Discriminating the Genuineness of Chinese Medicines Using Least Squares Support Vector Machines

Abstract A method for the rapid identification of the genuineness of Chinese medicines based on near infrared (NIR) spectroscopy and least squares support vector machines (LSSVM) was proposed. In this study, NIR spectra of the powdered Danshen ( Radix Salviae Miltiorrhizae ) were collected, and the nonlinear classifier based on LSSVM algorithm was developed to discriminate the genuineness of these herbs. The result obtained by the proposed method was compared with those from the traditional support vector machines (SVM) and BP-ANN methods. It was shown that the generalization performance of the classifier based on LSSVM was much better than that of BP-ANN, and the computation time of LSSVM was much shorter than that of the traditional SVM. The proposed method could be applied to the rapid and accurate identification of the quality of the natural products.