论文部分内容阅读
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0.2~1.2THz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。
An effective transgenic product identification method (CS-SVM) based on THz spectroscopy and the Cuckoo Search (CS) algorithm to optimize Support Vector Machine (SVM) is proposed. The THz spectra of three genetically modified soybean seeds and their parent samples in the band of 0.2-1.2 THz were measured by THz-TDS system. The classification of transgenic and non-transgenic soybean seeds was carried out by using SVM , Of which two important parameters of SVM (penalty factor and kernel parameter) are optimized by CS algorithm. The experimental results show that the application of THz spectroscopy combined with CS-SVM method provides a fast, non-destructive and reliable method for the detection and identification of transgenic and non-transgenic organisms.