采用太赫兹时域光谱(THz-TDS)技术对2种常见消炎用粉针类药品和4种胶囊、片剂、冲剂类药品进行实验研究并得到它们在0.2～2 THz频率范围的特征吸收光谱, 对这些光谱进行了分析比较, 用支持向量机(SVM)对太赫兹吸收光谱进行了识别分类。首先, 用归一化预处理后的6种药品的太赫兹吸收光谱训练libsvm模型; 然后, 选用与训练光谱不同时间测得的6种药品太赫兹吸收光谱作为检测光谱, 经过归一化预处理后分别输入到训练好的libsvm模型中进行识别。研究表明, 各种药物由于其化学成分的不同, 显示出不同的太赫兹吸收光谱。用支持向量机可以实现对不同种类药品的识别。这些结果为太赫兹光谱技术用于药品的检测和识别提供了另一种有效的方法。

On the base of absorption spectra obtained in the range from 0.2 to 2 THz of six different medicines using terahertz time-domain spectroscopy (THz-TDS) technique, the THz absorption spectra of medicines were identified successfully by support vector machines (SVM). Firstly, absorption spectra of the six different medicines, which were pretreated by normalized unit, were used to train libsvm program. Secondly, absorption spectra of the medicines which were measured on different date, pretreated by normalized unit too, were identified by the libsvm and the identification rate of 100% was achieved. The results indicated that it is feasible to apply SVM on identification of medicines and providing an effective method in the secure inspection and identification for medicines.