 1.2 THz.Then,the SVM model is employed to disting uish GM and non-GM soya seeds,in which the two crucial parameters,including the p enalty factor and kernel parameter,are optimized by CS algorithm.The exper imen tal results show that THz spectroscopy combined with CS-SVM can provide a rapid,reliable and non-invasive method for GMOs and non-GMOs discrimination.