【摘要】 支持向量机(SVM)是根据统计理论提出的一种新的学习算法。文章以40个西洋参样品为实验材料,通过FTIR-SVM建立了西洋参样品与籽播参识别的模型。对学习训练集中的30个样品模型识别率为100%,对10个预测样品的识别准确率为90%。研究结果表明,FTIR-SVM可以用于中药西洋参与籽播参的区别。更多还原

【Abstract】 The support vector machine(SVM) is a new learning technique based on the statistical learning theory.In the present paper,forty Panax quinquefolium L.samples were used as experimental materials.The classification models were established using Fourier transform infrared spectra(FTIR)-SVM training method with the intention of identifying whether the Panax quinquefolium L.samples are genuine or they are just Panax ginseng C.A.Mey.samples.The thirty samples in training set were identified by the classifying models with an accurate rate of 100%,while the ten estimate samples had an accurate rate of 90%.The research result shows the feasibility of establishing the models with FTIR-SVM method to identify Panax quinquefolium L.samples and Panax ginseng C.A.Mey.更多还原