基于主动标记支持向量机和太赫兹光谱的转基因物质检测方法研究

Detection method of genetically modified substances based on active label support vector machine and terahertz spectroscopy

为克服传统支持向量机需要事先对训练样本进行人为标记的缺点,提出了一种主动训练支持向量机模型。利用仿射传播聚类算法对未标记样本进行聚类分析,在迭代过程中不断更新现有支持向量机的训练数据,从而不仅可以减少人为标记样本所带来的误差,还能够最大限度地提高模型的识别准确率。本文以转基因棉花的太赫兹光谱数据为研究对象对该模型进行了验证,实验结果表明,本文提出的方法对总待测样品的种类的识别率为95.56%,较其他三种方法有较少的误判和更高的识别率。基于仿射传播聚类的支持向量机较传统支持向量机有更高的识别率和更低的误判率,为转基因物质的检测提供了一种快速,无损的新方法。

In order to overcome the shortcomings of the traditional support vector machines that the train- ing samples should be labeled artificially this paper proposes an active training support vector machine model which uses affine propagation clustering algorithm to cluster unlabeled samples. The model does not need to manually label training samples, but updates the training data of existing support vector ma- chines in the iterative process,so it can not only reduce the error caused by artificial marking samples, but also maximize the accuracy of the recognition model. In this paper, the terahertz spectra data of transgenic cotton are taken as the research object to verify the model. The recognition rate of the method is 95.56% for the total sample to be tested,which has less false and higher recognition rate than the other three methods. The results of experiment show that the support vector machine based on affine propagation clustering has higher recognition rate and lower misjudgment rate than the traditional sup- port vector machine and it provides a fast and nondestructive method for the detection of genetically modified substances.