Research of Drug Types Based on Raman Spectroscopy and PCA-KNN Algorithm

As the number of synthetic drug abusers in China rising, problems and phenomena were encountered in practical use. A rapid and convenient method for the identification of methcathinone and ephedrine was needed. In this paper, Ion mobility spectrometry (IMS) and Raman spectroscopy were used in combination to characterize methcathinone and ephedrine from different sources. We use spectral data fusion combined with Principal Components Analysis (PCA) and K-Nearest Neighbors (KNN) algorithm to identify the two types of drugs. The experimental data show that the fusion data compared to the single spectral data were used to identify and effectively improve the recognition rate and accuracy for the identification of drugs. The results from this study demonstrated that the Raman-IMS combined with PCA-KNN model can used as a safe, rapid and reliable analysis method for identification of drugs.